[PATCH 1/2] MIPS: clean up CONFIG_MIPS_PGD_C0_CONTEXT handling

[PATCH 1/2] MIPS: clean up CONFIG_MIPS_PGD_C0_CONTEXT handling

[Huang Pei]

+. LOONGSON64 use 0x98xx_xxxx_xxxx_xxxx as xphys cached

+. let CONFIG_MIPS_PGD_C0_CONTEXT depend on 64bit

+. cast CAC_BASE into u64 to silence warning on MIPS32

CP0 Context has enough room for wraping pgd into its 41-bit PTEBase field.

+. For XPHYS, the trick is that pgd is 4kB aligned, and the PABITS <= 48,
only save 48 - 12 + 5(for bit[63:59]) = 41 bits, aka. :

   bit[63:59] | 0000 0000 000 |  bit[47:12] | 0000 0000 0000

+. for CKSEG0, only save 29 - 12 = 17 bits

Signed-off-by: Huang Pei <huangpei@loongson.cn>
---
 arch/mips/Kconfig    |  3 ++-
 arch/mips/mm/tlbex.c | 10 +++++-----
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 2000bb2b0220..5741dae35b74 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2142,7 +2142,8 @@ config CPU_SUPPORTS_HUGEPAGES
 	depends on !(32BIT && (ARCH_PHYS_ADDR_T_64BIT || EVA))
 config MIPS_PGD_C0_CONTEXT
 	bool
-	default y if 64BIT && (CPU_MIPSR2 || CPU_MIPSR6) && !CPU_XLP
+	depends on 64BIT
+	default y if (CPU_MIPSR2 || CPU_MIPSR6) && !CPU_XLP
 
 #
 # Set to y for ptrace access to watch registers.
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index a7521b8f7658..591cfa0fca02 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -848,8 +848,8 @@ void build_get_pmde64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
 		/* Clear lower 23 bits of context. */
 		uasm_i_dins(p, ptr, 0, 0, 23);
 
-		/* 1 0	1 0 1  << 6  xkphys cached */
-		uasm_i_ori(p, ptr, ptr, 0x540);
+		/* insert bit[63:59] of CAC_BASE into bit[11:6] of ptr */
+		uasm_i_ori(p, ptr, ptr, ((u64)(CAC_BASE) >> 53));
 		uasm_i_drotr(p, ptr, ptr, 11);
 #elif defined(CONFIG_SMP)
 		UASM_i_CPUID_MFC0(p, ptr, SMP_CPUID_REG);
@@ -1164,8 +1164,9 @@ build_fast_tlb_refill_handler (u32 **p, struct uasm_label **l,
 
 	if (pgd_reg == -1) {
 		vmalloc_branch_delay_filled = 1;
-		/* 1 0	1 0 1  << 6  xkphys cached */
-		uasm_i_ori(p, ptr, ptr, 0x540);
+		/* insert bit[63:59] of CAC_BASE into bit[11:6] of ptr */
+		uasm_i_ori(p, ptr, ptr, ((u64)(CAC_BASE) >> 53));
+
 		uasm_i_drotr(p, ptr, ptr, 11);
 	}
 
@@ -1292,7 +1293,6 @@ build_fast_tlb_refill_handler (u32 **p, struct uasm_label **l,
 
 	return rv;
 }
-
 /*
  * For a 64-bit kernel, we are using the 64-bit XTLB refill exception
  * because EXL == 0.  If we wrap, we can also use the 32 instruction
-- 
2.17.1

[PATCH 2/2] MIPS: loongson64: alloc pglist_data at run time

[Huang Pei]

Loongson64 allocates arrays of pglist_data statically and is located
at Node 0, and cpu from Nodes other than 0 need remote access to
pglist_data and zone info.

Delay pglist_data allocation till run time, and make it NUMA-aware

Signed-off-by: Huang Pei <huangpei@loongson.cn>
---
 arch/mips/loongson64/numa.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/arch/mips/loongson64/numa.c b/arch/mips/loongson64/numa.c
index cf9459f79f9b..afafd367cb38 100644
--- a/arch/mips/loongson64/numa.c
+++ b/arch/mips/loongson64/numa.c
@@ -26,7 +26,6 @@
 #include <asm/wbflush.h>
 #include <boot_param.h>
 
