Re: [Need HELP!] Please help to test kernel patch (sparc64, NUMA)

Hi,

The system fails to boot with this patch:

[....] Setting preliminary keymap...[ 79.970910] Unable to handle kernel pagin g request at virtual address 0000000001976000

[ 80.075059] tsk->{mm,active_mm}->context = 00000000000002c6

[ 80.148245] tsk->{mm,active_mm}->pgd = fffffc133bbdc000

[ 80.216869] \|/ ____ \|/

[ 80.216869] "@'/ .. \`@"

[ 80.216869] /_| \__/ |_\

[ 80.216869] \__U_/

[ 80.410178] gzip(449): Oops [#1]

[ 80.452481] CPU: 1 PID: 449 Comm: gzip Not tainted 3.13.0-rc2-ghost-3-sparcnu ma-g1de425c-dirty #1

[ 80.569145] task: fffffc133be1c980 ti: fffffc033cbd8000 task.ti: fffffc033cbd 8000

[ 80.667505] TSTATE: 0000000080e01600 TPC: 0000000000634858 TNPC: 000000000063 485c Y: 00000000 Not tainted

[ 80.796755] TPC: <__blk_segment_map_sg+0x58/0x140>

[ 80.859643] g0: 0000004480e01601 g1: 0000010006789740 g2: 0000000000000000 g3 : 0000000000000000

[ 80.974023] g4: fffffc133be1c980 g5: fffffc133c9f6000 g6: fffffc033cbd8000 g7 : 000000033c4ba000

[ 81.088397] o0: 459442c846064700 o1: 0000000000000060 o2: 0000000000000000 o3 : fffffc033df00bd0

[ 81.202768] o4: 0000000000000000 o5: 0000000000001000 sp: fffffc033cbd9a41 re t_pc: 0000000000634838

[ 81.321719] RPC: <__blk_segment_map_sg+0x38/0x140>

[ 81.384617] l0: 0000000000001000 l1: 0000000000000005 l2: 0000000000000060 l3 : 0000000000000be8

[ 81.498994] l4: 000000000000007f l5: 0000000100000000 l6: fffffffe00000000 l7 : 0000000000c14550

[ 81.613369] i0: fffffc033c8c0000 i1: fffffc133bacbd00 i2: 459442c846064700 i3 : fffffc033cbda3b8

[ 81.727741] i4: fffffc033cbda3c0 i5: fffffc033cbda3c8 i6: fffffc033cbd9af1 i7 : 0000000000634a7c

[ 81.842116] I7: <blk_rq_map_sg+0x5c/0x1e0>

[ 81.895861] Call Trace:

