From 0e5e7f5e9700661c3ddd95501743fb52fec1ab07 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 25 May 2017 16:33:52 +1000 Subject: powerpc/64: Reclaim CPU_FTR_SUBCORE We are running low on CPU feature bits, so we only want to use them when it's really necessary. CPU_FTR_SUBCORE is only used in one place, and only in C, so we don't need it in order to make asm patching work. It can only be set on "Power8" CPUs, which in practice means POWER8, POWER8E and POWER8NVL. There are no plans to implement it on future CPUs, but if there ever were we could retrofit it then. Although KVM uses subcores, it never looks at the CPU feature, it either looks at the ISA level or the threads_per_subcore value. So drop the CPU feature and do a PVR check instead. Drop the device tree "subcore" feature as we no longer support doing anything with it, and we will drop it from skiboot too. Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/cputable.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index c2d509584a98..d02ad93bf708 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -214,7 +214,6 @@ enum { #define CPU_FTR_DAWR LONG_ASM_CONST(0x0400000000000000) #define CPU_FTR_DABRX LONG_ASM_CONST(0x0800000000000000) #define CPU_FTR_PMAO_BUG LONG_ASM_CONST(0x1000000000000000) -#define CPU_FTR_SUBCORE LONG_ASM_CONST(0x2000000000000000) #define CPU_FTR_POWER9_DD1 LONG_ASM_CONST(0x4000000000000000) #ifndef __ASSEMBLY__ @@ -463,7 +462,7 @@ enum { CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \ - CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_SUBCORE) + CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP) #define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG) #define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL) #define CPU_FTRS_POWER9 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ -- cgit v1.2.3 From ba4a648f12f4cd0a8003dd229b6ca8a53348ee4b Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 6 Jun 2017 20:23:57 +1000 Subject: powerpc/numa: Fix percpu allocations to be NUMA aware In commit 8c272261194d ("powerpc/numa: Enable USE_PERCPU_NUMA_NODE_ID"), we switched to the generic implementation of cpu_to_node(), which uses a percpu variable to hold the NUMA node for each CPU. Unfortunately we neglected to notice that we use cpu_to_node() in the allocation of our percpu areas, leading to a chicken and egg problem. In practice what happens is when we are setting up the percpu areas, cpu_to_node() reports that all CPUs are on node 0, so we allocate all percpu areas on node 0. This is visible in the dmesg output, as all pcpu allocs being in group 0: pcpu-alloc: [0] 00 01 02 03 [0] 04 05 06 07 pcpu-alloc: [0] 08 09 10 11 [0] 12 13 14 15 pcpu-alloc: [0] 16 17 18 19 [0] 20 21 22 23 pcpu-alloc: [0] 24 25 26 27 [0] 28 29 30 31 pcpu-alloc: [0] 32 33 34 35 [0] 36 37 38 39 pcpu-alloc: [0] 40 41 42 43 [0] 44 45 46 47 To fix it we need an early_cpu_to_node() which can run prior to percpu being setup. We already have the numa_cpu_lookup_table we can use, so just plumb it in. With the patch dmesg output shows two groups, 0 and 1: pcpu-alloc: [0] 00 01 02 03 [0] 04 05 06 07 pcpu-alloc: [0] 08 09 10 11 [0] 12 13 14 15 pcpu-alloc: [0] 16 17 18 19 [0] 20 21 22 23 pcpu-alloc: [1] 24 25 26 27 [1] 28 29 30 31 pcpu-alloc: [1] 32 33 34 35 [1] 36 37 38 39 pcpu-alloc: [1] 40 41 42 43 [1] 44 45 46 47 We can also check the data_offset in the paca of various CPUs, with the fix we see: CPU 0: data_offset = 0x0ffe8b0000 CPU 24: data_offset = 0x1ffe5b0000 And we can see from dmesg that CPU 24 has an allocation on node 1: node 0: [mem 0x0000000000000000-0x0000000fffffffff] node 1: [mem 0x0000001000000000-0x0000001fffffffff] Cc: stable@vger.kernel.org # v3.16+ Fixes: 8c272261194d ("powerpc/numa: Enable USE_PERCPU_NUMA_NODE_ID") Signed-off-by: Michael Ellerman Reviewed-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/topology.h | 14 ++++++++++++++ arch/powerpc/kernel/setup_64.c | 4 ++-- 2 files changed, 16 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 8b3b46b7b0f2..329771559cbb 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -44,8 +44,22 @@ extern void __init dump_numa_cpu_topology(void); extern int sysfs_add_device_to_node(struct device *dev, int nid); extern void sysfs_remove_device_from_node(struct device *dev, int nid); +static inline int early_cpu_to_node(int cpu) +{ + int nid; + + nid = numa_cpu_lookup_table[cpu]; + + /* + * Fall back to node 0 if nid is unset (it should be, except bugs). + * This allows callers to safely do NODE_DATA(early_cpu_to_node(cpu)). + */ + return (nid < 0) ? 