[PATCH V2 04/12] MIPS: c-r4k: Add r4k_blast_scache_node for Loongson-3

[PATCH V2 04/12] MIPS: c-r4k: Add r4k_blast_scache_node for Loongson-3

[Huacai Chen]

For multi-node Loongson-3 (NUMA configuration), r4k_blast_scache() can
only flush Node-0's scache. So we add r4k_blast_scache_node() by using
(CAC_BASE | (node_id << NODE_ADDRSPACE_SHIFT)) instead of CKSEG0 as the
start address.

Cc: <stable@vger.kernel.org> # 3.15+
Signed-off-by: Huacai Chen <chenhc@lemote.com>
---
 arch/mips/include/asm/r4kcache.h | 34 ++++++++++++++++++++++++++++++++
 arch/mips/mm/c-r4k.c             | 42 +++++++++++++++++++++++++++++++++-------
 2 files changed, 69 insertions(+), 7 deletions(-)

diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h
index 7f12d7e..c1f2806 100644
--- a/arch/mips/include/asm/r4kcache.h
+++ b/arch/mips/include/asm/r4kcache.h
@@ -747,4 +747,38 @@ __BUILD_BLAST_CACHE_RANGE(s, scache, Hit_Writeback_Inv_SD, , )
 __BUILD_BLAST_CACHE_RANGE(inv_d, dcache, Hit_Invalidate_D, , )
 __BUILD_BLAST_CACHE_RANGE(inv_s, scache, Hit_Invalidate_SD, , )
 
+#ifndef pa_to_nid
+#define pa_to_nid(addr) 0
+#endif
+
+#ifndef NODE_ADDRSPACE_SHIFT
+#define nid_to_addrbase(nid) 0
+#else
+#define nid_to_addrbase(nid) (nid << NODE_ADDRSPACE_SHIFT)
+#endif
+
+#define __BUILD_BLAST_CACHE_NODE(pfx, desc, indexop, hitop, lsize)	\
+static inline void blast_##pfx##cache##lsize##_node(long node)		\
+{									\
+	unsigned long start = CAC_BASE | nid_to_addrbase(node);		\
+	unsigned long end = start + current_cpu_data.desc.waysize;	\
+	unsigned long ws_inc = 1UL << current_cpu_data.desc.waybit;	\
+	unsigned long ws_end = current_cpu_data.desc.ways <<		\
+			       current_cpu_data.desc.waybit;		\
+	unsigned long ws, addr;						\
+									\
+	__##pfx##flush_prologue						\
+									\
+	for (ws = 0; ws < ws_end; ws += ws_inc)				\
+		for (addr = start; addr < end; addr += lsize * 32)	\
+			cache##lsize##_unroll32(addr|ws, indexop);	\
+									\
+	__##pfx##flush_epilogue						\
+}
+
+__BUILD_BLAST_CACHE_NODE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 16)
+__BUILD_BLAST_CACHE_NODE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 32)
+__BUILD_BLAST_CACHE_NODE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 64)
+__BUILD_BLAST_CACHE_NODE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 128)
+
 #endif /* _ASM_R4KCACHE_H */
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 6f534b20..155f5f5 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -459,11 +459,28 @@ static void r4k_blast_scache_setup(void)
 		r4k_blast_scache = blast_scache128;
 }
 
+static void (*r4k_blast_scache_node)(long node);
+
+static void r4k_blast_scache_node_setup(void)
+{
+	unsigned long sc_lsize = cpu_scache_line_size();
+
+	if (current_cpu_type() != CPU_LOONGSON3)
+		r4k_blast_scache_node = (void *)cache_noop;
+	else if (sc_lsize == 16)
+		r4k_blast_scache_node = blast_scache16_node;
+	else if (sc_lsize == 32)
+		r4k_blast_scache_node = blast_scache32_node;
+	else if (sc_lsize == 64)
+		r4k_blast_scache_node = blast_scache64_node;
+	else if (sc_lsize == 128)
+		r4k_blast_scache_node = blast_scache128_node;
+}
+
 static inline void local_r4k___flush_cache_all(void * args)
 {
 	switch (current_cpu_type()) {
 	case CPU_LOONGSON2:
-	case CPU_LOONGSON3:
 	case CPU_R4000SC:
 	case CPU_R4000MC:
 	case CPU_R4400SC:
@@ -480,6 +497,10 @@ static inline void local_r4k___flush_cache_all(void * args)
 		r4k_blast_scache();
 		break;
 