[ 81.927887] [0000000000634a7c] blk_rq_map_sg+0x5c/0x1e0

[ 81.997660] [00000000006e6ec8] scsi_init_sgtable+0x28/0x80

[ 82.070854] [00000000006e6f30] scsi_init_io+0x10/0x140

[ 82.139485] [0000000000700c30] sd_prep_fn+0x410/0x1020

[ 82.208109] [0000000000630160] blk_peek_request+0xe0/0x280

[ 82.281300] [00000000006e68e4] scsi_request_fn+0x44/0x580

[ 82.353355] [000000000062cbb4] __blk_run_queue+0x34/0x60

[ 82.424273] [0000000000648180] cfq_insert_request+0x2c0/0x4e0

[ 82.500896] [000000000062a1c8] __elv_add_request+0x1c8/0x2e0

[ 82.576382] [0000000000630734] blk_flush_plug_list+0x214/0x280

[ 82.654163] [0000000000816934] io_schedule+0x54/0xc0

[ 82.720494] [0000000000584604] sleep_on_buffer+0x4/0x20

[ 82.790261] [0000000000816fbc] __wait_on_bit+0x7c/0xe0

[ 82.858883] [0000000000817064] out_of_line_wait_on_bit+0x44/0x60

[ 82.938944] [0000000000586ce0] __bread+0xc0/0x100

[ 83.001855] [00000000005cb9a4] ext3_get_branch+0xa4/0x180

[ 83.073901] Disabling lock debugging due to kernel taint

[ 83.143672] Caller[0000000000634a7c]: blk_rq_map_sg+0x5c/0x1e0

[ 83.220301] Caller[00000000006e6ec8]: scsi_init_sgtable+0x28/0x80

[ 83.300363] Caller[00000000006e6f30]: scsi_init_io+0x10/0x140

[ 83.375849] Caller[0000000000700c30]: sd_prep_fn+0x410/0x1020

[ 83.451337] Caller[0000000000630160]: blk_peek_request+0xe0/0x280

[ 83.531395] Caller[00000000006e68e4]: scsi_request_fn+0x44/0x580

[ 83.610313] Caller[000000000062cbb4]: __blk_run_queue+0x34/0x60

[ 83.688087] Caller[0000000000648180]: cfq_insert_request+0x2c0/0x4e0

[ 83.771580] Caller[000000000062a1c8]: __elv_add_request+0x1c8/0x2e0

[ 83.853927] Caller[0000000000630734]: blk_flush_plug_list+0x214/0x280

[ 83.938563] Caller[0000000000816934]: io_schedule+0x54/0xc0

[ 84.011761] Caller[0000000000584604]: sleep_on_buffer+0x4/0x20

[ 84.088393] Caller[0000000000816fbc]: __wait_on_bit+0x7c/0xe0

[ 84.163878] Caller[0000000000817064]: out_of_line_wait_on_bit+0x44/0x60

[ 84.250800] Caller[0000000000586ce0]: __bread+0xc0/0x100

[ 84.320568] Caller[00000000005cb9a4]: ext3_get_branch+0xa4/0x180

[ 84.399487] Caller[00000000005cee3c]: ext3_get_blocks_handle+0x13c/0xf40

[ 84.487553] Caller[00000000005cfcc4]: ext3_get_block+0x84/0xe0

[ 84.564188] Caller[00000000005916b8]: do_mpage_readpage+0x358/0x620

[ 84.646532] Caller[0000000000591a7c]: mpage_readpages+0x9c/0x120

[ 84.725452] Caller[0000000000507188]: __do_page_cache_readahead+0x148/0x200

[ 84.816947] Caller[0000000000507514]: ra_submit+0x14/0x40

[ 84.887862] Caller[00000000004fcad8]: filemap_fault+0x318/0x400

[ 84.965639] Caller[000000000051fba8]: __do_fault+0x48/0x4c0

[ 85.038832] Caller[0000000000523a78]: handle_mm_fault+0x258/0xaa0

[ 85.118899] Caller[000000000044e57c]: do_sparc64_fault+0x41c/0x820

[ 85.200097] Caller[0000000000407a58]: sparc64_realfault_common+0x10/0x20

[ 85.288165] Caller[00000000005a7008]: padzero+0x28/0x40

[ 85.356787] Caller[00000000005a7968]: load_elf_binary+0x728/0x1240

[ 85.437997] Caller[000000000055b214]: search_binary_handler+0xb4/0x260

[ 85.523770] Instruction DUMP: c606600c 84086003 0ac08031 <ce5e8000> 8e09e00 3 c626a008 e026a00c 82104007 c2768000

[ 109.021944] BUG: soft lockup - CPU#1 stuck for 22s! [udevd:234]

[ 109.021955] BUG: soft lockup - CPU#0 stuck for 22s! [udevd:229]

[ 109.021998] Modules linked in: ohci_pci ohci_hcd ehci_hcd nouveau ttm drm_kms_helper snd_ali5451 snd_ac97_codec ac97_bus snd_pcm snd_page_alloc usbcore snd_timer usb_common snd tg3 drm ptp soundcore i2c_algo_bit pps_core libphy uio_pdrv_genirq uio

[ 109.022007] CPU: 0 PID: 229 Comm: udevd Tainted: G D 3.13.0-rc2-ghost-3-sparcnuma-g1de425c-dirty #1

[ 109.022012] task: fffffc033c923720 ti: fffffc033ca38000 task.ti: fffffc033ca38000

[ 109.022017] TSTATE: 0000004480001603 TPC: 0000000000819650 TNPC: 0000000000819654 Y: 00000000 Tainted: G D

[ 109.022031] TPC: <_raw_write_lock_bh+0x50/0x100>

[ 109.022034] g0: 000000000000099e g1: 0000000000000000 g2: 00000000000000ff g3: 000000000000000e

