Discussion:
[PATCH V3 0/8] MIPS: Loongson-3: Add NUMA and Loongson-3B support
Huacai Chen
2014-06-26 03:41:24 UTC
Permalink
This patchset is prepared for the next 3.17 release for Linux/MIPS. In
this series we add NUMA and Loongson-3B support. Multiple Loongson-3A
chips can be interconnected with HT0-bus. This is a CC-NUMA system that
every chip (node) has its own local memory and cache coherency is
maintained by hardware. Loongson-3B is a 8-cores processor which looks
like there are two Loongson-3A integrated in one chip: 8 cores are
separated into two groups (two NUMA node).

V1 -> V2:
1, Rework the first patch.
2, Use compat numa-related syscall for N32/O32 ABI.
3, Drop the patch "MIPS: Loongson: Make CPU name more clear".

V2 -> V3:
1, Rebase the code for 3.17.
2, Reviewed by Andreas Herrmann.
3, Rework the patch "MIPS: Add NUMA support for Loongson-3".

Huacai Chen(8):
MIPS: Support hard limit of cpu count (nr_cpu_ids).
MIPS: Support CPU topology files in sysfs.
MIPS: Loongson: Modify ChipConfig register definition.
MIPS: Add NUMA support for Loongson-3.
MIPS: Add numa api support.
MIPS: Add Loongson-3B support.
MIPS: Loongson-3: Enable the COP2 usage.
MIPS: Loongson: Rename CONFIG_LEMOTE_MACH3A to CONFIG_LOONGSON_MACH3X.

Signed-off-by: Huacai Chen <***@lemote.com>
Signed-off-by: Hongliang Tao <***@lemote.com>
Signed-off-by: Hua Yan <***@lemote.com>
---
arch/mips/configs/loongson3_defconfig | 2 +-
arch/mips/include/asm/addrspace.h | 2 +-
arch/mips/include/asm/cop2.h | 8 +
arch/mips/include/asm/cpu-info.h | 1 +
arch/mips/include/asm/cpu.h | 2 +
arch/mips/include/asm/mach-loongson/boot_param.h | 4 +
.../include/asm/mach-loongson/kernel-entry-init.h | 52 +++
arch/mips/include/asm/mach-loongson/loongson.h | 11 +-
arch/mips/include/asm/mach-loongson/machine.h | 4 +-
arch/mips/include/asm/mach-loongson/mmzone.h | 53 +++
arch/mips/include/asm/mach-loongson/topology.h | 23 ++
arch/mips/include/asm/smp.h | 6 +
arch/mips/include/asm/sparsemem.h | 2 +-
arch/mips/kernel/cpu-probe.c | 6 +
arch/mips/kernel/proc.c | 1 +
arch/mips/kernel/scall32-o32.S | 4 +-
arch/mips/kernel/scall64-64.S | 4 +-
arch/mips/kernel/scall64-n32.S | 10 +-
arch/mips/kernel/scall64-o32.S | 8 +-
arch/mips/kernel/setup.c | 22 +-
arch/mips/kernel/smp.c | 26 ++-
arch/mips/loongson/Kconfig | 9 +-
arch/mips/loongson/Platform | 2 +-
arch/mips/loongson/common/env.c | 49 +++-
arch/mips/loongson/common/init.c | 4 +
arch/mips/loongson/common/pm.c | 8 +-
arch/mips/loongson/lemote-2f/clock.c | 4 +-
arch/mips/loongson/lemote-2f/reset.c | 2 +-
arch/mips/loongson/loongson-3/Makefile | 4 +-
arch/mips/loongson/loongson-3/cop2-ex.c | 63 ++++
arch/mips/loongson/loongson-3/irq.c | 26 +-
arch/mips/loongson/loongson-3/numa.c | 291 +++++++++++++++
arch/mips/loongson/loongson-3/smp.c | 387 +++++++++++++++-----
arch/mips/loongson/loongson-3/smp.h | 37 +-
arch/mips/pci/Makefile | 2 +-
drivers/cpufreq/loongson2_cpufreq.c | 6 +-
36 files changed, 986 insertions(+), 159 deletions(-)
create mode 100644 arch/mips/include/asm/mach-loongson/kernel-entry-init.h
create mode 100644 arch/mips/include/asm/mach-loongson/mmzone.h
create mode 100644 arch/mips/include/asm/mach-loongson/topology.h
create mode 100644 arch/mips/loongson/loongson-3/cop2-ex.c
create mode 100644 arch/mips/loongson/loongson-3/numa.c
--
1.7.7.3
Huacai Chen
2014-06-26 03:41:25 UTC
Permalink
On MIPS currently, only the soft limit of cpu count (maxcpus) has its
effect, this patch enable the hard limit (nr_cpus) as well. Processor
cores which greater than maxcpus and less than nr_cpus can be taken up
via cpu hotplug. The code is borrowed from X86.

Signed-off-by: Huacai Chen <***@lemote.com>
Reviewed-by: Andreas Herrmann <***@caviumnetworks.com>
---
arch/mips/kernel/setup.c | 20 ++++++++++++++++++++
1 files changed, 20 insertions(+), 0 deletions(-)

diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index a842154..2f01201 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -729,6 +729,25 @@ static void __init resource_init(void)
}
}

+#ifdef CONFIG_SMP
+static void __init prefill_possible_map(void)
+{
+ int i, possible = num_possible_cpus();
+
+ if (possible > nr_cpu_ids)
+ possible = nr_cpu_ids;
+
+ for (i = 0; i < possible; i++)
+ set_cpu_possible(i, true);
+ for (; i < NR_CPUS; i++)
+ set_cpu_possible(i, false);
+
+ nr_cpu_ids = possible;
+}
+#else
+static inline void prefill_possible_map(void) {}
+#endif
+
void __init setup_arch(char **cmdline_p)
{
cpu_probe();
@@ -752,6 +771,7 @@ void __init setup_arch(char **cmdline_p)

resource_init();
plat_smp_setup();
+ prefill_possible_map();

cpu_cache_init();
}
--
1.7.7.3
Huacai Chen
2014-06-26 03:41:26 UTC
Permalink
This post might be inappropriate. Click to display it.
Huacai Chen
2014-06-26 03:41:27 UTC
Permalink
This patch is prepared for Multi-chip interconnection. Since each chip
has a ChipConfig register, LOONGSON_CHIPCFG should be an array.

Signed-off-by: Huacai Chen <***@lemote.com>
---
arch/mips/include/asm/mach-loongson/loongson.h | 7 +++++--
arch/mips/loongson/common/env.c | 11 +++++++++++
arch/mips/loongson/common/pm.c | 8 ++++----
arch/mips/loongson/lemote-2f/clock.c | 4 ++--
arch/mips/loongson/lemote-2f/reset.c | 2 +-
arch/mips/loongson/loongson-3/smp.c | 4 ++--
drivers/cpufreq/loongson2_cpufreq.c | 6 +++---
7 files changed, 28 insertions(+), 14 deletions(-)

diff --git a/arch/mips/include/asm/mach-loongson/loongson.h b/arch/mips/include/asm/mach-loongson/loongson.h
index f3fd1eb..a1c76ca 100644
--- a/arch/mips/include/asm/mach-loongson/loongson.h
+++ b/arch/mips/include/asm/mach-loongson/loongson.h
@@ -249,8 +249,11 @@ static inline void do_perfcnt_IRQ(void)
#define LOONGSON_PXARB_CFG LOONGSON_REG(LOONGSON_REGBASE + 0x68)
#define LOONGSON_PXARB_STATUS LOONGSON_REG(LOONGSON_REGBASE + 0x6c)

-/* Chip Config */
-#define LOONGSON_CHIPCFG0 LOONGSON_REG(LOONGSON_REGBASE + 0x80)
+#define MAX_PACKAGES 4
+
+/* Chip Config registor of each physical cpu package, PRid >= Loongson-2F */
+extern u64 loongson_chipcfg[MAX_PACKAGES];
+#define LOONGSON_CHIPCFG(id) (*(volatile u32 *)(loongson_chipcfg[id]))

/* pcimap */

diff --git a/arch/mips/loongson/common/env.c b/arch/mips/loongson/common/env.c
index 0c543ea..dc59241 100644
--- a/arch/mips/loongson/common/env.c
+++ b/arch/mips/loongson/common/env.c
@@ -27,6 +27,8 @@ EXPORT_SYMBOL(cpu_clock_freq);
struct efi_memory_map_loongson *loongson_memmap;
struct loongson_system_configuration loongson_sysconf;

