From 1d0761d2557d1540727723e4f05395d53321d555 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 14 Dec 2016 13:36:51 +1100 Subject: powerpc/powernv: Initialise nest mmu POWER9 contains an off core mmu called the nest mmu (NMMU). This is used by other hardware units on the chip to translate virtual addresses into real addresses. The unit attempting an address translation provides the majority of the context required for the translation request except for the base address of the partition table (ie. the PTCR) which needs to be programmed into the NMMU. This patch adds a call to OPAL to set the PTCR for the nest mmu in opal_init(). Signed-off-by: Alistair Popple Signed-off-by: Michael Ellerman --- arch/powerpc/mm/pgtable-radix.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc/mm/pgtable-radix.c') diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index cfa53ccc8baf..086522b7c60f 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -18,6 +18,7 @@ #include #include #include +#include #include @@ -438,6 +439,7 @@ void radix__mmu_cleanup_all(void) lpcr = mfspr(SPRN_LPCR); mtspr(SPRN_LPCR, lpcr & ~LPCR_UPRT); mtspr(SPRN_PTCR, 0); + powernv_set_nmmu_ptcr(0); radix__flush_tlb_all(); } } -- cgit v1.2.3 From b5200ec9edf038459619fce9988842efa751a2c5 Mon Sep 17 00:00:00 2001 From: Reza Arbab Date: Mon, 16 Jan 2017 13:07:43 -0600 Subject: powerpc/mm: refactor radix physical page mapping Move the page mapping code in radix_init_pgtable() into a separate function that will also be used for memory hotplug. The current goto loop progressively decreases its mapping size as it covers the tail of a range whose end is unaligned. Change this to a for loop which can do the same for both ends of the range. Signed-off-by: Reza Arbab Signed-off-by: Michael Ellerman --- arch/powerpc/mm/pgtable-radix.c | 88 +++++++++++++++++++++++------------------ 1 file changed, 50 insertions(+), 38 deletions(-) (limited to 'arch/powerpc/mm/pgtable-radix.c') diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 086522b7c60f..c0365eca7f81 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -108,54 +108,66 @@ set_the_pte: return 0; } +static inline void __meminit print_mapping(unsigned long start, + unsigned long end, + unsigned long size) +{ + if (end <= start) + return; + + pr_info("Mapped range 0x%lx - 0x%lx with 0x%lx\n", start, end, size); +} + +static int __meminit create_physical_mapping(unsigned long start, + unsigned long end) +{ + unsigned long addr, mapping_size = 0; + + start = _ALIGN_UP(start, PAGE_SIZE); + for (addr = start; addr < end; addr += mapping_size) { + unsigned long gap, previous_size; + int rc; + + gap = end - addr; + previous_size = mapping_size; + + if (IS_ALIGNED(addr, PUD_SIZE) && gap >= PUD_SIZE && + mmu_psize_defs[MMU_PAGE_1G].shift) + mapping_size = PUD_SIZE; + else if (IS_ALIGNED(addr, PMD_SIZE) && gap >= PMD_SIZE && + mmu_psize_defs[MMU_PAGE_2M].shift) + mapping_size = PMD_SIZE; + else + mapping_size = PAGE_SIZE; + + if (mapping_size != previous_size) { + print_mapping(start, addr, previous_size); + start = addr; + } + + rc = radix__map_kernel_page((unsigned long)__va(addr), addr, + PAGE_KERNEL_X, mapping_size); + if (rc) + return rc; + } + + print_mapping(start, addr, mapping_size); + return 0; +} + static void __init radix_init_pgtable(void) { - int loop_count; - u64 base, end, start_addr; unsigned long rts_field; struct memblock_region *reg; - unsigned long linear_page_size; /* We don't support slb for radix */ mmu_slb_size = 0; /* * Create the linear mapping, using standard page size for now */ - loop_count = 0; - for_each_memblock(memory, reg) { - - start_addr = reg->base; - -redo: - if (loop_count < 1 && mmu_psize_defs[MMU_PAGE_1G].shift) - linear_page_size = PUD_SIZE; - else if (loop_count < 2 && mmu_psize_defs[MMU_PAGE_2M].shift) - linear_page_size = PMD_SIZE; - else - linear_page_size = PAGE_SIZE; - - base = _ALIGN_UP(start_addr, linear_page_size); - end = _ALIGN_DOWN(reg->base + reg->size, linear_page_size); - - pr_info("Mapping range 0x%lx - 0x%lx with 0x%lx\n", - (unsigned long)base, (unsigned long)end, - linear_page_size); - - while (base < end) { - radix__map_kernel_page((unsigned long)__va(base), - base, PAGE_KERNEL_X, - linear_page_size); - base += linear_page_size; - } - /* - * map the rest using lower page size - */ - if (end < reg->base + reg->size) { - start_addr = end; - loop_count++; - goto redo; - } - } + for_each_memblock(memory, reg) + WARN_ON(create_physical_mapping(reg->base, + reg->base + reg->size)); /* * Allocate Partition table and process table for the * host. -- cgit v1.2.3 From 6cc27341b21a81052f36c137bc44cf55f83e46ff Mon Sep 17 00:00:00 2001 From: Reza Arbab Date: Mon, 16 Jan 2017 13:07:44 -0600 Subject: powerpc/mm: add radix__create_section_mapping() Wire up memory hotplug page mapping for radix. Share the mapping function already used by radix_init_pgtable(). Signed-off-by: Reza Arbab Acked-by: Balbir Singh Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/radix.h | 4 ++++ arch/powerpc/mm/pgtable-book3s64.c | 2 +- arch/powerpc/mm/pgtable-radix.c | 7 +++++++ 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/mm/pgtable-radix.c') diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index b4d1302387a3..43c25718de61 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -291,5 +291,9 @@ static inline unsigned long radix__get_tree_size(void) } return rts_field; } + +#ifdef CONFIG_MEMORY_HOTPLUG +int radix__create_section_mapping(unsigned long start, unsigned long end); +#endif /* CONFIG_MEMORY_HOTPLUG */ #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index 653ff6c74ebe..2b13f6b87e25 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -131,7 +131,7 @@ void mmu_cleanup_all(void) int create_section_mapping(unsigned long start, unsigned long end) { if (radix_enabled()) - return -ENODEV; + return radix__create_section_mapping(start, end); return hash__create_section_mapping(start, end); } diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index c0365eca7f81..7829e09ab4dd 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -481,6 +481,13 @@ void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base, memblock_set_current_limit(first_memblock_base + first_memblock_size); } +#ifdef CONFIG_MEMORY_HOTPLUG +int __ref radix__create_section_mapping(unsigned long start, unsigned long end) +{ + return create_physical_mapping(start, end); +} +#endif /* CONFIG_MEMORY_HOTPLUG */ + #ifdef CONFIG_SPARSEMEM_VMEMMAP int __meminit radix__vmemmap_create_mapping(unsigned long start, unsigned long page_size, -- cgit v1.2.3 From 4b5d62ca17a1cd2ffc8399e1d1c3ebbabf16e78f Mon Sep 17 00:00:00 2001 From: Reza Arbab Date: Mon, 16 Jan 2017 13:07:45 -0600 Subject: powerpc/mm: add radix__remove_section_mapping() Tear down and free the four-level page tables of physical mappings during memory hotremove. Borrow the basic structure of remove_pagetable() and friends from the identically-named x86 functions. Reduce the frequency of tlb flushes and page_table_lock spinlocks by only doing them in the outermost function. There was some question as to whether the locking is needed at all. Leave it for now, but we could consider dropping it. Memory must be offline to be removed, thus not in use. So there shouldn't be the sort of concurrent page walking activity here that might prompt us to use RCU. Signed-off-by: Reza Arbab Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/radix.h | 1 + arch/powerpc/mm/pgtable-book3s64.c | 2 +- arch/powerpc/mm/pgtable-radix.c | 133 +++++++++++++++++++++++++++++ 3 files changed, 135 