0 : nid; +} #else +static inline int early_cpu_to_node(int cpu) { return 0; } + static inline void dump_numa_cpu_topology(void) {} static inline int sysfs_add_device_to_node(struct device *dev, int nid) diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index f35ff9dea4fb..a8c1f99e9607 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -661,7 +661,7 @@ void __init emergency_stack_init(void) static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) { - return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align, + return __alloc_bootmem_node(NODE_DATA(early_cpu_to_node(cpu)), size, align, __pa(MAX_DMA_ADDRESS)); } @@ -672,7 +672,7 @@ static void __init pcpu_fc_free(void *ptr, size_t size) static int pcpu_cpu_distance(unsigned int from, unsigned int to) { - if (cpu_to_node(from) == cpu_to_node(to)) + if (early_cpu_to_node(from) == early_cpu_to_node(to)) return LOCAL_DISTANCE; else return REMOTE_DISTANCE; -- cgit v1.2.3 From 92d9dfda8b547cc292af27e11e11c9eff3bb574f Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 1 Jun 2017 20:05:04 +0530 Subject: powerpc/mm/4k: Limit 4k page size config to 64TB virtual address space Supporting 512TB requires us to do a order 3 allocation for level 1 page table (pgd). This results in page allocation failures with certain workloads. For now limit 4k linux page size config to 64TB. Fixes: f6eedbba7a26 ("powerpc/mm/hash: Increase VA range to 128TB") Reported-by: Hugh Dickins Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/hash-4k.h | 2 +- arch/powerpc/include/asm/processor.h | 25 ++++++++++++------------- arch/powerpc/kernel/setup-common.c | 2 +- arch/powerpc/mm/mmu_context_book3s64.c | 2 +- 4 files changed, 15 insertions(+), 16 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index b4b5e6b671ca..0c4e470571ca 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -8,7 +8,7 @@ #define H_PTE_INDEX_SIZE 9 #define H_PMD_INDEX_SIZE 7 #define H_PUD_INDEX_SIZE 9 -#define H_PGD_INDEX_SIZE 12 +#define H_PGD_INDEX_SIZE 9 #ifndef __ASSEMBLY__ #define H_PTE_TABLE_SIZE (sizeof(pte_t) << H_PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index a2123f291ab0..bb99b651085a 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -110,13 +110,18 @@ void release_thread(struct task_struct *); #define TASK_SIZE_128TB (0x0000800000000000UL) #define TASK_SIZE_512TB (0x0002000000000000UL) -#ifdef CONFIG_PPC_BOOK3S_64 +/* + * For now 512TB is only supported with book3s and 64K linux page size. + */ +#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_64K_PAGES) /* * Max value currently used: */ -#define TASK_SIZE_USER64 TASK_SIZE_512TB +#define TASK_SIZE_USER64 TASK_SIZE_512TB +#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_128TB #else -#define TASK_SIZE_USER64 TASK_SIZE_64TB +#define TASK_SIZE_USER64 TASK_SIZE_64TB +#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_64TB #endif /* @@ -132,7 +137,7 @@ void release_thread(struct task_struct *); * space during mmap's. */ #define TASK_UNMAPPED_BASE_USER32 (PAGE_ALIGN(TASK_SIZE_USER32 / 4)) -#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(TASK_SIZE_128TB / 4)) +#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(DEFAULT_MAP_WINDOW_USER64 / 4)) #define TASK_UNMAPPED_BASE ((is_32bit_task()) ? \ TASK_UNMAPPED_BASE_USER32 : TASK_UNMAPPED_BASE_USER64 ) @@ -143,21 +148,15 @@ void release_thread(struct task_struct *); * with 128TB and conditionally enable upto 512TB */ #ifdef CONFIG_PPC_BOOK3S_64 -#define DEFAULT_MAP_WINDOW ((is_32bit_task()) ? \ - TASK_SIZE_USER32 : TASK_SIZE_128TB) +#define DEFAULT_MAP_WINDOW ((is_32bit_task()) ? \ + TASK_SIZE_USER32 : DEFAULT_MAP_WINDOW_USER64) #else #define DEFAULT_MAP_WINDOW TASK_SIZE #endif #ifdef __powerpc64__ -#ifdef CONFIG_PPC_BOOK3S_64 -/* Limit stack to 128TB */ -#define STACK_TOP_USER64 TASK_SIZE_128TB -#else -#define STACK_TOP_USER64 TASK_SIZE_USER64 -#endif - +#define STACK_TOP_USER64 DEFAULT_MAP_WINDOW_USER64 #define STACK_TOP_USER32 TASK_SIZE_USER32 #define STACK_TOP (is_32bit_task() ? \ diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 71dcda91755d..857129acf960 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -928,7 +928,7 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_PPC_MM_SLICES #ifdef CONFIG_PPC64 - init_mm.context.addr_limit = TASK_SIZE_128TB; + init_mm.context.addr_limit = DEFAULT_MAP_WINDOW_USER64; #else #error "context.addr_limit not initialized." #endif diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index c6dca2ae78ef..a3edf813d455 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -99,7 +99,7 @@ static int hash__init_new_context(struct mm_struct *mm) * mm->context.addr_limit. Default to max task size so that we copy the * default values to paca which will help us to handle slb miss early. */ - mm->context.addr_limit = TASK_SIZE_128TB; + mm->context.addr_limit = DEFAULT_MAP_WINDOW_USER64; /* * The old code would re-promote on fork, we don't do that when using -- cgit v1.2.3