+u64 loongson_chipcfg[MAX_PACKAGES] = {0xffffffffbfc00180};
+
#define parse_even_earlier(res, option, p) \
do { \
unsigned int tmp __maybe_unused; \
@@ -77,6 +79,15 @@ void __init prom_init_env(void)

cpu_clock_freq = ecpu->cpu_clock_freq;
loongson_sysconf.cputype = ecpu->cputype;
+ if (ecpu->cputype == Loongson_3A) {
+ loongson_chipcfg[0] = 0x900000001fe00180;
+ loongson_chipcfg[1] = 0x900010001fe00180;
+ loongson_chipcfg[2] = 0x900020001fe00180;
+ loongson_chipcfg[3] = 0x900030001fe00180;
+ } else {
+ loongson_chipcfg[0] = 0x900000001fe00180;
+ }
+
loongson_sysconf.nr_cpus = ecpu->nr_cpus;
if (ecpu->nr_cpus > NR_CPUS || ecpu->nr_cpus == 0)
loongson_sysconf.nr_cpus = NR_CPUS;
diff --git a/arch/mips/loongson/common/pm.c b/arch/mips/loongson/common/pm.c
index f55e07a..a6b67cc 100644
--- a/arch/mips/loongson/common/pm.c
+++ b/arch/mips/loongson/common/pm.c
@@ -79,7 +79,7 @@ int __weak wakeup_loongson(void)
static void wait_for_wakeup_events(void)
{
while (!wakeup_loongson())
- LOONGSON_CHIPCFG0 &= ~0x7;
+ LOONGSON_CHIPCFG(0) &= ~0x7;
}

/*
@@ -102,15 +102,15 @@ static void loongson_suspend_enter(void)

stop_perf_counters();

- cached_cpu_freq = LOONGSON_CHIPCFG0;
+ cached_cpu_freq = LOONGSON_CHIPCFG(0);

/* Put CPU into wait mode */
- LOONGSON_CHIPCFG0 &= ~0x7;
+ LOONGSON_CHIPCFG(0) &= ~0x7;

/* wait for the given events to wakeup cpu from wait mode */
wait_for_wakeup_events();

- LOONGSON_CHIPCFG0 = cached_cpu_freq;
+ LOONGSON_CHIPCFG(0) = cached_cpu_freq;
mmiowb();
}

diff --git a/arch/mips/loongson/lemote-2f/clock.c b/arch/mips/loongson/lemote-2f/clock.c
index 1eed38e..a217061 100644
--- a/arch/mips/loongson/lemote-2f/clock.c
+++ b/arch/mips/loongson/lemote-2f/clock.c
@@ -114,9 +114,9 @@ int clk_set_rate(struct clk *clk, unsigned long rate)

clk->rate = rate;

- regval = LOONGSON_CHIPCFG0;
+ regval = LOONGSON_CHIPCFG(0);
regval = (regval & ~0x7) | (pos->driver_data - 1);
- LOONGSON_CHIPCFG0 = regval;
+ LOONGSON_CHIPCFG(0) = regval;

return ret;
}
diff --git a/arch/mips/loongson/lemote-2f/reset.c b/arch/mips/loongson/lemote-2f/reset.c
index 90962a3..79ac694 100644
--- a/arch/mips/loongson/lemote-2f/reset.c
+++ b/arch/mips/loongson/lemote-2f/reset.c
@@ -28,7 +28,7 @@ static void reset_cpu(void)
* reset cpu to full speed, this is needed when enabling cpu frequency
* scalling
*/
- LOONGSON_CHIPCFG0 |= 0x7;
+ LOONGSON_CHIPCFG(0) |= 0x7;
}

/* reset support for fuloong2f */
diff --git a/arch/mips/loongson/loongson-3/smp.c b/arch/mips/loongson/loongson-3/smp.c
index 1e88940..3c320e7 100644
--- a/arch/mips/loongson/loongson-3/smp.c
+++ b/arch/mips/loongson/loongson-3/smp.c
@@ -399,12 +399,12 @@ static int loongson3_cpu_callback(struct notifier_block *nfb,
case CPU_POST_DEAD:
case CPU_POST_DEAD_FROZEN:
pr_info("Disable clock for CPU#%d\n", cpu);
- LOONGSON_CHIPCFG0 &= ~(1 << (12 + cpu));
+ LOONGSON_CHIPCFG(0) &= ~(1 << (12 + cpu));
break;
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
pr_info("Enable clock for CPU#%d\n", cpu);
- LOONGSON_CHIPCFG0 |= 1 << (12 + cpu);
+ LOONGSON_CHIPCFG(0) |= 1 << (12 + cpu);
break;
}

diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c
index d4add86..9fa1772 100644
--- a/drivers/cpufreq/loongson2_cpufreq.c
+++ b/drivers/cpufreq/loongson2_cpufreq.c
@@ -148,9 +148,9 @@ static void loongson2_cpu_wait(void)
u32 cpu_freq;

spin_lock_irqsave(&loongson2_wait_lock, flags);
- cpu_freq = LOONGSON_CHIPCFG0;
- LOONGSON_CHIPCFG0 &= ~0x7; /* Put CPU into wait mode */
- LOONGSON_CHIPCFG0 = cpu_freq; /* Restore CPU state */
+ cpu_freq = LOONGSON_CHIPCFG(0);
+ LOONGSON_CHIPCFG(0) &= ~0x7; /* Put CPU into wait mode */
+ LOONGSON_CHIPCFG(0) = cpu_freq; /* Restore CPU state */
spin_unlock_irqrestore(&loongson2_wait_lock, flags);
local_irq_enable();
}
--
1.7.7.3
Huacai Chen
2014-06-26 03:41:29 UTC
Permalink
Enable sys_mbind()/sys_get_mempolicy()/sys_set_mempolicy() for O32, N32,
and N64 ABIs. By the way, O32/N32 should use the compat version of
sys_migrate_pages()/sys_move_pages(), so fix that.

Signed-off-by: Huacai Chen <***@lemote.com>
---
arch/mips/kernel/scall32-o32.S | 4 ++--
arch/mips/kernel/scall64-64.S | 4 ++--
arch/mips/kernel/scall64-n32.S | 10 +++++-----
arch/mips/kernel/scall64-o32.S | 8 ++++----
4 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 3245474..6bfdc82 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -495,8 +495,8 @@ EXPORT(sys_call_table)
PTR sys_tgkill
PTR sys_utimes
PTR sys_mbind
- PTR sys_ni_syscall /* sys_get_mempolicy */
- PTR sys_ni_syscall /* 4270 sys_set_mempolicy */
+ PTR sys_get_mempolicy
+ PTR sys_set_mempolicy /* 4270 */
PTR sys_mq_open
PTR sys_mq_unlink
PTR sys_mq_timedsend
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index be2fedd..0952139 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -347,8 +347,8 @@ EXPORT(sys_call_table)
PTR sys_tgkill /* 5225 */
PTR sys_utimes
PTR sys_mbind
- PTR sys_ni_syscall /* sys_get_mempolicy */
- PTR sys_ni_syscall /* sys_set_mempolicy */
+ PTR sys_get_mempolicy
+ PTR sys_set_mempolicy
PTR sys_mq_open /* 5230 */
PTR sys_mq_unlink
PTR sys_mq_timedsend
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index c1dbcda..7641c87 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -339,9 +339,9 @@ EXPORT(sysn32_call_table)
PTR compat_sys_clock_nanosleep
PTR sys_tgkill
PTR compat_sys_utimes /* 6230 */
- PTR sys_ni_syscall /* sys_mbind */
- PTR sys_ni_syscall /* sys_get_mempolicy */
- PTR sys_ni_syscall /* sys_set_mempolicy */
+ PTR compat_sys_mbind
+ PTR compat_sys_get_mempolicy
+ PTR compat_sys_set_mempolicy
PTR compat_sys_mq_open
PTR sys_mq_unlink /* 6235 */
PTR compat_sys_mq_timedsend
@@ -358,7 +358,7 @@ EXPORT(sysn32_call_table)
PTR sys_inotify_init
PTR sys_inotify_add_watch
PTR sys_inotify_rm_watch
- PTR sys_migrate_pages /* 6250 */
+ PTR compat_sys_migrate_pages /* 6250 */
PTR sys_openat
PTR sys_mkdirat
PTR sys_mknodat
@@ -379,7 +379,7 @@ EXPORT(sysn32_call_table)
PTR sys_sync_file_range
PTR sys_tee
PTR compat_sys_vmsplice /* 6270 */
- PTR sys_move_pages
+ PTR compat_sys_move_pages
PTR compat_sys_set_robust_list
PTR compat_sys_get_robust_list
PTR compat_sys_kexec_load
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index f1343cc..18cfa11 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -473,9 +473,9 @@ EXPORT(sys32_call_table)
PTR compat_sys_clock_nanosleep /* 4265 */
PTR sys_tgkill
PTR compat_sys_utimes
- PTR sys_ni_syscall /* sys_mbind */
- PTR sys_ni_syscall /* sys_get_mempolicy */
- PTR sys_ni_syscall /* 4270 sys_set_mempolicy */
+ PTR compat_sys_mbind
+ PTR compat_sys_get_mempolicy
+ PTR compat_sys_set_mempolicy /* 4270 */
PTR compat_sys_mq_open
PTR sys_mq_unlink
PTR compat_sys_mq_timedsend
@@ -492,7 +492,7 @@ EXPORT(sys32_call_table)
PTR sys_inotify_init
PTR sys_inotify_add_watch /* 4285 */
PTR sys_inotify_rm_watch
- PTR sys_migrate_pages
+ PTR compat_sys_migrate_pages
PTR compat_sys_openat
PTR sys_mkdirat
PTR sys_mknodat /* 4290 */
--
1.7.7.3
Huacai Chen
2014-06-26 03:41:28 UTC
Permalink
Multiple Loongson-3A chips can be interconnected with HT0-bus. This is
a CC-NUMA system that every chip (node) has its own local memory and
cache coherency is maintained by hardware. The 64-bit physical memory
address format is as follows:

0x-0000-YZZZ-ZZZZ-ZZZZ

The high 16 bits should be 0, which means the real physical address
supported by Loongson-3 is 48-bit. The "Y" bits is the base address of
each node, which can be also considered as the node-id. The "Z" bits is
the address offset within a node, which means every node has a 44 bits
address space.