-static struct pglist_data prealloc__node_data[MAX_NUMNODES];
 unsigned char __node_distances[MAX_NUMNODES][MAX_NUMNODES];
 EXPORT_SYMBOL(__node_distances);
 struct pglist_data *__node_data[MAX_NUMNODES];
@@ -151,8 +150,12 @@ static void __init szmem(unsigned int node)
 
 static void __init node_mem_init(unsigned int node)
 {
+	struct pglist_data *nd;
 	unsigned long node_addrspace_offset;
 	unsigned long start_pfn, end_pfn;
+	unsigned long nd_pa;
+	int tnid;
+	const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES);
 
 	node_addrspace_offset = nid_to_addrbase(node);
 	pr_info("Node%d's addrspace_offset is 0x%lx\n",
@@ -162,8 +165,16 @@ static void __init node_mem_init(unsigned int node)
 	pr_info("Node%d: start_pfn=0x%lx, end_pfn=0x%lx\n",
 		node, start_pfn, end_pfn);
 
-	__node_data[node] = prealloc__node_data + node;
-
+	nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, node);
+	if (!nd_pa)
+		panic("Cannot allocate %zu bytes for node %d data\n",
+		      nd_size, node);
+	nd = __va(nd_pa);
+	memset(nd, 0, sizeof(struct pglist_data));
+	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
+	if (tnid != node)
+		pr_info("NODE_DATA(%d) on node %d\n", node, tnid);
+	__node_data[node] = nd;
 	NODE_DATA(node)->node_start_pfn = start_pfn;
 	NODE_DATA(node)->node_spanned_pages = end_pfn - start_pfn;
 
-- 
2.17.1

Re: [PATCH 1/2] MIPS: clean up CONFIG_MIPS_PGD_C0_CONTEXT handling

[Thomas Bogendoerfer]

On Tue, Mar 09, 2021 at 04:02:09PM +0800, Huang Pei wrote:
> +. LOONGSON64 use 0x98xx_xxxx_xxxx_xxxx as xphys cached
> 
> +. let CONFIG_MIPS_PGD_C0_CONTEXT depend on 64bit
> 
> +. cast CAC_BASE into u64 to silence warning on MIPS32
> 
> CP0 Context has enough room for wraping pgd into its 41-bit PTEBase field.
> 
> +. For XPHYS, the trick is that pgd is 4kB aligned, and the PABITS <= 48,
> only save 48 - 12 + 5(for bit[63:59]) = 41 bits, aka. :
> 
>    bit[63:59] | 0000 0000 000 |  bit[47:12] | 0000 0000 0000
> 
> +. for CKSEG0, only save 29 - 12 = 17 bits

you are explaining what you are doing, but not why you are doing this.
So why are you doing this ?

>  #
>  # Set to y for ptrace access to watch registers.
> diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
> index a7521b8f7658..591cfa0fca02 100644
> --- a/arch/mips/mm/tlbex.c
> +++ b/arch/mips/mm/tlbex.c
> @@ -848,8 +848,8 @@ void build_get_pmde64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
>  		/* Clear lower 23 bits of context. */
>  		uasm_i_dins(p, ptr, 0, 0, 23);
>  
> -		/* 1 0	1 0 1  << 6  xkphys cached */
> -		uasm_i_ori(p, ptr, ptr, 0x540);
> +		/* insert bit[63:59] of CAC_BASE into bit[11:6] of ptr */
> +		uasm_i_ori(p, ptr, ptr, ((u64)(CAC_BASE) >> 53));

you want to use bits 63..59 but picking bits 63..53 with this.  While
bits 58..53 are probably 0, wouldn't it make also sense to mask them out ?

>  		uasm_i_drotr(p, ptr, ptr, 11);
>  #elif defined(CONFIG_SMP)
>  		UASM_i_CPUID_MFC0(p, ptr, SMP_CPUID_REG);
> @@ -1164,8 +1164,9 @@ build_fast_tlb_refill_handler (u32 **p, struct uasm_label **l,
>  
>  	if (pgd_reg == -1) {
>  		vmalloc_branch_delay_filled = 1;
> -		/* 1 0	1 0 1  << 6  xkphys cached */
> -		uasm_i_ori(p, ptr, ptr, 0x540);
> +		/* insert bit[63:59] of CAC_BASE into bit[11:6] of ptr */
> +		uasm_i_ori(p, ptr, ptr, ((u64)(CAC_BASE) >> 53));
> +
>  		uasm_i_drotr(p, ptr, ptr, 11);
>  	}
>  
> @@ -1292,7 +1293,6 @@ build_fast_tlb_refill_handler (u32 **p, struct uasm_label **l,
>  
>  	return rv;
>  }
> -
>  /*

why are you removing this empty line ? I'd prefer that it stays there...