[ 109.022037] g4: fffffc033c923720 g5: fffffc033d5f6000 g6: fffffc033ca38000 g7: 0000000003126e98

[ 109.022040] o0: fffffc033c8c0408 o1: 00000000000007f5 o2: 0000000000000000 o3: 000000137c50adaf

[ 109.022043] o4: 00000000000137c5 o5: 00000000000007f5 sp: fffffc033fffb431 ret_pc: 0000000000635cb0

[ 109.022055] RPC: <blk_rq_timed_out_timer+0x10/0xa0>

[ 109.022058] l0: 000000000081f000 l1: 0000000000000000 l2: 0000000000000001 l3: fffffc033e004bb0

[ 109.022061] l4: 00000000f7efc938 l5: 00000000f7ee9720 l6: 00000000f7c68124 l7: 00000000f7efc000

[ 109.022064] i0: fffffc033c8c0000 i1: 0000000000000000 i2: 0000000000000000 i3: fffffc033e003618

[ 109.022067] i4: fffffc033c8c0540 i5: fffffc033e003768 i6: fffffc033fffb4f1 i7: 0000000000467a78

[ 109.022077] I7: <call_timer_fn+0x18/0x140>

[ 109.022078] Call Trace:

[ 109.022083] [0000000000467a78] call_timer_fn+0x18/0x140

[ 109.022087] [00000000004680bc] run_timer_softirq+0x23c/0x280

[ 109.022098] [0000000000460400] __do_softirq+0xc0/0x2a0

[ 109.022107] [000000000042b9ec] do_softirq_own_stack+0x2c/0x40

[ 109.022111] [0000000000460984] irq_exit+0xa4/0xc0

[ 109.022119] [000000000042f9cc] timer_interrupt+0xac/0xe0

[ 109.022126] [00000000004209d4] tl0_irq14+0x14/0x20

[ 109.022130] [0000000000819230] _raw_spin_unlock_irqrestore+0x10/0x40

[ 109.022134] [000000000045de50] do_exit+0x590/0xa00

[ 109.022137] [000000000045e3e8] do_group_exit+0x28/0xc0

[ 109.022141] [000000000045e494] SyS_exit_group+0x14/0x20

[ 109.022151] [0000000000406174] linux_sparc_syscall32+0x34/0x40

[ 111.819554] Modules linked in: ohci_pci ohci_hcd ehci_hcd nouveau ttm drm_kms_helper snd_ali5451 snd_ac97_codec ac97_bus snd_pcm snd_page_alloc usbcore snd_timer usb_common snd tg3 drm ptp soundcore i2c_algo_bit pps_core libphy uio_pdrv_genirq uio

[ 112.107775] CPU: 1 PID: 234 Comm: udevd Tainted: G D 3.13.0-rc2-ghost-3-sparcnuma-g1de425c-dirty #1

[ 112.238168] task: fffffc033c9255c0 ti: fffffc033ca78000 task.ti: fffffc033ca78000

[ 112.336527] TSTATE: 0000004411001603 TPC: 0000000000819230 TNPC: 0000000000819234 Y: 0000b7f8 Tainted: G D

[ 112.478356] TPC: <_raw_spin_unlock_irqrestore+0x10/0x40>

[ 112.548111] g0: fffffc133c09afc8 g1: 0000000000000000 g2: 0000000000000000 g3: 0000000000980058

[ 112.662489] g4: fffffc033c9255c0 g5: fffffc133c9f6000 g6: fffffc033ca78000 g7: 0000000000000001

[ 112.776863] o0: fffffc133ba53e10 o1: 0000000000000000 o2: 0000000000000001 o3: fffffc033c9255c0

[ 112.891236] o4: 0000000000000000 o5: 000000000000000e sp: fffffc033ca7b3c1 ret_pc: 0000000000633a58

[ 113.010187] RPC: <put_io_context_active+0xd8/0x100>

[ 113.074227] l0: fffffc033c925a18 l1: 0000000000100100 l2: 0000000000000001 l3: 00000000008ce2f0

[ 113.188606] l4: 00000000f7efc938 l5: 00000000f7ee9720 l6: 00000000f7c68124 l7: 00000000f7efc000

[ 113.302978] i0: fffffc133ba53e00 i1: 0000000000000014 i2: 0000000000000000 i3: fffffc133ba645a0