Macros XPHYSADDR and MAX_PHYSMEM_BITS are modified unconditionally,
because many other MIPS CPUs have also extended their address spaces.

Signed-off-by: Huacai Chen <***@lemote.com>
---
arch/mips/include/asm/addrspace.h | 2 +-
arch/mips/include/asm/mach-loongson/boot_param.h | 3 +
.../include/asm/mach-loongson/kernel-entry-init.h | 52 ++++
arch/mips/include/asm/mach-loongson/mmzone.h | 53 ++++
arch/mips/include/asm/mach-loongson/topology.h | 23 ++
arch/mips/include/asm/sparsemem.h | 2 +-
arch/mips/kernel/setup.c | 2 +-
arch/mips/loongson/Kconfig | 1 +
arch/mips/loongson/common/env.c | 7 +
arch/mips/loongson/common/init.c | 4 +
arch/mips/loongson/loongson-3/Makefile | 2 +
arch/mips/loongson/loongson-3/numa.c | 291 ++++++++++++++++++++
arch/mips/loongson/loongson-3/smp.c | 8 +-
13 files changed, 445 insertions(+), 5 deletions(-)
create mode 100644 arch/mips/include/asm/mach-loongson/kernel-entry-init.h
create mode 100644 arch/mips/include/asm/mach-loongson/mmzone.h
create mode 100644 arch/mips/include/asm/mach-loongson/topology.h
create mode 100644 arch/mips/loongson/loongson-3/numa.c

diff --git a/arch/mips/include/asm/addrspace.h b/arch/mips/include/asm/addrspace.h
index 3f74545..3b0e51d 100644
--- a/arch/mips/include/asm/addrspace.h
+++ b/arch/mips/include/asm/addrspace.h
@@ -52,7 +52,7 @@
*/
#define CPHYSADDR(a) ((_ACAST32_(a)) & 0x1fffffff)
#define XPHYSADDR(a) ((_ACAST64_(a)) & \
- _CONST64_(0x000000ffffffffff))
+ _CONST64_(0x0000ffffffffffff))

#ifdef CONFIG_64BIT

diff --git a/arch/mips/include/asm/mach-loongson/boot_param.h b/arch/mips/include/asm/mach-loongson/boot_param.h
index 829a7ec..8b06c96 100644
--- a/arch/mips/include/asm/mach-loongson/boot_param.h
+++ b/arch/mips/include/asm/mach-loongson/boot_param.h
@@ -146,6 +146,9 @@ struct boot_params {

struct loongson_system_configuration {
u32 nr_cpus;
+ u32 nr_nodes;
+ int cores_per_node;
+ int cores_per_package;
enum loongson_cpu_type cputype;
u64 ht_control_base;
u64 pci_mem_start_addr;
diff --git a/arch/mips/include/asm/mach-loongson/kernel-entry-init.h b/arch/mips/include/asm/mach-loongson/kernel-entry-init.h
new file mode 100644
index 0000000..df5fca8
--- /dev/null
+++ b/arch/mips/include/asm/mach-loongson/kernel-entry-init.h
@@ -0,0 +1,52 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2005 Embedded Alley Solutions, Inc
+ * Copyright (C) 2005 Ralf Baechle (***@linux-mips.org)
+ * Copyright (C) 2009 Jiajie Chen (***@cse.buaa.edu.cn)
+ * Copyright (C) 2012 Huacai Chen (***@lemote.com)
+ */
+#ifndef __ASM_MACH_LOONGSON_KERNEL_ENTRY_H
+#define __ASM_MACH_LOONGSON_KERNEL_ENTRY_H
+
+/*
+ * Override macros used in arch/mips/kernel/head.S.
+ */
+ .macro kernel_entry_setup
+#ifdef CONFIG_CPU_LOONGSON3
+ .set push
+ .set mips64
+ /* Set LPA on LOONGSON3 config3 */
+ mfc0 t0, $16, 3
+ or t0, (0x1 << 7)
+ mtc0 t0, $16, 3
+ /* Set ELPA on LOONGSON3 pagegrain */
+ li t0, (0x1 << 29)
+ mtc0 t0, $5, 1
+ _ehb
+ .set pop
+#endif
+ .endm
+
+/*
+ * Do SMP slave processor setup.
+ */
+ .macro smp_slave_setup
+#ifdef CONFIG_CPU_LOONGSON3
+ .set push
+ .set mips64
+ /* Set LPA on LOONGSON3 config3 */
+ mfc0 t0, $16, 3
+ or t0, (0x1 << 7)
+ mtc0 t0, $16, 3
+ /* Set ELPA on LOONGSON3 pagegrain */
+ li t0, (0x1 << 29)
+ mtc0 t0, $5, 1
+ _ehb
+ .set pop
+#endif
+ .endm
+
+#endif /* __ASM_MACH_LOONGSON_KERNEL_ENTRY_H */
diff --git a/arch/mips/include/asm/mach-loongson/mmzone.h b/arch/mips/include/asm/mach-loongson/mmzone.h
new file mode 100644
index 0000000..37c08a2
--- /dev/null
+++ b/arch/mips/include/asm/mach-loongson/mmzone.h
@@ -0,0 +1,53 @@
+/*
+ * Copyright (C) 2010 Loongson Inc. & Lemote Inc. &
+ * Insititute of Computing Technology
+ * Author: Xiang Gao, ***@ict.ac.cn
+ * Huacai Chen, ***@lemote.com
+ * Xiaofu Meng, Shuangshuang Zhang
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+#ifndef _ASM_MACH_MMZONE_H
+#define _ASM_MACH_MMZONE_H
+
+#include <boot_param.h>
+#define NODE_ADDRSPACE_SHIFT 44
+#define NODE0_ADDRSPACE_OFFSET 0x000000000000UL
+#define NODE1_ADDRSPACE_OFFSET 0x100000000000UL
+#define NODE2_ADDRSPACE_OFFSET 0x200000000000UL
+#define NODE3_ADDRSPACE_OFFSET 0x300000000000UL
+
+#define pa_to_nid(addr) (((addr) & 0xf00000000000) >> NODE_ADDRSPACE_SHIFT)
+
+#define LEVELS_PER_SLICE 128
+
+struct slice_data {
+ unsigned long irq_enable_mask[2];
+ int level_to_irq[LEVELS_PER_SLICE];
+};
+
+struct hub_data {
+ cpumask_t h_cpus;
+ unsigned long slice_map;
+ unsigned long irq_alloc_mask[2];
+ struct slice_data slice[2];
+};
+
+struct node_data {
+ struct pglist_data pglist;
+ struct hub_data hub;
+ cpumask_t cpumask;
+};
+
+extern struct node_data *__node_data[];
+
+#define NODE_DATA(n) (&__node_data[(n)]->pglist)
+#define hub_data(n) (&__node_data[(n)]->hub)
+
+extern void setup_zero_pages(void);
+extern void __init prom_init_numa_memory(void);
+
+#endif /* _ASM_MACH_MMZONE_H */
diff --git a/arch/mips/include/asm/mach-loongson/topology.h b/arch/mips/include/asm/mach-loongson/topology.h
new file mode 100644
index 0000000..5598ba7
--- /dev/null
+++ b/arch/mips/include/asm/mach-loongson/topology.h
@@ -0,0 +1,23 @@
+#ifndef _ASM_MACH_TOPOLOGY_H
+#define _ASM_MACH_TOPOLOGY_H
+
+#ifdef CONFIG_NUMA
+
+#define cpu_to_node(cpu) ((cpu) >> 2)
+#define parent_node(node) (node)
+#define cpumask_of_node(node) (&__node_data[(node)]->cpumask)
+
+struct pci_bus;
+extern int pcibus_to_node(struct pci_bus *);
+
+#define cpumask_of_pcibus(bus) (cpu_online_mask)
+
+extern unsigned char __node_distances[MAX_NUMNODES][MAX_NUMNODES];
+
+#define node_distance(from, to) (__node_distances[(from)][(to)])
+
+#endif
+
+#include <asm-generic/topology.h>
+
+#endif /* _ASM_MACH_TOPOLOGY_H */
diff --git a/arch/mips/include/asm/sparsemem.h b/arch/mips/include/asm/sparsemem.h
index d2da53c..b1071c1 100644
--- a/arch/mips/include/asm/sparsemem.h
+++ b/arch/mips/include/asm/sparsemem.h
@@ -11,7 +11,7 @@
#else
# define SECTION_SIZE_BITS 28
#endif
-#define MAX_PHYSMEM_BITS 35
+#define MAX_PHYSMEM_BITS 48