+	case CPU_LOONGSON3:
+		r4k_blast_scache_node(get_ebase_cpunum() >> 2);
+		break;
+
 	case CPU_BMIPS5000:
 		r4k_blast_scache();
 		__sync();
@@ -839,9 +860,12 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 
 	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
-		if (size >= scache_size)
-			r4k_blast_scache();
-		else
+		if (size >= scache_size) {
+			if (current_cpu_type() != CPU_LOONGSON3)
+				r4k_blast_scache();
+			else
+				r4k_blast_scache_node(pa_to_nid(addr));
+		} else
 			blast_scache_range(addr, addr + size);
 		preempt_enable();
 		__sync();
@@ -872,9 +896,12 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 
 	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
-		if (size >= scache_size)
-			r4k_blast_scache();
-		else {
+		if (size >= scache_size) {
+			if (current_cpu_type() != CPU_LOONGSON3)
+				r4k_blast_scache();
+			else
+				r4k_blast_scache_node(pa_to_nid(addr));
+		} else {
 			/*
 			 * There is no clearly documented alignment requirement
 			 * for the cache instruction on MIPS processors and
@@ -1905,6 +1932,7 @@ void r4k_cache_init(void)
 	r4k_blast_scache_page_setup();
 	r4k_blast_scache_page_indexed_setup();
 	r4k_blast_scache_setup();
+	r4k_blast_scache_node_setup();
 #ifdef CONFIG_EVA
 	r4k_blast_dcache_user_page_setup();
 	r4k_blast_icache_user_page_setup();
-- 
2.7.0

Re: [PATCH V2 04/12] MIPS: c-r4k: Add r4k_blast_scache_node for Loongson-3

[James Hogan]

[-- Attachment #1: Type: text/plain, Size: 3534 bytes --]

On Sat, Jan 27, 2018 at 11:19:05AM +0800, Huacai Chen wrote:
> For multi-node Loongson-3 (NUMA configuration), r4k_blast_scache() can
> only flush Node-0's scache. So we add r4k_blast_scache_node() by using
> (CAC_BASE | (node_id << NODE_ADDRSPACE_SHIFT)) instead of CKSEG0 as the
> start address.
> 
> Cc: <stable@vger.kernel.org> # 3.15+
> Signed-off-by: Huacai Chen <chenhc@lemote.com>
> ---
>  arch/mips/include/asm/r4kcache.h | 34 ++++++++++++++++++++++++++++++++
>  arch/mips/mm/c-r4k.c             | 42 +++++++++++++++++++++++++++++++++-------
>  2 files changed, 69 insertions(+), 7 deletions(-)
> 
> diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h
> index 7f12d7e..c1f2806 100644
> --- a/arch/mips/include/asm/r4kcache.h
> +++ b/arch/mips/include/asm/r4kcache.h
> @@ -747,4 +747,38 @@ __BUILD_BLAST_CACHE_RANGE(s, scache, Hit_Writeback_Inv_SD, , )
>  __BUILD_BLAST_CACHE_RANGE(inv_d, dcache, Hit_Invalidate_D, , )
>  __BUILD_BLAST_CACHE_RANGE(inv_s, scache, Hit_Invalidate_SD, , )
>  
> +#ifndef pa_to_nid
> +#define pa_to_nid(addr) 0
> +#endif
> +
> +#ifndef NODE_ADDRSPACE_SHIFT

To be sure you get the right definition of both of these if they exist,
and wherever this header is included, we should explicitly #include the
appropriate header (asm/mmzone.h?) from this header.

> +#define nid_to_addrbase(nid) 0
> +#else
> +#define nid_to_addrbase(nid) (nid << NODE_ADDRSPACE_SHIFT)

Technically this should have parentheses around nid.

It seems slightly inconsistent to have pa_to_nid() defined in mmzone.h,
but not the reverse nid_to_addrbase(). NODE_ADDRSPACE_SHIFT is very
loongson specific afterall.

Would it make sense to move it into
arch/mips/include/asm/mach-loongson64/mmzone.h and put the 0 definition
in #ifndef nid_to_addrbase?

> +#endif
> +
> +#define __BUILD_BLAST_CACHE_NODE(pfx, desc, indexop, hitop, lsize)	\

I think this is worthy of a quick comment to explain that this is very
specific to Loongson3.

>  #endif /* _ASM_R4KCACHE_H */
> diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
> index 6f534b20..155f5f5 100644
> --- a/arch/mips/mm/c-r4k.c
> +++ b/arch/mips/mm/c-r4k.c

...

> @@ -480,6 +497,10 @@ static inline void local_r4k___flush_cache_all(void * args)
>  		r4k_blast_scache();
>  		break;
>  
> +	case CPU_LOONGSON3:
> +		r4k_blast_scache_node(get_ebase_cpunum() >> 2);

I assume this can't use cpu_to_node() because it needs to work even when
NUMA=n? If so, I think it deserves a brief comment to explain that.