[ 113.417350] i4: fffffc133ba53e10 i5: fffffc133ba53e00 i6: fffffc033ca7b471 i7: 000000000045de50

[ 113.531728] I7: <do_exit+0x590/0xa00>

[ 113.579752] Call Trace:

[ 113.611777] [000000000045de50] do_exit+0x590/0xa00

[ 113.675827] [000000000045e3e8] do_group_exit+0x28/0xc0

[ 113.744451] [000000000045e494] SyS_exit_group+0x14/0x20

[ 113.814224] [0000000000406174] linux_sparc_syscall32+0x34/0x40

On Mon, Apr 21, 2014 at 3:55 AM, Kirill Tkhai <tkhai@yandex.ru> wrote:

Hi, Patrick,

have you tried the patch we spoke about?

Could you please test it?

Kirill

06.12.2013, 00:44, "Kirill Tkhai" <tkhai@yandex.ru>:

I attach the patch as file

Kirill

05.12.2013, 21:00, "Patrick Baggett" <baggett.patrick@gmail.com>:

Kirill,

I copied the contents of your email into a patch file, and when I did git apply --check, it didn't really work:

figgles@ghost:~/sparc-numa/sparc$ git apply --check numa.patch
error: patch failed: arch/sparc/include/asm/trap_block.h:138
error: arch/sparc/include/asm/trap_block.h: patch does not apply
error: patch failed: arch/sparc/kernel/smp_64.c:285
error: arch/sparc/kernel/smp_64.c: patch does not apply
error: patch failed: arch/sparc/kernel/trampoline_64.S:117
error: arch/sparc/kernel/trampoline_64.S: patch does not apply
error: patch failed: arch/sparc/mm/init_64.c:591
error: arch/sparc/mm/init_64.c: patch does not apply
I'm probably doing something dumb, so let me know what I need to change. ;)

Patrick

On Wed, Dec 4, 2013 at 3:56 AM, Kirill Tkhai <tkhai@yandex.ru> wrote:

Hi,

I'm looking for a person who has sparc64 machine with NUMA. The patch below adds
NUMA kernel text replication support. This should improve sparc64 kernel performance
a little bit.

I tested it on my machines, and it looks working for me. But they are not standard
sun v9. So person with standard vanila-supported machine is seeked!

Is anybody able to help me?

It's necessary to 1)clone David Miller's git tree:

git clone --depth=1 git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc.git

2)apply the patch and 3)do not forget to enable CONFIG_NUMA in xconfig/menuconfig.

The following actions is to do a boot test. If everything is OK, I'll be very thankful
if you're able to execute any short performance test: before patch and with it.

Thanks!

Signed-off-by: Kirill Tkhai <tkhai@yandex.ru>
---
arch/sparc/include/asm/page_64.h | 3 +
arch/sparc/include/asm/pgtable_64.h | 6 ++
arch/sparc/include/asm/trap_block.h | 17 ++++++
arch/sparc/kernel/smp_64.c | 8 ++-
arch/sparc/kernel/trampoline_64.S | 46 ++++++++++++++---
arch/sparc/mm/init_64.c | 94 ++++++++++++++++++++++++++++++++++-
arch/sparc/mm/init_64.h | 2 +-
7 files changed, 163 insertions(+), 13 deletions(-)
diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h
index aac53fc..5a85352 100644
--- a/arch/sparc/include/asm/page_64.h
+++ b/arch/sparc/include/asm/page_64.h
@@ -8,6 +8,9 @@
#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT)
#define PAGE_MASK (~(PAGE_SIZE-1))

+#define PAGE4MB_SHIFT 22
+#define PAGE4MB_SIZE (_AC(1,UL) << PAGE4MB_SHIFT)
+
/* Flushing for D-cache alias handling is only needed if
* the page size is smaller than 16K.
*/
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 8358dc1..0b0495f 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -884,6 +884,12 @@ extern pmd_t swapper_low_pmd_dir[PTRS_PER_PMD];
extern void paging_init(void);
extern unsigned long find_ecache_flush_span(unsigned long size);