#endif /* CONFIG_SPARSEMEM */
#endif /* _MIPS_SPARSEMEM_H */
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 2f01201..7c1fe2b 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -282,7 +282,7 @@ static unsigned long __init init_initrd(void)
* Initialize the bootmem allocator. It also setup initrd related data
* if needed.
*/
-#ifdef CONFIG_SGI_IP27
+#if defined(CONFIG_SGI_IP27) || (defined(CONFIG_CPU_LOONGSON3) && defined(CONFIG_NUMA))

static void __init bootmem_init(void)
{
diff --git a/arch/mips/loongson/Kconfig b/arch/mips/loongson/Kconfig
index e6a86cc..a14a50d 100644
--- a/arch/mips/loongson/Kconfig
+++ b/arch/mips/loongson/Kconfig
@@ -79,6 +79,7 @@ config LEMOTE_MACH3A
select SYS_HAS_EARLY_PRINTK
select SYS_SUPPORTS_SMP
select SYS_SUPPORTS_HOTPLUG_CPU
+ select SYS_SUPPORTS_NUMA
select SYS_SUPPORTS_64BIT_KERNEL
select SYS_SUPPORTS_HIGHMEM
select SYS_SUPPORTS_LITTLE_ENDIAN
diff --git a/arch/mips/loongson/common/env.c b/arch/mips/loongson/common/env.c
index dc59241..33a13b9 100644
--- a/arch/mips/loongson/common/env.c
+++ b/arch/mips/loongson/common/env.c
@@ -80,17 +80,24 @@ void __init prom_init_env(void)
cpu_clock_freq = ecpu->cpu_clock_freq;
loongson_sysconf.cputype = ecpu->cputype;
if (ecpu->cputype == Loongson_3A) {
+ loongson_sysconf.cores_per_node = 4;
+ loongson_sysconf.cores_per_package = 4;
loongson_chipcfg[0] = 0x900000001fe00180;
loongson_chipcfg[1] = 0x900010001fe00180;
loongson_chipcfg[2] = 0x900020001fe00180;
loongson_chipcfg[3] = 0x900030001fe00180;
} else {
+ loongson_sysconf.cores_per_node = 1;
+ loongson_sysconf.cores_per_package = 1;
loongson_chipcfg[0] = 0x900000001fe00180;
}

loongson_sysconf.nr_cpus = ecpu->nr_cpus;
if (ecpu->nr_cpus > NR_CPUS || ecpu->nr_cpus == 0)
loongson_sysconf.nr_cpus = NR_CPUS;
+ loongson_sysconf.nr_nodes = (loongson_sysconf.nr_cpus +
+ loongson_sysconf.cores_per_node - 1) /
+ loongson_sysconf.cores_per_node;

loongson_sysconf.pci_mem_start_addr = eirq_source->pci_mem_start_addr;
loongson_sysconf.pci_mem_end_addr = eirq_source->pci_mem_end_addr;
diff --git a/arch/mips/loongson/common/init.c b/arch/mips/loongson/common/init.c
index f37fe54..f6af3ab 100644
--- a/arch/mips/loongson/common/init.c
+++ b/arch/mips/loongson/common/init.c
@@ -30,7 +30,11 @@ void __init prom_init(void)
set_io_port_base((unsigned long)
ioremap(LOONGSON_PCIIO_BASE, LOONGSON_PCIIO_SIZE));

+#ifdef CONFIG_NUMA
+ prom_init_numa_memory();
+#else
prom_init_memory();
+#endif

/*init the uart base address */
prom_init_uart_base();
diff --git a/arch/mips/loongson/loongson-3/Makefile b/arch/mips/loongson/loongson-3/Makefile
index 70152b2..471b0f2a 100644
--- a/arch/mips/loongson/loongson-3/Makefile
+++ b/arch/mips/loongson/loongson-3/Makefile
@@ -4,3 +4,5 @@
obj-y += irq.o