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/mm/pgtable-radix.c') diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 43c25718de61..0032b662284c 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -294,6 +294,7 @@ static inline unsigned long radix__get_tree_size(void) #ifdef CONFIG_MEMORY_HOTPLUG int radix__create_section_mapping(unsigned long start, unsigned long end); +int radix__remove_section_mapping(unsigned long start, unsigned long end); #endif /* CONFIG_MEMORY_HOTPLUG */ #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index 2b13f6b87e25..b798ff674fab 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -139,7 +139,7 @@ int create_section_mapping(unsigned long start, unsigned long end) int remove_section_mapping(unsigned long start, unsigned long end) { if (radix_enabled()) - return -ENODEV; + return radix__remove_section_mapping(start, end); return hash__remove_section_mapping(start, end); } diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 7829e09ab4dd..aef9d49f70ce 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -482,10 +482,143 @@ void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base, } #ifdef CONFIG_MEMORY_HOTPLUG +static void free_pte_table(pte_t *pte_start, pmd_t *pmd) +{ + pte_t *pte; + int i; + + for (i = 0; i < PTRS_PER_PTE; i++) { + pte = pte_start + i; + if (!pte_none(*pte)) + return; + } + + pte_free_kernel(&init_mm, pte_start); + pmd_clear(pmd); +} + +static void free_pmd_table(pmd_t *pmd_start, pud_t *pud) +{ + pmd_t *pmd; + int i; + + for (i = 0; i < PTRS_PER_PMD; i++) { + pmd = pmd_start + i; + if (!pmd_none(*pmd)) + return; + } + + pmd_free(&init_mm, pmd_start); + pud_clear(pud); +} + +static void remove_pte_table(pte_t *pte_start, unsigned long addr, + unsigned long end) +{ + unsigned long next; + pte_t *pte; + + pte = pte_start + pte_index(addr); + for (; addr < end; addr = next, pte++) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + if (next > end) + next = end; + + if (!pte_present(*pte)) + continue; + + pte_clear(&init_mm, addr, pte); + } +} + +static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr, + unsigned long end) +{ + unsigned long next; + pte_t *pte_base; + pmd_t *pmd; + + pmd = pmd_start + pmd_index(addr); + for (; addr < end; addr = next, pmd++) { + next = pmd_addr_end(addr, end); + + if (!pmd_present(*pmd)) + continue; + + if (pmd_huge(*pmd)) { + pte_clear(&init_mm, addr, (pte_t *)pmd); + continue; + } + + pte_base = (pte_t *)pmd_page_vaddr(*pmd); + remove_pte_table(pte_base, addr, next); + free_pte_table(pte_base, pmd); + } +} + +static void remove_pud_table(pud_t *pud_start, unsigned long addr, + unsigned long end) +{ + unsigned long next; + pmd_t *pmd_base; + pud_t *pud; + + pud = pud_start + pud_index(addr); + for (; addr < end; addr = next, pud++) { + next = pud_addr_end(addr, end); + + if (!pud_present(*pud)) + continue; + + if (pud_huge(*pud)) { + pte_clear(&init_mm, addr, (pte_t *)pud); + continue; + } + + pmd_base = (pmd_t *)pud_page_vaddr(*pud); + remove_pmd_table(pmd_base, addr, next); + free_pmd_table(pmd_base, pud); + } +} + +static void remove_pagetable(unsigned long start, unsigned long end) +{ + unsigned long addr, next; + pud_t *pud_base; + pgd_t *pgd; + + spin_lock(&init_mm.page_table_lock); + + for (addr = start; addr < end; addr = next) { + next = pgd_addr_end(addr, end); + + pgd = pgd_offset_k(addr); + if (!pgd_present(*pgd)) + continue; + + if (pgd_huge(*pgd)) { + pte_clear(&init_mm, addr, (pte_t *)pgd); + continue; + } + + pud_base = (pud_t *)pgd_page_vaddr(*pgd); + remove_pud_table(pud_base, addr, next); + } + + spin_unlock(&init_mm.page_table_lock); + radix__flush_tlb_kernel_range(start, end); +} + int __ref radix__create_section_mapping(unsigned long start, unsigned long end) { return create_physical_mapping(start, end); } + +int