+#ifdef CONFIG_NUMA
+extern void numa_copy_kernel_text(void);
+#else
+static inline void numa_copy_kernel_text(void) {}
+#endif
+
struct seq_file;
extern void mmu_info(struct seq_file *);

diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h
index 7e26b2d..a2f0990 100644
--- a/arch/sparc/include/asm/trap_block.h
+++ b/arch/sparc/include/asm/trap_block.h
@@ -138,6 +138,23 @@ extern struct sun4v_2insn_patch_entry __sun4v_2insn_patch,
nop; \
.previous;

+#ifdef CONFIG_NUMA
+
+#define __GET_NODEID(REG, TMP) \
+ __GET_CPUID(REG) \
+ sethi %hi(numa_cpu_lookup_table), TMP; \
+ or TMP, %lo(numa_cpu_lookup_table), TMP; \
+ sllx REG, 2, REG; \
+ add TMP, REG, TMP; \
+ lduw [TMP], REG;
+
+#else /* !CONFIG_NUMA */
+
+#define __GET_NODEID(REG, TMP) \
+ clr REG
+
+#endif /* !CONFIG_NUMA */
+
#ifdef CONFIG_SMP

#define TRAP_LOAD_TRAP_BLOCK(DEST, TMP) \
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index b66a533..554a0c5 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -285,7 +285,7 @@ static void ldom_startcpu_cpuid(unsigned int cpu, unsigned long thread_reg,
void **descrp)
{
extern unsigned long sparc64_ttable_tl0;
- extern unsigned long kern_locked_tte_data;
+ extern unsigned long kern_locked_tte_data[MAX_NUMNODES];
struct hvtramp_descr *hdesc;
unsigned long trampoline_ra;
struct trap_per_cpu *tb;
@@ -315,7 +315,7 @@ static void ldom_startcpu_cpuid(unsigned int cpu, unsigned long thread_reg,
hdesc->thread_reg = thread_reg;

tte_vaddr = (unsigned long) KERNBASE;
- tte_data = kern_locked_tte_data;
+ tte_data = kern_locked_tte_data[0];

for (i = 0; i < hdesc->num_mappings; i++) {
hdesc->maps[i].vaddr = tte_vaddr;
@@ -1214,6 +1214,10 @@ int setup_profiling_timer(unsigned int multiplier)

void __init smp_prepare_cpus(unsigned int max_cpus)
{
+ /* Dublicate kernel on every node. Do this after
+ * all kernel patches are applied.
+ */
+ numa_copy_kernel_text();
}

void smp_prepare_boot_cpu(void)
diff --git a/arch/sparc/kernel/trampoline_64.S b/arch/sparc/kernel/trampoline_64.S
index ad4bde3..e5a4f85 100644
--- a/arch/sparc/kernel/trampoline_64.S
+++ b/arch/sparc/kernel/trampoline_64.S
@@ -117,26 +117,42 @@ startup_continue:
flushw

/* Setup the loop variables:
+ * %l1: Number of 4MB pages containing not-init kernel text
+ * %l2: TTE base of node 0. Used for DTLB and for rest of __init text
+ * ITLB mappings. See numa_alloc_kernel_text() for details.
* %l3: VADDR base
- * %l4: TTE base
+ * %l4: TTE base of current node. Used for ITLB.
* %l5: Loop iterator, iterates from 0 to 'num_kernel_image_mappings'
* %l6: Number of TTE entries to map
* %l7: Highest TTE entry number, we count down
*/
sethi %hi(KERNBASE), %l3
sethi %hi(kern_locked_tte_data), %l4
- ldx [%l4 + %lo(kern_locked_tte_data)], %l4
+ or %l4, %lo(kern_locked_tte_data), %l4
+ ldx [%l4], %l2 ! kern_locked_tte_data[0]
+
+ __GET_NODEID(%g2, %g1)
+ sllx %g2, 3, %g2
+ add %l4, %g2, %l4
+ ldx [%l4], %l4 ! kern_locked_tte_data[node]
+
clr %l5
sethi %hi(num_kernel_image_mappings), %l6
lduw [%l6 + %lo(num_kernel_image_mappings)], %l6