obj-$(CONFIG_SMP) += smp.o
+
+obj-$(CONFIG_NUMA) += numa.o
diff --git a/arch/mips/loongson/loongson-3/numa.c b/arch/mips/loongson/loongson-3/numa.c
new file mode 100644
index 0000000..ca025a6
--- /dev/null
+++ b/arch/mips/loongson/loongson-3/numa.c
@@ -0,0 +1,291 @@
+/*
+ * Copyright (C) 2010 Loongson Inc. & Lemote Inc. &
+ * Insititute of Computing Technology
+ * Author: Xiang Gao, ***@ict.ac.cn
+ * Huacai Chen, ***@lemote.com
+ * Xiaofu Meng, Shuangshuang Zhang
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/module.h>
+#include <linux/nodemask.h>
+#include <linux/swap.h>
+#include <linux/memblock.h>
+#include <linux/bootmem.h>
+#include <linux/pfn.h>
+#include <linux/highmem.h>
+#include <asm/page.h>
+#include <asm/pgalloc.h>
+#include <asm/sections.h>
+#include <linux/bootmem.h>
+#include <linux/init.h>
+#include <linux/irq.h>
+#include <asm/bootinfo.h>
+#include <asm/mc146818-time.h>
+#include <asm/time.h>
+#include <asm/wbflush.h>
+#include <boot_param.h>
+
+static struct node_data prealloc__node_data[MAX_NUMNODES];
+unsigned char __node_distances[MAX_NUMNODES][MAX_NUMNODES];
+struct node_data *__node_data[MAX_NUMNODES];
+EXPORT_SYMBOL(__node_data);
+
+static void enable_lpa(void)
+{
+ unsigned long value;
+
+ value = __read_32bit_c0_register($16, 3);
+ value |= 0x00000080;
+ __write_32bit_c0_register($16, 3, value);
+ value = __read_32bit_c0_register($16, 3);
+ pr_info("CP0_Config3: CP0 16.3 (0x%lx)\n", value);
+
+ value = __read_32bit_c0_register($5, 1);
+ value |= 0x20000000;
+ __write_32bit_c0_register($5, 1, value);
+ value = __read_32bit_c0_register($5, 1);
+ pr_info("CP0_PageGrain: CP0 5.1 (0x%lx)\n", value);
+}
+
+static void cpu_node_probe(void)
+{
+ int i;
+
+ nodes_clear(node_possible_map);
+ nodes_clear(node_online_map);
+ for (i = 0; i < loongson_sysconf.nr_nodes; i++) {
+ node_set_state(num_online_nodes(), N_POSSIBLE);
+ node_set_online(num_online_nodes());
+ }
+
+ pr_info("NUMA: Discovered %d cpus on %d nodes\n",
+ loongson_sysconf.nr_cpus, num_online_nodes());
+}
+
+static int __init compute_node_distance(int row, int col)
+{
+ int package_row = row * loongson_sysconf.cores_per_node /
+ loongson_sysconf.cores_per_package;
+ int package_col = col * loongson_sysconf.cores_per_node /
+ loongson_sysconf.cores_per_package;
+
+ if (col == row)
+ return 0;
+ else if (package_row == package_col)
+ return 40;
+ else
+ return 100;
+}
+
+static void __init init_topology_matrix(void)
+{
+ int row, col;
+
+ for (row = 0; row < MAX_NUMNODES; row++)
+ for (col = 0; col < MAX_NUMNODES; col++)
+ __node_distances[row][col] = -1;
+
+ for_each_online_node(row) {
+ for_each_online_node(col) {
+ __node_distances[row][col] =
+ compute_node_distance(row, col);
+ }
+ }
+}
+
+static unsigned long nid_to_addroffset(unsigned int nid)
+{
+ unsigned long result;
+ switch (nid) {
+ case 0:
+ default:
+ result = NODE0_ADDRSPACE_OFFSET;
+ break;
+ case 1:
+ result = NODE1_ADDRSPACE_OFFSET;
+ break;
+ case 2:
+ result = NODE2_ADDRSPACE_OFFSET;
+ break;
+ case 3:
+ result = NODE3_ADDRSPACE_OFFSET;
+ break;
+ }
+ return result;
+}
+
+static void __init szmem(unsigned int node)
+{
+ u32 i, mem_type;
+ static unsigned long num_physpages = 0;
+ u64 node_id, node_psize, start_pfn, end_pfn, mem_start, mem_size;
+
+ /* Parse memory information and activate */
+ for (i = 0; i < loongson_memmap->nr_map; i++) {
+ node_id = loongson_memmap->map[i].node_id;
+ if (node_id != node)
+ continue;
+
+ mem_type = loongson_memmap->map[i].mem_type;
+ mem_size = loongson_memmap->map[i].mem_size;
+ mem_start = loongson_memmap->map[i].mem_start;
+
+ switch (mem_type) {
+ case SYSTEM_RAM_LOW:
+ start_pfn = ((node_id << 44) + mem_start) >> PAGE_SHIFT;
+ node_psize = (mem_size << 20) >> PAGE_SHIFT;
+ end_pfn = start_pfn + node_psize;
+ num_physpages += node_psize;
+ pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n",
+ (u32)node_id, mem_type, mem_start, mem_size);
+ pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n",
+ start_pfn, end_pfn, num_physpages);
+ add_memory_region((node_id << 44) + mem_start,
+ (u64)mem_size << 20, BOOT_MEM_RAM);
+ memblock_add_node(PFN_PHYS(start_pfn),
+ PFN_PHYS(end_pfn - start_pfn), node);
+ break;
+ case SYSTEM_RAM_HIGH:
+ start_pfn = ((node_id << 44) + mem_start) >> PAGE_SHIFT;
+ node_psize = (mem_size << 20) >> PAGE_SHIFT;
+ end_pfn = start_pfn + node_psize;
+ num_physpages += node_psize;
+ pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n",
+ (u32)node_id, mem_type, mem_start, mem_size);
+ pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n",
+ start_pfn, end_pfn, num_physpages);
+ add_memory_region((node_id << 44) + mem_start,
+ (u64)mem_size << 20, BOOT_MEM_RAM);
+ memblock_add_node(PFN_PHYS(start_pfn),
+ PFN_PHYS(end_pfn - start_pfn), node);
+ break;
+ case MEM_RESERVED:
+ pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n",
+ (u32)node_id, mem_type, mem_start, mem_size);
+ add_memory_region((node_id << 44) + mem_start,
+ (u64)mem_size << 20, BOOT_MEM_RESERVED);
+ memblock_reserve(((node_id << 44) + mem_start),
+ mem_size << 20);
+ break;
+ }
+ }
+}
+
+static void __init node_mem_init(unsigned int node)
+{
+ unsigned long bootmap_size;
+ unsigned long node_addrspace_offset;
+ unsigned long start_pfn, end_pfn, freepfn;
+
+ node_addrspace_offset = nid_to_addroffset(node);
+ pr_info("Node%d's addrspace_offset is 0x%lx\n",
+ node, node_addrspace_offset);
+
+ get_pfn_range_for_nid(node, &start_pfn, &end_pfn);
+ freepfn = start_pfn;
+ if (node == 0)
+ freepfn = PFN_UP(__pa_symbol(&_end)); /* kernel end address */
+ pr_info("Node%d: start_pfn=0x%lx, end_pfn=0x%lx, freepfn=0x%lx\n",
+ node, start_pfn, end_pfn, freepfn);
+
+ __node_data[node] = prealloc__node_data + node;
+
+ NODE_DATA(node)->bdata = &bootmem_node_data[node];
+ NODE_DATA(node)->node_start_pfn = start_pfn;
+ NODE_DATA(node)->node_spanned_pages = end_pfn - start_pfn;
+
+ bootmap_size = init_bootmem_node(NODE_DATA(node), freepfn,
+ start_pfn, end_pfn);
+ free_bootmem_with_active_regions(node, end_pfn);
+ if (node == 0) /* used by finalize_initrd() */
+ max_low_pfn = end_pfn;
+
+ /* This is reserved for the kernel and bdata->node_bootmem_map */
+ reserve_bootmem_node(NODE_DATA(node), start_pfn << PAGE_SHIFT,
+ ((freepfn - start_pfn) << PAGE_SHIFT) + bootmap_size,
+ BOOTMEM_DEFAULT);
+
+ if (node == 0 && node_end_pfn(0) >= (0xffffffff >> PAGE_SHIFT)) {
+ /* Reserve 0xff800000~0xffffffff for RS780E integrated GPU */
+ reserve_bootmem_node(NODE_DATA(node),
+ (node_addrspace_offset | 0xff800000),
+ 8 << 20, BOOTMEM_DEFAULT);
+ }
+
+ sparse_memory_present_with_active_regions(node);
+}
+
+static __init void prom_meminit(void)
+{
+ unsigned int node, cpu;
+
+ cpu_node_probe();
+ init_topology_matrix();
+
+ for (node = 0; node < loongson_sysconf.nr_nodes; node++) {
+ if (node_online(node)) {
+ szmem(node);
+ node_mem_init(node);
+ cpus_clear(__node_data[(node)]->cpumask);
+ }
+ }
+ for (cpu = 0; cpu < loongson_sysconf.nr_cpus; cpu++) {
+ node = cpu / loongson_sysconf.cores_per_node;
+ if (node >= num_online_nodes())
+ node = 0;
+ pr_info("NUMA: set cpumask cpu %d on node %d\n", cpu, node);
+ cpu_set(cpu, __node_data[(node)]->cpumask);
+ }
+}
+
+void __init paging_init(void)
+{
+ unsigned node;
+ unsigned long zones_size[MAX_NR_ZONES] = {0, };
+
+ pagetable_init();
+
+ for_each_online_node(node) {
+ unsigned long start_pfn, end_pfn;
+
+ get_pfn_range_for_nid(node, &start_pfn, &end_pfn);
+
+ if (end_pfn > max_low_pfn)
+ max_low_pfn = end_pfn;
+ }
+#ifdef CONFIG_ZONE_DMA32
+ zones_size[ZONE_DMA32] = MAX_DMA32_PFN;
+#endif
+ zones_size[ZONE_NORMAL] = max_low_pfn;
+ free_area_init_nodes(zones_size);
+}
+
+void __init mem_init(void)
+{
+ high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT);
+ free_all_bootmem();
+ setup_zero_pages(); /* This comes from node 0 */
+ mem_init_print_info(NULL);
+}
+
+/* All PCI device belongs to logical Node-0 */
+int pcibus_to_node(struct pci_bus *bus)
+{
+ return 0;
+}
+EXPORT_SYMBOL(pcibus_to_node);
+
+void __init prom_init_numa_memory(void)
+{
+ enable_lpa();
+ prom_meminit();
+}
+EXPORT_SYMBOL(prom_init_numa_memory);
diff --git a/arch/mips/loongson/loongson-3/smp.c b/arch/mips/loongson/loongson-3/smp.c
index 3c320e7..ed0e2d0 100644
--- a/arch/mips/loongson/loongson-3/smp.c
+++ b/arch/mips/loongson/loongson-3/smp.c
@@ -203,6 +203,8 @@ static void loongson3_init_secondary(void)
for (i = 0; i < loongson_sysconf.nr_cpus; i++)
loongson3_ipi_write32(0xffffffff, ipi_en0_regs[i]);

+ cpu_data[cpu].package = cpu / loongson_sysconf.cores_per_package;
+ cpu_data[cpu].core = cpu % loongson_sysconf.cores_per_package;
per_cpu(cpu_state, cpu) = CPU_ONLINE;

i = 0;
@@ -394,17 +396,19 @@ static int loongson3_cpu_callback(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
unsigned int cpu = (unsigned long)hcpu;
+ uint64_t core_id = cpu_data[cpu].core;
+ uint64_t package_id = cpu_data[cpu].package;