radix__remove_section_mapping(unsigned long start, unsigned long end) +{ + remove_pagetable(start, end); + return 0; +} #endif /* CONFIG_MEMORY_HOTPLUG */ #ifdef CONFIG_SPARSEMEM_VMEMMAP -- cgit v1.2.3 From 0d0a4bc2a6f7de19cb0256a55891955961d70b1c Mon Sep 17 00:00:00 2001 From: Reza Arbab Date: Mon, 16 Jan 2017 13:07:46 -0600 Subject: powerpc/mm: unstub radix__vmemmap_remove_mapping() Use remove_pagetable() and friends for radix vmemmap removal. We do not require the special-case handling of vmemmap done in the x86 versions of these functions. This is because vmemmap_free() has already freed the mapped pages, and calls us with an aligned address range. So, add a few failsafe WARNs, but otherwise the code to remove physical mappings is already sufficient for vmemmap. Signed-off-by: Reza Arbab Acked-by: Balbir Singh Signed-off-by: Michael Ellerman --- arch/powerpc/mm/pgtable-radix.c | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/mm/pgtable-radix.c') diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index aef9d49f70ce..30374586e01d 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -527,6 +527,15 @@ static void remove_pte_table(pte_t *pte_start, unsigned long addr, if (!pte_present(*pte)) continue; + if (!PAGE_ALIGNED(addr) || !PAGE_ALIGNED(next)) { + /* + * The vmemmap_free() and remove_section_mapping() + * codepaths call us with aligned addresses. + */ + WARN_ONCE(1, "%s: unaligned range\n", __func__); + continue; + } + pte_clear(&init_mm, addr, pte); } } @@ -546,6 +555,12 @@ static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr, continue; if (pmd_huge(*pmd)) { + if (!IS_ALIGNED(addr, PMD_SIZE) || + !IS_ALIGNED(next, PMD_SIZE)) { + WARN_ONCE(1, "%s: unaligned range\n", __func__); + continue; + } + pte_clear(&init_mm, addr, (pte_t *)pmd); continue; } @@ -571,6 +586,12 @@ static void remove_pud_table(pud_t *pud_start, unsigned long addr, continue; if (pud_huge(*pud)) { + if (!IS_ALIGNED(addr, PUD_SIZE) || + !IS_ALIGNED(next, PUD_SIZE)) { + WARN_ONCE(1, "%s: unaligned range\n", __func__); + continue; + } + pte_clear(&init_mm, addr, (pte_t *)pud); continue; } @@ -597,6 +618,12 @@ static void remove_pagetable(unsigned long start, unsigned long end) continue; if (pgd_huge(*pgd)) { + if (!IS_ALIGNED(addr, PGDIR_SIZE) || + !IS_ALIGNED(next, PGDIR_SIZE)) { + WARN_ONCE(1, "%s: unaligned range\n", __func__); + continue; + } + pte_clear(&init_mm, addr, (pte_t *)pgd); continue; } @@ -636,7 +663,7 @@ int __meminit radix__vmemmap_create_mapping(unsigned long start, #ifdef CONFIG_MEMORY_HOTPLUG void radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size) { - /* FIXME!! intel does more. We should free page tables mapping vmemmap ? */ + remove_pagetable(start, start + page_size); } #endif #endif -- cgit v1.2.3 From cc3d2940133d24000e2866b21e03ce32adfead0a Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 30 Jan 2017 21:21:36 +1100 Subject: powerpc/64: Enable use of radix MMU under hypervisor on POWER9 To use radix as a guest, we first need to tell the hypervisor via the ibm,client-architecture call first that we support POWER9 and architecture v3.00, and that we can do either radix or hash and that we would like to choose later using an hcall (the H_REGISTER_PROC_TBL hcall). Then we need to check whether the hypervisor agreed to us using radix. We need to do this very early on in the kernel boot process before any of the MMU initialization is done. If the hypervisor doesn't agree, we can't use radix and therefore clear the radix MMU feature bit. Later, when we have set up our process table, which points to the radix tree for each process, we need to install that using the H_REGISTER_PROC_TBL hcall. Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/mmu.h | 6 ++++++ arch/powerpc/include/asm/hvcall.h | 11 +++++++++++ arch/powerpc/include/asm/prom.h | 9 +++++++++ arch/powerpc/kernel/prom_init.c | 18 +++++++++++++++++- arch/powerpc/mm/init_64.c | 12 +++++++----- arch/powerpc/mm/pgtable-radix.c | 2 ++ arch/powerpc/platforms/pseries/lpar.c | 29 +++++++++++++++++++++++++++++ 7 files changed, 81 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/mm/pgtable-radix.c') diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index 8afb0e00f7d9..cea522c3bcae 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -138,5 +138,11 @@ static inline void setup_initial_memory_limit(phys_addr_t first_memblock_base, extern int (*register_process_table)(unsigned long base, unsigned long page_size, unsigned long tbl_size); +#ifdef CONFIG_PPC_PSERIES +extern void radix_init_pseries(void); +#else +static inline void radix_init_pseries(void) { }; +#endif + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_MMU_H_ */ diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 77ff1ba99d1f..54d11b3a6bf7 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -276,6 +276,7 @@ #define H_GET_MPP_X 0x314 #define H_SET_MODE 0x31C #define H_CLEAR_HPT 0x358 +#define H_REGISTER_PROC_TBL 0x37C #define H_SIGNAL_SYS_RESET 0x380 #define MAX_HCALL_OPCODE H_SIGNAL_SYS_RESET @@ -313,6 +314,16 @@ #define H_SIGNAL_SYS_RESET_ALL_OTHERS -2 /* >= 0 values are CPU number */ +/* Flag values used in H_REGISTER_PROC_TBL hcall */ +#define PROC_TABLE_OP_MASK 0x18 +#define PROC_TABLE_DEREG 0x10 +#define PROC_TABLE_NEW 0x18 +#define PROC_TABLE_TYPE_MASK 0x06 +#define PROC_TABLE_HPT_SLB 0x00 +#define PROC_TABLE_HPT_PT 0x02 +#define PROC_TABLE_RADIX 0x04 +#define PROC_TABLE_GTSE 0x01 + #ifndef __ASSEMBLY__ /** diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index e6d83d0fada7..8af2546ea593 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -121,6 +121,8 @@ struct of_drconf_cell { #define OV1_PPC_2_06 0x02 /* set if we support PowerPC 2.06 */ #define OV1_PPC_2_07 0x01 /* set if we support PowerPC 2.07 */ +#define OV1_PPC_3_00 0x80 /* set if we support PowerPC 3.00 */ + /* Option vector 2: Open Firmware options supported */ #define OV2_REAL_MODE 0x20 /* set if we want OF in real mode */ @@ -155,6 +157,13 @@ struct of_drconf_cell { #define OV5_PFO_HW_842 0x1140 /* PFO Compression Accelerator */ #define OV5_PFO_HW_ENCR 0x1120 /* PFO Encryption Accelerator */ #define OV5_SUB_PROCESSORS 0x1501 /* 1,2,or 4 Sub-Processors supported */ +#define OV5_XIVE_EXPLOIT 0x1701 /* XIVE exploitation supported */ +#define OV5_MMU_RADIX_300 0x1880 /* ISA v3.00 radix MMU supported */ +#define OV5_MMU_HASH_300 0x1840 /* ISA v3.00 hash MMU supported */ +#define OV5_MMU_SEGM_RADIX 0x1820 /* radix mode (no segmentation) */ +#define OV5_MMU_PROC_TBL 0x1810 /* hcall selects SLB or proc table */ +#define OV5_MMU_SLB 0x1800 /* always use SLB */ +#define OV5_MMU_GTSE 0x1808 /* Guest translation shootdown */ /* Option Vector 6: IBM PAPR hints */ #define OV6_LINUX 0x02 /* Linux is our OS */ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index ec47a939cbdd..358d43f8f84f 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -649,6 +649,7 @@ static void __init early_cmdline_parse(void) struct option_vector1 { u8 byte1; u8 arch_versions; + u8 arch_versions3; } __packed; struct option_vector2 { @@ -691,6 +692,9 @@ struct option_vector5 { u8 reserved2; __be16 reserved3; u8 subprocessors; + u8 byte22; + u8 intarch; + u8 mmu; } __packed; struct option_vector6 { @@ -700,7 +704,7 @@ struct option_vector6 { } __packed; struct ibm_arch_vec { - struct { u32 mask, val; } pvrs[10]; + struct { u32 mask, val; } pvrs[12]; u8 num_vectors; @@ -749,6 +753,14 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = { .mask = cpu_to_be32(0xffff0000), /* POWER8 */ .val = cpu_to_be32(0x004d0000), }, + { + .mask = cpu_to_be32(0xffff0000), /* POWER9 */ + .val = cpu_to_be32(0x004e0000), + }, + { + .mask = cpu_to_be32(0xffffffff), /* all 3.00-compliant */ + .val = cpu_to_be32(0x0f000005), + }, { .mask = cpu_to_be32(0xffffffff), /* all 2.07-compliant */ .val = cpu_to_be32(0x0f000004), @@ -774,6 +786,7 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = { .byte1 = 0, .arch_versions = OV1_PPC_2_00 | OV1_PPC_2_01 | OV1_PPC_2_02 | OV1_PPC_2_03 | OV1_PPC_2_04 | OV1_PPC_2_05 | OV1_PPC_2_06 | OV1_PPC_2_07, + .arch_versions3 = OV1_PPC_3_00, }, .vec2_len = VECTOR_LENGTH(sizeof(struct option_vector2)), @@ -836,6 +849,9 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = { .reserved2 = 0, .reserved3 = 0, .subprocessors = 1, + .intarch = 0, + .mmu = OV5_FEAT(OV5_MMU_RADIX_300) | OV5_FEAT(OV5_MMU_HASH_300) | + OV5_FEAT(OV5_MMU_PROC_TBL) | OV5_FEAT(OV5_MMU_GTSE), }, /* option vector 6: IBM PAPR hints */ diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 4d9481ec2468..10c9a545a646 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -347,10 +347,9 @@ static int __init parse_disable_radix(char *p) early_param("disable_radix", parse_disable_radix); /* - * If we're running under a hypervisor, we currently can't do radix - * since we don't have the code to do the H_REGISTER_PROC_TBL hcall. - * We tell that we're running under a hypervisor by looking for the - * /chosen/ibm,architecture-vec-5 property. + * If we're running under a hypervisor, we need to check the contents of + * /chosen/ibm,architecture-vec-5 to see if the hypervisor is willing to do + * radix. If not, we clear the radix feature bit so we fall back to hash. */ static void early_check_vec5(void) { @@ -365,7 +364,10 @@ static void early_check_vec5(void) vec5 = of_get_flat_dt_prop(chosen, "ibm,architecture-vec-5", &size); if (!vec5) return; - cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; + if (size <= OV5_INDX(OV5_MMU_RADIX_300) || + !(vec5[OV5_INDX(OV5_MMU_RADIX_300)] & OV5_FEAT(OV5_MMU_RADIX_300))) + /* Hypervisor doesn't support radix */ + cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; } void __init mmu_early_init_devtree(void) diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index cfa53ccc8baf..94323c4ececc 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -401,6 +401,8 @@ void __init radix__early_init_mmu(void) mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR); radix_init_partition_table(); radix_init_amor(); + } else { + radix_init_pseries(); } memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE); diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 5dc1c3c6e716..0587655aea69 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -609,6 +609,29 @@ static int __init disable_bulk_remove(char *str) __setup("bulk_remove=", disable_bulk_remove); +/* Actually only used for radix, so far */ +static int pseries_lpar_register_process_table(unsigned long base, + unsigned long page_size, unsigned long table_size) +{ + long rc; + unsigned long flags = PROC_TABLE_NEW; + + if (radix_enabled()) + flags |= PROC_TABLE_RADIX | PROC_TABLE_GTSE; + for (;;) { + rc = plpar_hcall_norets(H_REGISTER_PROC_TBL, flags, base, + page_size, table_size); + if (!H_IS_LONG_BUSY(rc)) + break; + mdelay(get_longbusy_msecs(rc)); + } + if (rc != H_SUCCESS) { + pr_err("Failed to register process table (rc=%ld)\n", rc); + BUG(); + } + return rc; +} + void __init hpte_init_pseries(void) { mmu_hash_ops.hpte_invalidate = pSeries_lpar_hpte_invalidate; @@ -622,6 +645,12 @@ void __init hpte_init_pseries(void) mmu_hash_ops.hugepage_invalidate = pSeries_lpar_hugepage_invalidate; } +void radix_init_pseries(void) +{ + pr_info("Using radix MMU under hypervisor\n"); + register_process_table = pseries_lpar_register_process_table; +} + #ifdef CONFIG_PPC_SMLPAR #define CMO_FREE_HINT_DEFAULT 1 static int cmo_free_hint_flag = CMO_FREE_HINT_DEFAULT; -- cgit v1.2.3