>   * For a 64-bit kernel, we are using the 64-bit XTLB refill exception
>   * because EXL == 0.  If we wrap, we can also use the 32 instruction
> -- 
> 2.17.1

-- 
Crap can work. Given enough thrust pigs will fly, but it's not necessarily a
good idea.                                                [ RFC1925, 2.3 ]

Re: [PATCH 2/2] MIPS: loongson64: alloc pglist_data at run time

[Thomas Bogendoerfer]

On Tue, Mar 09, 2021 at 04:02:10PM +0800, Huang Pei wrote:
> Loongson64 allocates arrays of pglist_data statically and is located
> at Node 0, and cpu from Nodes other than 0 need remote access to
> pglist_data and zone info.
> 
> Delay pglist_data allocation till run time, and make it NUMA-aware
> 
> Signed-off-by: Huang Pei <huangpei@loongson.cn>
> ---
>  arch/mips/loongson64/numa.c | 17 ++++++++++++++---
>  1 file changed, 14 insertions(+), 3 deletions(-)

applied to mips-next.

This patch looks independant from the first one in this series (that's
why I've applied it). So please post such patches as single patches
and not as series.

Thomas.

-- 
Crap can work. Given enough thrust pigs will fly, but it's not necessarily a
good idea.                                                [ RFC1925, 2.3 ]

Re: [PATCH V4]: minor cleanup and improvement

[Maciej W. Rozycki]

On Tue, 9 Mar 2021, Huang Pei wrote:

> [PATCH 1/2] V4 vs V3:

 It will help if you don't change the subject proper of the cover letter 
with every iteration of a patch series, as in that case mail user agents 
(at least the sane ones) will group all iterations together in the thread 
sorting mode.  With the subject changed every time the link is lost and 
submissions are scattered all over the mail folder.

  Maciej

[PATCH 2/2] MIPS: loongson64: alloc pglist_data at run time

[Huang Pei]

Loongson64 allocates arrays of pglist_data statically and is located
at Node 0, and cpu from Nodes other than 0 need remote access to
pglist_data and zone info.

Delay pglist_data allocation till run time, and make it NUMA-aware

Signed-off-by: Huang Pei <huangpei@loongson.cn>
---
 arch/mips/loongson64/numa.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/arch/mips/loongson64/numa.c b/arch/mips/loongson64/numa.c
index cf9459f79f9b..afafd367cb38 100644
--- a/arch/mips/loongson64/numa.c
+++ b/arch/mips/loongson64/numa.c
@@ -26,7 +26,6 @@
 #include <asm/wbflush.h>
 #include <boot_param.h>
 
-static struct pglist_data prealloc__node_data[MAX_NUMNODES];
 unsigned char __node_distances[MAX_NUMNODES][MAX_NUMNODES];
 EXPORT_SYMBOL(__node_distances);
 struct pglist_data *__node_data[MAX_NUMNODES];
@@ -151,8 +150,12 @@ static void __init szmem(unsigned int node)
 
 static void __init node_mem_init(unsigned int node)
 {
+	struct pglist_data *nd;
 	unsigned long node_addrspace_offset;
 	unsigned long start_pfn, end_pfn;
+	unsigned long nd_pa;
+	int tnid;
+	const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES);
 
 	node_addrspace_offset = nid_to_addrbase(node);
 	pr_info("Node%d's addrspace_offset is 0x%lx\n",
@@ -162,8 +165,16 @@ static void __init node_mem_init(unsigned int node)
 	pr_info("Node%d: start_pfn=0x%lx, end_pfn=0x%lx\n",
 		node, start_pfn, end_pfn);
 
-	__node_data[node] = prealloc__node_data + node;
-
+	nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, node);
+	if (!nd_pa)
+		panic("Cannot allocate %zu bytes for node %d data\n",
+		      nd_size, node);
+	nd = __va(nd_pa);
+	memset(nd, 0, sizeof(struct pglist_data));
+	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
+	if (tnid != node)
+		pr_info("NODE_DATA(%d) on node %d\n", node, tnid);
+	__node_data[node] = nd;
 	NODE_DATA(node)->node_start_pfn = start_pfn;
 	NODE_DATA(node)->node_spanned_pages = end_pfn - start_pfn;
 
-- 
2.17.1