> +		break;
> +
>  	case CPU_BMIPS5000:
>  		r4k_blast_scache();
>  		__sync();
> @@ -839,9 +860,12 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
>  
>  	preempt_disable();
>  	if (cpu_has_inclusive_pcaches) {
> -		if (size >= scache_size)
> -			r4k_blast_scache();
> -		else
> +		if (size >= scache_size) {
> +			if (current_cpu_type() != CPU_LOONGSON3)
> +				r4k_blast_scache();
> +			else
> +				r4k_blast_scache_node(pa_to_nid(addr));

If I read this right, addr is a virtual address so this feels a bit
hacky, but I suppose its harmless since it'll probably always be memory
in xkphys space where pa_to_nid() will do the right thing. Perhaps a
comment along the lines of:
/* This assumes that addr is in XKPhys */

> +		} else

Please keep braces consistent, i.e. add to the trailing else statement
too.

Other than those niggles, the actual mechanism looks reasonable to me.

Thanks
James

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

[PATCH V2 05/12] MIPS: Loongson fix name confict - MEM_RESERVED

[Huacai Chen]

MEM_RESERVED is used as a value of enum mem_type in include/linux/
edac.h. This will make failure to build for Loongson in some case:
for example with CONFIG_RAS enabled.

So here rename MEM_RESERVED to SYSTEM_RAM_RESERVED in Loongson code.

Cc: <stable@vger.kernel.org> # 3.15+
Reviewed-by: James Hogan <jhogan@kernel.org>
Signed-off-by: YunQiang Su <yunqiang.su@imgtec.com>
Signed-off-by: Huacai Chen <chenhc@lemote.com>
---
 arch/mips/include/asm/mach-loongson64/boot_param.h | 2 +-
 arch/mips/loongson64/common/mem.c                  | 2 +-
 arch/mips/loongson64/loongson-3/numa.c             | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/mips/include/asm/mach-loongson64/boot_param.h b/arch/mips/include/asm/mach-loongson64/boot_param.h
index 4f69f08..8c286be 100644
--- a/arch/mips/include/asm/mach-loongson64/boot_param.h
+++ b/arch/mips/include/asm/mach-loongson64/boot_param.h
@@ -4,7 +4,7 @@
 
 #define SYSTEM_RAM_LOW		1
 #define SYSTEM_RAM_HIGH		2
-#define MEM_RESERVED		3
+#define SYSTEM_RAM_RESERVED	3
 #define PCI_IO			4
 #define PCI_MEM			5
 #define LOONGSON_CFG_REG	6
diff --git a/arch/mips/loongson64/common/mem.c b/arch/mips/loongson64/common/mem.c
index b01d524..c549e52 100644
--- a/arch/mips/loongson64/common/mem.c
+++ b/arch/mips/loongson64/common/mem.c
@@ -79,7 +79,7 @@ void __init prom_init_memory(void)
 					(u64)loongson_memmap->map[i].mem_size << 20,
 					BOOT_MEM_RAM);
 				break;
-			case MEM_RESERVED:
+			case SYSTEM_RAM_RESERVED:
 				add_memory_region(loongson_memmap->map[i].mem_start,
 					(u64)loongson_memmap->map[i].mem_size << 20,
 					BOOT_MEM_RESERVED);
diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/loongson-3/numa.c
index f17ef52..9717106 100644
--- a/arch/mips/loongson64/loongson-3/numa.c
+++ b/arch/mips/loongson64/loongson-3/numa.c
@@ -166,7 +166,7 @@ static void __init szmem(unsigned int node)
 			memblock_add_node(PFN_PHYS(start_pfn),
 				PFN_PHYS(end_pfn - start_pfn), node);
 			break;
-		case MEM_RESERVED:
+		case SYSTEM_RAM_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,
-- 
2.7.0

[PATCH V2 06/12] MIPS: Ensure pmd_present() returns false after pmd_mknotpresent()

[Huacai Chen]

This patch is borrowed from ARM64 to ensure pmd_present() returns false
after pmd_mknotpresent(). This is needed for THP.

Cc: <stable@vger.kernel.org> # 3.8+
References: 5bb1cc0ff9a6 ("arm64: Ensure pmd_present() returns false after pmd_mknotpresent()")
Reviewed-by: James Hogan <jhogan@kernel.org>
Signed-off-by: Huacai Chen <chenhc@lemote.com>
---
 arch/mips/include/asm/pgtable-64.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h
index 0036ea0..93a9dce 100644
--- a/arch/mips/include/asm/pgtable-64.h
+++ b/arch/mips/include/asm/pgtable-64.h
@@ -265,6 +265,11 @@ static inline int pmd_bad(pmd_t pmd)
 
 static inline int pmd_present(pmd_t pmd)
 {
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
+	if (unlikely(pmd_val(pmd) & _PAGE_HUGE))
+		return pmd_val(pmd) & _PAGE_PRESENT;
+#endif
+
 	return pmd_val(pmd) != (unsigned long) invalid_pte_table;
 }
 
-- 
2.7.0

[PATCH V2 11/12] MIPS: Loongson-3: Fix CPU UART irq delivery problem

[Huacai Chen]

Masking/unmasking the CPU UART irq in CP0_Status (and redirecting it to
other CPUs) may cause interrupts be lost, especially in multi-package
machines (Package-0's UART irq cannot be delivered to others). So make
mask_loongson_irq() and unmask_loongson_irq() be no-ops.