+ sethi %hi(num_node_copy_mappings), %l1
+ lduw [%l1 + %lo(num_node_copy_mappings)], %l1
+
mov 15, %l7
BRANCH_IF_ANY_CHEETAH(g1,g5,2f)

mov 63, %l7
2:
-
-3:
+ cmp %l5, %l1 !__init section
+ bne 4f
+ nop
+ mov %l2, %l4 !use node 0 TTE
+4:
/* Lock into I-MMU */
sethi %hi(call_method), %g2
or %g2, %lo(call_method), %g2
@@ -190,7 +206,7 @@ startup_continue:

add %l3, %g1, %g2
stx %g2, [%sp + 2047 + 128 + 0x28] ! VADDR
- add %l4, %g1, %g2
+ add %l2, %g1, %g2
stx %g2, [%sp + 2047 + 128 + 0x30] ! TTE

/* TTE index is highest minus loop index. */
@@ -205,7 +221,7 @@ startup_continue:

add %l5, 1, %l5
cmp %l5, %l6
- bne,pt %xcc, 3b
+ bne,pt %xcc, 2b
nop

sethi %hi(prom_entry_lock), %g2
@@ -217,12 +233,26 @@ startup_continue:
niagara_lock_tlb:
sethi %hi(KERNBASE), %l3
sethi %hi(kern_locked_tte_data), %l4
- ldx [%l4 + %lo(kern_locked_tte_data)], %l4
+ or %l4, %lo(kern_locked_tte_data), %l4
+ ldx [%l4], %l2 ! kern_locked_tte_data[0]
+
+ __GET_NODEID(%g2, %g1)
+ sllx %g2, 3, %g2
+ add %l4, %g2, %l4
+ ldx [%l4], %l4 ! kern_locked_tte_data[node]
+
clr %l5
sethi %hi(num_kernel_image_mappings), %l6
lduw [%l6 + %lo(num_kernel_image_mappings)], %l6

+ sethi %hi(num_node_copy_mappings), %l1
+ lduw [%l1 + %lo(num_node_copy_mappings)], %l1
1:
+ cmp %l5, %l1 !__init section
+ bne 4f
+ nop
+ mov %l2, %l4 !use node 0 TTE
+4:
mov HV_FAST_MMU_MAP_PERM_ADDR, %o5
sllx %l5, 22, %g2
add %l3, %g2, %o0
@@ -235,7 +265,7 @@ niagara_lock_tlb:
sllx %l5, 22, %g2
add %l3, %g2, %o0
clr %o1
- add %l4, %g2, %o2
+ add %l2, %g2, %o2
mov HV_MMU_DMMU, %o3
ta HV_FAST_TRAP

diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 5322e53..0183213 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -186,6 +186,7 @@ unsigned long sparc64_kern_pri_nuc_bits __read_mostly;
unsigned long sparc64_kern_sec_context __read_mostly;

int num_kernel_image_mappings;
+int num_node_copy_mappings;

#ifdef CONFIG_DEBUG_DCFLUSH
atomic_t dcpage_flushes = ATOMIC_INIT(0);
@@ -477,7 +478,7 @@ void mmu_info(struct seq_file *m)
struct linux_prom_translation prom_trans[512] __read_mostly;
unsigned int prom_trans_ents __read_mostly;

-unsigned long kern_locked_tte_data;
+unsigned long kern_locked_tte_data[MAX_NUMNODES];

/* The obp translations are saved based on 8k pagesize, since obp can
* use a mixture of pagesizes. Misses to the LOW_OBP_ADDRESS ->
@@ -591,7 +592,7 @@ static void __init remap_kernel(void)
phys_page = (prom_boot_mapping_phys_low >> 22UL) << 22UL;
tte_data = kern_large_tte(phys_page);

- kern_locked_tte_data = tte_data;
+ kern_locked_tte_data[0] = tte_data;

/* Now lock us into the TLBs via Hypervisor or OBP. */
if (tlb_type == hypervisor) {
@@ -1330,6 +1331,79 @@ static void __init bootmem_init_nonnuma(void)
node_set_online(0);
}