switch (action) {
case CPU_POST_DEAD:
case CPU_POST_DEAD_FROZEN:
pr_info("Disable clock for CPU#%d\n", cpu);
- LOONGSON_CHIPCFG(0) &= ~(1 << (12 + cpu));
+ LOONGSON_CHIPCFG(package_id) &= ~(1 << (12 + core_id));
break;
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
pr_info("Enable clock for CPU#%d\n", cpu);
- LOONGSON_CHIPCFG(0) |= 1 << (12 + cpu);
+ LOONGSON_CHIPCFG(package_id) |= 1 << (12 + core_id);
break;
}
--
1.7.7.3
Aurelien Jarno
2014-10-20 15:27:09 UTC
Permalink
Hi,
Post by Huacai Chen
Multiple Loongson-3A chips can be interconnected with HT0-bus. This is
a CC-NUMA system that every chip (node) has its own local memory and
cache coherency is maintained by hardware. The 64-bit physical memory
0x-0000-YZZZ-ZZZZ-ZZZZ
The high 16 bits should be 0, which means the real physical address
supported by Loongson-3 is 48-bit. The "Y" bits is the base address of
each node, which can be also considered as the node-id. The "Z" bits is
the address offset within a node, which means every node has a 44 bits
address space.
Macros XPHYSADDR and MAX_PHYSMEM_BITS are modified unconditionally,
because many other MIPS CPUs have also extended their address spaces.
---
[snip]
Post by Huacai Chen
diff --git a/arch/mips/include/asm/sparsemem.h b/arch/mips/include/asm/sparsemem.h
index d2da53c..b1071c1 100644
--- a/arch/mips/include/asm/sparsemem.h
+++ b/arch/mips/include/asm/sparsemem.h
@@ -11,7 +11,7 @@
#else
# define SECTION_SIZE_BITS 28
#endif
-#define MAX_PHYSMEM_BITS 35
+#define MAX_PHYSMEM_BITS 48
#endif /* CONFIG_SPARSEMEM */
#endif /* _MIPS_SPARSEMEM_H */
This part of the patch has broken Loongson 2E support. The pata_via
module fails to allocate memory in the DMA zone:

| [ 4.708000] swapper: page allocation failure: order:0, mode:0x10d1
| [ 4.716000] CPU: 0 PID: 1 Comm: swapper Not tainted 3.17-1-loongson-2e #1 Debian 3.17-1~exp1
| [ 4.724000] Stack : 0000000000000050 ffffffff8016c7d8 0000000000000004 000000000000000b
| 0000000000000000 0000000000000000 0000000000000000 0000000000000000
| ffffffff8074b9f0 ffffffff8080f347 ffffffff8092e3b8 980000002e06b868
| 0000000000000001 0000000000000000 0000000000000000 0000000000000000
| 0000000000000000 ffffffff80655c84 00000000000010d1 980000002e06f838
| 0000000000000001 ffffffff8016ddec 980000002e06b460 00ffffff8074b9f0
| 0000000000000000 0000000000000000 0000000000000000 0000000000000000
| 0000000000000000 980000002e06f780 0000000000000000 ffffffff801f72e8
| 0000000000000000 00000000bc3e288d 00000000000010d1 0000000000000000
| 0000000000000001 ffffffff801098f0 ffffffff80892718 ffffffff801f72e8
| ...
| [ 4.792000] Call Trace:
| [ 4.796000] [<ffffffff801098f0>] show_stack+0x78/0x90
| [ 4.800000] [<ffffffff801f72e8>] warn_alloc_failed+0x100/0x148
| [ 4.808000] [<ffffffff801faabc>] __alloc_pages_nodemask+0x6e4/0x9c0
| [ 4.812000] [<ffffffff801fadbc>] __get_free_pages+0x24/0xa0
| [ 4.820000] [<ffffffff8011988c>] mips_dma_alloc_coherent+0x10c/0x1e0
| [ 4.824000] [<ffffffff804a925c>] dmam_alloc_coherent+0x84/0x100
| [ 4.832000] [<ffffffff804ed540>] ata_bmdma_port_start+0x48/0x68
| [ 4.840000] [<ffffffff804f3a1c>] via_port_start+0x2c/0x70
| [ 4.844000] [<ffffffff804d904c>] ata_host_start+0x124/0x270
| [ 4.848000] [<ffffffff804edfac>] ata_pci_sff_activate_host+0x54/0x270
| [ 4.856000] [<ffffffff804ee688>] ata_pci_init_one+0x150/0x208
| [ 4.864000] [<ffffffff804f36ac>] via_init_one+0x1b4/0x2d8
| [ 4.868000] [<ffffffff80424268>] pci_device_probe+0xb0/0x100
| [ 4.876000] [<ffffffff804984ac>] driver_probe_device+0xdc/0x400
| [ 4.880000] [<ffffffff804988a0>] __driver_attach+0xd0/0xd8
| [ 4.888000] [<ffffffff80496260>] bus_for_each_dev+0x70/0xc0
| [ 4.892000] [<ffffffff804978c8>] bus_add_driver+0x128/0x248
| [ 4.896000] [<ffffffff80499308>] driver_register+0x90/0x138
| [ 4.904000] [<ffffffff801005c0>] do_one_initcall+0x110/0x210
| [ 4.908000] [<ffffffff808a8e60>] kernel_init_freeable+0x17c/0x248
| [ 4.916000] [<ffffffff806546f8>] kernel_init+0x20/0x118
| [ 4.920000] [<ffffffff80103d50>] ret_from_kernel_thread+0x14/0x1c
| [ 4.928000]
| [ 4.928000] Mem-Info:
| [ 4.932000] DMA per-cpu:
| [ 4.936000] CPU 0: hi: 0, btch: 1 usd: 0
| [ 4.940000] Normal per-cpu:
| [ 4.944000] CPU 0: hi: 42, btch: 7 usd: 37
| [ 4.948000] active_anon:0 inactive_anon:0 isolated_anon:0
| [ 4.948000] active_file:1657 inactive_file:1899 isolated_file:0
| [ 4.948000] unevictable:0 dirty:0 writeback:0 unstable:0
| [ 4.948000] free:25711 slab_reclaimable:315 slab_unreclaimable:191
| [ 4.948000] mapped:0 shmem:0 pagetables:0 bounce:0
| [ 4.948000] free_cma:0
| [ 4.980000] DMA free:0kB min:0kB low:0kB high:0kB active_anon:0kB inactive_anon:0kB active_file:0kB inactive_file:0kB unevictable:0kB isolated(anon):0kB isolated(file):0k
| B present:16384kB managed:0kB mlocked:0kB dirty:0kB writeback:0kB mapped:0kB shmem:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB unstable:0
| kB bounce:0kB free_cma:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? yes
| [ 5.020000] lowmem_reserve[]: 0 116 116
| [ 5.024000] Normal free:411376kB min:2752kB low:3440kB high:4128kB active_anon:0kB inactive_anon:0kB active_file:26512kB inactive_file:30384kB unevictable:0kB isolated(an
| on):0kB isolated(file):0kB present:638960kB managed:478096kB mlocked:0kB dirty:0kB writeback:0kB mapped:0kB shmem:0kB slab_reclaimable:5040kB slab_unreclaimable:3056kB kerne
| l_stack:352kB pagetables:0kB unstable:0kB bounce:0kB free_cma:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? no
| [ 5.064000] lowmem_reserve[]: 0 0 0
| [ 5.068000] DMA: 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB 0*8192kB 0*16384kB 0*32768kB = 0kB
| [ 5.080000] Normal: 5*16kB (EM) 5*32kB (UEM) 2*64kB (EM) 3*128kB (EM) 6*256kB (UEM) 3*512kB (EM) 2*1024kB (M) 6*2048kB (EM) 2*4096kB (UM) 3*8192kB (EM) 2*16384kB (EM) 10*
| 32768kB (MR) = 411376kB
| [ 5.100000] Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 hugepages_size=32768kB
| [ 5.108000] 3559 total pagecache pages
| [ 5.112000] 0 pages in swap cache
| [ 5.116000] Swap cache stats: add 0, delete 0, find 0/0
| [ 5.120000] Free swap = 0kB
| [ 5.124000] Total swap = 0kB
| [ 5.128000] 40959 pages RAM
| [ 5.132000] 0 pages HighMem/MovableOnly
| [ 5.136000] 10054 pages reserved
| [ 5.140000] pata_via 0000:00:05.1: failed to start port 0 (errno=-12)
| [ 5.144000] pata_via: probe of 0000:00:05.1 failed with error -12

Does anyone has an idea of the problem, or have experienced the issue
with other MIPS platforms?

Thanks,
Aurelien
--
Aurelien Jarno GPG: 4096R/1DDD8C9B
***@aurel32.net http://www.aurel32.net
陈华才
2014-10-21 01:12:20 UTC
Permalink
Hi, Aurelien,

Alexandre Oliva meet the same problem, and the root cause is arch/mips/include/asm/sparsemem.h,
#define MAX_PHYSMEM_BITS 48
This line is not suitable for Loongson-2. My original patch make this line depend on CONFIG_NUMA, but Ralf suggest to remove that dependency.
Maybe we should bring back NUMA dependency again?