Cc: stable@vger.kernel.org
Signed-off-by: Huacai Chen <chenhc@lemote.com>
---
 arch/mips/loongson64/loongson-3/irq.c | 41 ++---------------------------------
 1 file changed, 2 insertions(+), 39 deletions(-)

diff --git a/arch/mips/loongson64/loongson-3/irq.c b/arch/mips/loongson64/loongson-3/irq.c
index cbeb20f..e8381ec 100644
--- a/arch/mips/loongson64/loongson-3/irq.c
+++ b/arch/mips/loongson64/loongson-3/irq.c
@@ -102,45 +102,8 @@ static struct irqaction cascade_irqaction = {
 	.name = "cascade",
 };
 
-static inline void mask_loongson_irq(struct irq_data *d)
-{
-	clear_c0_status(0x100 << (d->irq - MIPS_CPU_IRQ_BASE));
-	irq_disable_hazard();
-
-	/* Workaround: UART IRQ may deliver to any core */
-	if (d->irq == LOONGSON_UART_IRQ) {
-		int cpu = smp_processor_id();
-		int node_id = cpu_logical_map(cpu) / loongson_sysconf.cores_per_node;
-		int core_id = cpu_logical_map(cpu) % loongson_sysconf.cores_per_node;
-		u64 intenclr_addr = smp_group[node_id] |
-			(u64)(&LOONGSON_INT_ROUTER_INTENCLR);
-		u64 introuter_lpc_addr = smp_group[node_id] |
-			(u64)(&LOONGSON_INT_ROUTER_LPC);
-
-		*(volatile u32 *)intenclr_addr = 1 << 10;
-		*(volatile u8 *)introuter_lpc_addr = 0x10 + (1<<core_id);
-	}
-}
-
-static inline void unmask_loongson_irq(struct irq_data *d)
-{
-	/* Workaround: UART IRQ may deliver to any core */
-	if (d->irq == LOONGSON_UART_IRQ) {
-		int cpu = smp_processor_id();
-		int node_id = cpu_logical_map(cpu) / loongson_sysconf.cores_per_node;
-		int core_id = cpu_logical_map(cpu) % loongson_sysconf.cores_per_node;
-		u64 intenset_addr = smp_group[node_id] |
-			(u64)(&LOONGSON_INT_ROUTER_INTENSET);
-		u64 introuter_lpc_addr = smp_group[node_id] |
-			(u64)(&LOONGSON_INT_ROUTER_LPC);
-
-		*(volatile u32 *)intenset_addr = 1 << 10;
-		*(volatile u8 *)introuter_lpc_addr = 0x10 + (1<<core_id);
-	}
-
-	set_c0_status(0x100 << (d->irq - MIPS_CPU_IRQ_BASE));
-	irq_enable_hazard();
-}
+static inline void mask_loongson_irq(struct irq_data *d) { }
+static inline void unmask_loongson_irq(struct irq_data *d) { }
 
  /* For MIPS IRQs which shared by all cores */
 static struct irq_chip loongson_irq_chip = {
-- 
2.7.0

Re: [PATCH V2 11/12] MIPS: Loongson-3: Fix CPU UART irq delivery problem

[James Hogan]

[-- Attachment #1: Type: text/plain, Size: 842 bytes --]

On Sat, Jan 27, 2018 at 11:23:00AM +0800, Huacai Chen wrote:
> Masking/unmasking the CPU UART irq in CP0_Status (and redirecting it to
> other CPUs) may cause interrupts be lost, especially in multi-package
> machines (Package-0's UART irq cannot be delivered to others). So make
> mask_loongson_irq() and unmask_loongson_irq() be no-ops.
> 
> Cc: stable@vger.kernel.org

...

> -static inline void mask_loongson_irq(struct irq_data *d)
> -{
> -	clear_c0_status(0x100 << (d->irq - MIPS_CPU_IRQ_BASE));
> -	irq_disable_hazard();
> -
> -	/* Workaround: UART IRQ may deliver to any core */

Wouldn't removing this self-described "workaround" bring back the
original problem?

At the very least you need a much better explanation of why these
workarounds are no longer applicable and can be safely removed.

Cheers
James

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]