+#ifdef CONFIG_NUMA
+
+/* Allocate memory for per-node copy of kernel text.
+ * The copying itself will be made after all kernel
+ * patches are applied.
+ */
+static void __init numa_alloc_kernel_text(void)
+{
+ unsigned long init_start = (unsigned long)__init_begin;
+ unsigned int size, node;
+
+ /* The rest init text will be mapped from the original image.
+ */
+ size = round_up(init_start - KERNBASE, PAGE4MB_SIZE);
+ num_node_copy_mappings = size >> PAGE4MB_SHIFT;
+
+ for (node = 1; node < num_node_masks; node++) {
+ unsigned long tte_data;
+ phys_addr_t new_base_pa;
+
+ new_base_pa = memblock_alloc_nid(size, PAGE4MB_SIZE, node);
+
+ if (new_base_pa) {
+ pr_info("node %d: Allocated memory for copy of "
+ "kernel text: [%016llx, %016llx]\n",
+ node, new_base_pa, new_base_pa + size);
+ tte_data = kern_large_tte(new_base_pa);
+ } else {
+ pr_err("node %d: Can't allocate memory for kernel "
+ "text duplicate\n", node);
+ tte_data = kern_locked_tte_data[0];
+ }
+
+ kern_locked_tte_data[node] = tte_data;
+ }
+}
+
+/* Dublicate kernel text on every NUMA node.
+ * Do not copy pages which contain only init text,
+ * because they are mapped from original kernel.
+ */
+void numa_copy_kernel_text(void)
+{
+ unsigned int size, node;
+ unsigned long tte_data0;
+
+ size = num_node_copy_mappings << PAGE4MB_SHIFT;
+ tte_data0 = kern_locked_tte_data[0];
+
+ for (node = 1; node < num_node_masks; node++) {
+ unsigned long tte_data, phys_addr;
+
+ tte_data = kern_locked_tte_data[node];
+
+ if (tte_data == tte_data0)
+ continue;
+
+ /* PA is [42:12] range */
+ phys_addr = (((tte_data << 21) >> 21) >> 13) << 13;
+
+ memcpy(__va(phys_addr), (void *)KERNBASE, size);
+ }
+}
+
+#else /* CONFIG_NUMA */
+
+static void __init numa_alloc_kernel_text(void)
+{
+}
+
+#endif /* CONFIG_NUMA */
+
+
static unsigned long __init bootmem_init(unsigned long phys_base)
{
unsigned long end_pfn;
@@ -1341,6 +1415,8 @@ static unsigned long __init bootmem_init(unsigned long phys_base)
if (bootmem_init_numa() < 0)
bootmem_init_nonnuma();

+ numa_alloc_kernel_text();
+
/* Dump memblock with node info. */
memblock_dump_all();

@@ -1922,6 +1998,9 @@ void __init paging_init(void)
memblock_add(pavail[i].phys_addr, pavail[i].reg_size);
}

+#ifdef CONFIG_NUMA
+ kern_size = round_up(kern_size, PAGE4MB_SIZE);
+#endif
memblock_reserve(kern_base, kern_size);

find_ramdisk(phys_base);
@@ -2188,6 +2267,17 @@ void free_initmem(void)
* The init section is aligned to 8k in vmlinux.lds. Page align for >8k pagesizes.
*/
addr = PAGE_ALIGN((unsigned long)(__init_begin));
+
+#ifdef CONFIG_NUMA
+ if (num_node_masks > 1) {
+ /* Do not free 4KB pages which are lying at 4MB page
+ * together with normal kernel text. Their addresses
+ * are forbidden forever.
+ */
+ addr = round_up(addr, PAGE4MB_SIZE);
+ }
+#endif
+
initend = (unsigned long)(__init_end) & PAGE_MASK;
for (; addr < initend; addr += PAGE_SIZE) {
unsigned long page;
diff --git a/arch/sparc/mm/init_64.h b/arch/sparc/mm/init_64.h
index 5d3782de..a14c8d8 100644
--- a/arch/sparc/mm/init_64.h
+++ b/arch/sparc/mm/init_64.h
@@ -34,7 +34,7 @@ extern struct linux_prom_translation prom_trans[512];
extern unsigned int prom_trans_ents;

/* Exported for SMP bootup purposes. */
-extern unsigned long kern_locked_tte_data;
+extern unsigned long kern_locked_tte_data[MAX_NUMNODES];

extern void prom_world(int enter);

--
To UNSUBSCRIBE, email to debian-sparc-REQUEST@lists.debian.org
with a subject of "unsubscribe". Trouble? Contact listmaster@lists.debian.org
Archive: http://lists.debian.org/176311386150980@web5m.yandex.ru