Huacai

------------------ Original ------------------
From: "Aurelien Jarno"<***@aurel32.net>;
Date: Mon, Oct 20, 2014 11:27 PM
To: "Huacai Chen"<***@lemote.com>;
Cc: "Ralf Baechle"<***@linux-mips.org>; "John Crispin"<***@phrozen.org>; "Steven J. Hill"<***@imgtec.com>; "linux-mips"<linux-***@linux-mips.org>; "Fuxin Zhang"<***@lemote.com>; "wuzhangjin"<***@gmail.com>; "764223"<***@bugs.debian.org>; "Martin Zobel-Helas"<***@debian.org>;
Subject: Re: [PATCH V3 4/8] MIPS: Add NUMA support for Loongson-3


Hi,
Post by Huacai Chen
Multiple Loongson-3A chips can be interconnected with HT0-bus. This is
a CC-NUMA system that every chip (node) has its own local memory and
cache coherency is maintained by hardware. The 64-bit physical memory
0x-0000-YZZZ-ZZZZ-ZZZZ
The high 16 bits should be 0, which means the real physical address
supported by Loongson-3 is 48-bit. The "Y" bits is the base address of
each node, which can be also considered as the node-id. The "Z" bits is
the address offset within a node, which means every node has a 44 bits
address space.
Macros XPHYSADDR and MAX_PHYSMEM_BITS are modified unconditionally,
because many other MIPS CPUs have also extended their address spaces.
---
[snip]
Post by Huacai Chen
diff --git a/arch/mips/include/asm/sparsemem.h b/arch/mips/include/asm/sparsemem.h
index d2da53c..b1071c1 100644
--- a/arch/mips/include/asm/sparsemem.h
+++ b/arch/mips/include/asm/sparsemem.h
@@ -11,7 +11,7 @@
#else
# define SECTION_SIZE_BITS 28
#endif
-#define MAX_PHYSMEM_BITS 35
+#define MAX_PHYSMEM_BITS 48
#endif /* CONFIG_SPARSEMEM */
#endif /* _MIPS_SPARSEMEM_H */
This part of the patch has broken Loongson 2E support. The pata_via
module fails to allocate memory in the DMA zone:

| [ 4.708000] swapper: page allocation failure: order:0, mode:0x10d1
| [ 4.716000] CPU: 0 PID: 1 Comm: swapper Not tainted 3.17-1-loongson-2e #1 Debian 3.17-1~exp1
| [ 4.724000] Stack : 0000000000000050 ffffffff8016c7d8 0000000000000004 000000000000000b
| 0000000000000000 0000000000000000 0000000000000000 0000000000000000
| ffffffff8074b9f0 ffffffff8080f347 ffffffff8092e3b8 980000002e06b868
| 0000000000000001 0000000000000000 0000000000000000 0000000000000000
| 0000000000000000 ffffffff80655c84 00000000000010d1 980000002e06f838
| 0000000000000001 ffffffff8016ddec 980000002e06b460 00ffffff8074b9f0
| 0000000000000000 0000000000000000 0000000000000000 0000000000000000
| 0000000000000000 980000002e06f780 0000000000000000 ffffffff801f72e8
| 0000000000000000 00000000bc3e288d 00000000000010d1 0000000000000000
| 0000000000000001 ffffffff801098f0 ffffffff80892718 ffffffff801f72e8
| ...
| [ 4.792000] Call Trace:
| [ 4.796000] [<ffffffff801098f0>] show_stack+0x78/0x90
| [ 4.800000] [<ffffffff801f72e8>] warn_alloc_failed+0x100/0x148
| [ 4.808000] [<ffffffff801faabc>] __alloc_pages_nodemask+0x6e4/0x9c0
| [ 4.812000] [<ffffffff801fadbc>] __get_free_pages+0x24/0xa0
| [ 4.820000] [<ffffffff8011988c>] mips_dma_alloc_coherent+0x10c/0x1e0
| [ 4.824000] [<ffffffff804a925c>] dmam_alloc_coherent+0x84/0x100
| [ 4.832000] [<ffffffff804ed540>] ata_bmdma_port_start+0x48/0x68
| [ 4.840000] [<ffffffff804f3a1c>] via_port_start+0x2c/0x70
| [ 4.844000] [<ffffffff804d904c>] ata_host_start+0x124/0x270
| [ 4.848000] [<ffffffff804edfac>] ata_pci_sff_activate_host+0x54/0x270
| [ 4.856000] [<ffffffff804ee688>] ata_pci_init_one+0x150/0x208
| [ 4.864000] [<ffffffff804f36ac>] via_init_one+0x1b4/0x2d8
| [ 4.868000] [<ffffffff80424268>] pci_device_probe+0xb0/0x100
| [ 4.876000] [<ffffffff804984ac>] driver_probe_device+0xdc/0x400
| [ 4.880000] [<ffffffff804988a0>] __driver_attach+0xd0/0xd8
| [ 4.888000] [<ffffffff80496260>] bus_for_each_dev+0x70/0xc0
| [ 4.892000] [<ffffffff804978c8>] bus_add_driver+0x128/0x248
| [ 4.896000] [<ffffffff80499308>] driver_register+0x90/0x138
| [ 4.904000] [<ffffffff801005c0>] do_one_initcall+0x110/0x210
| [ 4.908000] [<ffffffff808a8e60>] kernel_init_freeable+0x17c/0x248
| [ 4.916000] [<ffffffff806546f8>] kernel_init+0x20/0x118
| [ 4.920000] [<ffffffff80103d50>] ret_from_kernel_thread+0x14/0x1c
| [ 4.928000]
| [ 4.928000] Mem-Info:
| [ 4.932000] DMA per-cpu:
| [ 4.936000] CPU 0: hi: 0, btch: 1 usd: 0
| [ 4.940000] Normal per-cpu:
| [ 4.944000] CPU 0: hi: 42, btch: 7 usd: 37
| [ 4.948000] active_anon:0 inactive_anon:0 isolated_anon:0
| [ 4.948000] active_file:1657 inactive_file:1899 isolated_file:0
| [ 4.948000] unevictable:0 dirty:0 writeback:0 unstable:0
| [ 4.948000] free:25711 slab_reclaimable:315 slab_unreclaimable:191
| [ 4.948000] mapped:0 shmem:0 pagetables:0 bounce:0
| [ 4.948000] free_cma:0
| [ 4.980000] DMA free:0kB min:0kB low:0kB high:0kB active_anon:0kB inactive_anon:0kB active_file:0kB inactive_file:0kB unevictable:0kB isolated(anon):0kB isolated(file):0k
| B present:16384kB managed:0kB mlocked:0kB dirty:0kB writeback:0kB mapped:0kB shmem:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB unstable:0
| kB bounce:0kB free_cma:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? yes
| [ 5.020000] lowmem_reserve[]: 0 116 116
| [ 5.024000] Normal free:411376kB min:2752kB low:3440kB high:4128kB active_anon:0kB inactive_anon:0kB active_file:26512kB inactive_file:30384kB unevictable:0kB isolated(an
| on):0kB isolated(file):0kB present:638960kB managed:478096kB mlocked:0kB dirty:0kB writeback:0kB mapped:0kB shmem:0kB slab_reclaimable:5040kB slab_unreclaimable:3056kB kerne
| l_stack:352kB pagetables:0kB unstable:0kB bounce:0kB free_cma:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? no
| [ 5.064000] lowmem_reserve[]: 0 0 0
| [ 5.068000] DMA: 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB 0*8192kB 0*16384kB 0*32768kB = 0kB
| [ 5.080000] Normal: 5*16kB (EM) 5*32kB (UEM) 2*64kB (EM) 3*128kB (EM) 6*256kB (UEM) 3*512kB (EM) 2*1024kB (M) 6*2048kB (EM) 2*4096kB (UM) 3*8192kB (EM) 2*16384kB (EM) 10*
| 32768kB (MR) = 411376kB
| [ 5.100000] Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 hugepages_size=32768kB
| [ 5.108000] 3559 total pagecache pages
| [ 5.112000] 0 pages in swap cache
| [ 5.116000] Swap cache stats: add 0, delete 0, find 0/0
| [ 5.120000] Free swap = 0kB
| [ 5.124000] Total swap = 0kB
| [ 5.128000] 40959 pages RAM
| [ 5.132000] 0 pages HighMem/MovableOnly
| [ 5.136000] 10054 pages reserved
| [ 5.140000] pata_via 0000:00:05.1: failed to start port 0 (errno=-12)
| [ 5.144000] pata_via: probe of 0000:00:05.1 failed with error -12

Does anyone has an idea of the problem, or have experienced the issue
with other MIPS platforms?

Thanks,
Aurelien

--
Aurelien Jarno GPG: 4096R/1DDD8C9B
***@aurel32.net

Huacai Chen
2014-06-26 03:41:30 UTC
Permalink
This post might be inappropriate. Click to display it.
Huacai Chen
2014-06-26 03:41:31 UTC
Permalink
Loongson-3 has some specific instructions (MMI/SIMD) in coprocessor 2.
COP2 isn't independent because it share COP1 (FPU)'s registers. This
patch enable the COP2 usage so user-space programs can use the MMI/SIMD
instructions. When COP2 exception happens, we enable both COP1 (FPU)
and COP2, only in this way the fp context can be saved and restored
correctly.

Signed-off-by: Huacai Chen <***@lemote.com>
---
arch/mips/include/asm/cop2.h | 8 ++++
arch/mips/loongson/loongson-3/Makefile | 2 +-
arch/mips/loongson/loongson-3/cop2-ex.c | 63 +++++++++++++++++++++++++++++++
3 files changed, 72 insertions(+), 1 deletions(-)
create mode 100644 arch/mips/loongson/loongson-3/cop2-ex.c

diff --git a/arch/mips/include/asm/cop2.h b/arch/mips/include/asm/cop2.h
index c1516cc..d035298 100644
--- a/arch/mips/include/asm/cop2.h
+++ b/arch/mips/include/asm/cop2.h
@@ -32,6 +32,14 @@ extern void nlm_cop2_restore(struct nlm_cop2_state *);
#define cop2_present 1
#define cop2_lazy_restore 0

+#elif defined(CONFIG_CPU_LOONGSON3)
+
+#define cop2_save(r)
+#define cop2_restore(r)
+
+#define cop2_present 1
+#define cop2_lazy_restore 1
+
#else

#define cop2_present 0
diff --git a/arch/mips/loongson/loongson-3/Makefile b/arch/mips/loongson/loongson-3/Makefile
index 471b0f2a..b4df775 100644
--- a/arch/mips/loongson/loongson-3/Makefile
+++ b/arch/mips/loongson/loongson-3/Makefile
@@ -1,7 +1,7 @@
#
# Makefile for Loongson-3 family machines
#
-obj-y += irq.o
+obj-y += irq.o cop2-ex.o

obj-$(CONFIG_SMP) += smp.o

diff --git a/arch/mips/loongson/loongson-3/cop2-ex.c b/arch/mips/loongson/loongson-3/cop2-ex.c
new file mode 100644
index 0000000..9182e8d
--- /dev/null
+++ b/arch/mips/loongson/loongson-3/cop2-ex.c
@@ -0,0 +1,63 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2014 Lemote Corporation.
+ * written by Huacai Chen <***@lemote.com>
+ *
+ * based on arch/mips/cavium-octeon/cpu.c
+ * Copyright (C) 2009 Wind River Systems,
+ * written by Ralf Baechle <***@linux-mips.org>
+ */
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/notifier.h>
+
+#include <asm/fpu.h>
+#include <asm/cop2.h>
+#include <asm/current.h>
+#include <asm/mipsregs.h>
+
+static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
+ void *data)
+{
+ int fpu_enabled;
+ int fr = !test_thread_flag(TIF_32BIT_FPREGS);
+
+ switch (action) {
+ case CU2_EXCEPTION:
+ preempt_disable();
+ fpu_enabled = read_c0_status() & ST0_CU1;
+ if (!fr)
+ set_c0_status(ST0_CU1 | ST0_CU2);
+ else
+ set_c0_status(ST0_CU1 | ST0_CU2 | ST0_FR);
+ enable_fpu_hazard();
+ KSTK_STATUS(current) |= (ST0_CU1 | ST0_CU2);
+ if (fr)
+ KSTK_STATUS(current) |= ST0_FR;
+ else
+ KSTK_STATUS(current) &= ~ST0_FR;
+ /* If FPU is enabled, we needn't init or restore fp */
+ if(!fpu_enabled) {
+ set_thread_flag(TIF_USEDFPU);
+ if (!used_math()) {
+ _init_fpu();
+ set_used_math();
+ } else
+ _restore_fp(current);
+ }
+ preempt_enable();
+
+ return NOTIFY_STOP; /* Don't call default notifier */
+ }
+
+ return NOTIFY_OK; /* Let default notifier send signals */
+}
+
+static int __init loongson_cu2_setup(void)
+{
+ return cu2_notifier(loongson_cu2_call, 0);
+}
+early_initcall(loongson_cu2_setup);
--
1.7.7.3
Huacai Chen
2014-06-26 03:41:32 UTC
Permalink
Since this CONFIG option will be used for both Loongson-3A/3B machines,
and not all Loongson-3 machines are produced by Lemote, we rename
CONFIG_LEMOTE_MACH3A to CONFIG_LOONGSON_MACH3X.

Signed-off-by: Huacai Chen <***@lemote.com>
---
arch/mips/configs/loongson3_defconfig | 2 +-
arch/mips/include/asm/mach-loongson/machine.h | 4 ++--
arch/mips/loongson/Kconfig | 8 ++++----
arch/mips/loongson/Platform | 2 +-
arch/mips/pci/Makefile | 2 +-
5 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig
index ea1761f..130e31b 100644
--- a/arch/mips/configs/loongson3_defconfig
+++ b/arch/mips/configs/loongson3_defconfig
@@ -1,6 +1,6 @@
CONFIG_MACH_LOONGSON=y
CONFIG_SWIOTLB=y
-CONFIG_LEMOTE_MACH3A=y
+CONFIG_LOONGSON_MACH3X=y
CONFIG_CPU_LOONGSON3=y
CONFIG_64BIT=y
CONFIG_PAGE_SIZE_16KB=y
diff --git a/arch/mips/include/asm/mach-loongson/machine.h b/arch/mips/include/asm/mach-loongson/machine.h
index 1b1f592..228e3784 100644
--- a/arch/mips/include/asm/mach-loongson/machine.h
+++ b/arch/mips/include/asm/mach-loongson/machine.h
@@ -24,10 +24,10 @@

#endif

-#ifdef CONFIG_LEMOTE_MACH3A
+#ifdef CONFIG_LOONGSON_MACH3X

#define LOONGSON_MACHTYPE MACH_LEMOTE_A1101

-#endif /* CONFIG_LEMOTE_MACH3A */
+#endif /* CONFIG_LOONGSON_MACH3X */

#endif /* __ASM_MACH_LOONGSON_MACHINE_H */
diff --git a/arch/mips/loongson/Kconfig b/arch/mips/loongson/Kconfig
index a14a50d..1b91fc6 100644
--- a/arch/mips/loongson/Kconfig
+++ b/arch/mips/loongson/Kconfig
@@ -60,8 +60,8 @@ config LEMOTE_MACH2F
These family machines include fuloong2f mini PC, yeeloong2f notebook,
LingLoong allinone PC and so forth.

-config LEMOTE_MACH3A
- bool "Lemote Loongson 3A family machines"
+config LOONGSON_MACH3X
+ bool "Generic Loongson 3 family machines"
select ARCH_SPARSEMEM_ENABLE
select GENERIC_ISA_DMA_SUPPORT_BROKEN
select BOOT_ELF32
@@ -87,8 +87,8 @@ config LEMOTE_MACH3A
select ZONE_DMA32
select LEFI_FIRMWARE_INTERFACE
help
- Lemote Loongson 3A family machines utilize the 3A revision of
- Loongson processor and RS780/SBX00 chipset.
+ Generic Loongson 3 family machines utilize the 3A/3B revision
+ of Loongson processor and RS780/SBX00 chipset.
endchoice

config CS5536
diff --git a/arch/mips/loongson/Platform b/arch/mips/loongson/Platform
index 6205372..0ac20eb 100644
--- a/arch/mips/loongson/Platform
+++ b/arch/mips/loongson/Platform
@@ -30,4 +30,4 @@ platform-$(CONFIG_MACH_LOONGSON) += loongson/
cflags-$(CONFIG_MACH_LOONGSON) += -I$(srctree)/arch/mips/include/asm/mach-loongson -mno-branch-likely
load-$(CONFIG_LEMOTE_FULOONG2E) += 0xffffffff80100000
load-$(CONFIG_LEMOTE_MACH2F) += 0xffffffff80200000
-load-$(CONFIG_CPU_LOONGSON3) += 0xffffffff80200000
+load-$(CONFIG_LOONGSON_MACH3X) += 0xffffffff80200000
diff --git a/arch/mips/pci/Makefile b/arch/mips/pci/Makefile
index ff8a553..6523d55 100644
--- a/arch/mips/pci/Makefile
+++ b/arch/mips/pci/Makefile
@@ -29,7 +29,7 @@ obj-$(CONFIG_LASAT) += pci-lasat.o
obj-$(CONFIG_MIPS_COBALT) += fixup-cobalt.o
obj-$(CONFIG_LEMOTE_FULOONG2E) += fixup-fuloong2e.o ops-loongson2.o
obj-$(CONFIG_LEMOTE_MACH2F) += fixup-lemote2f.o ops-loongson2.o
-obj-$(CONFIG_LEMOTE_MACH3A) += fixup-loongson3.o ops-loongson3.o
+obj-$(CONFIG_LOONGSON_MACH3X) += fixup-loongson3.o ops-loongson3.o
obj-$(CONFIG_MIPS_MALTA) += fixup-malta.o pci-malta.o
obj-$(CONFIG_PMC_MSP7120_GW) += fixup-pmcmsp.o ops-pmcmsp.o
obj-$(CONFIG_PMC_MSP7120_EVAL) += fixup-pmcmsp.o ops-pmcmsp.o
--
1.7.7.3
Loading...