diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-05 11:36:44 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-05 11:36:44 -0700 |
| commit | 7246f60068840847bdcf595be5f0b5ca632736e0 (patch) | |
| tree | fd9a963a03c2655f3ba9d1ced3c87a2775f5b166 /arch/powerpc/include | |
| parent | e579dde654fc2c6b0d3e4b77a9a4b2d2405c510e (diff) | |
| parent | 700b7eadd5625d22b8235fb21259b3d7d564c000 (diff) | |
| download | op-kernel-dev-7246f60068840847bdcf595be5f0b5ca632736e0.zip op-kernel-dev-7246f60068840847bdcf595be5f0b5ca632736e0.tar.gz | |
Merge tag 'powerpc-4.12-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
"Highlights include:
- Larger virtual address space on 64-bit server CPUs. By default we
use a 128TB virtual address space, but a process can request access
to the full 512TB by passing a hint to mmap().
- Support for the new Power9 "XIVE" interrupt controller.
- TLB flushing optimisations for the radix MMU on Power9.
- Support for CAPI cards on Power9, using the "Coherent Accelerator
Interface Architecture 2.0".
- The ability to configure the mmap randomisation limits at build and
runtime.
- Several small fixes and cleanups to the kprobes code, as well as
support for KPROBES_ON_FTRACE.
- Major improvements to handling of system reset interrupts,
correctly treating them as NMIs, giving them a dedicated stack and
using a new hypervisor call to trigger them, all of which should
aid debugging and robustness.
- Many fixes and other minor enhancements.
Thanks to: Alastair D'Silva, Alexey Kardashevskiy, Alistair Popple,
Andrew Donnellan, Aneesh Kumar K.V, Anshuman Khandual, Anton
Blanchard, Balbir Singh, Ben Hutchings, Benjamin Herrenschmidt,
Bhupesh Sharma, Chris Packham, Christian Zigotzky, Christophe Leroy,
Christophe Lombard, Daniel Axtens, David Gibson, Gautham R. Shenoy,
Gavin Shan, Geert Uytterhoeven, Guilherme G. Piccoli, Hamish Martin,
Hari Bathini, Kees Cook, Laurent Dufour, Madhavan Srinivasan, Mahesh J
Salgaonkar, Mahesh Salgaonkar, Masami Hiramatsu, Matt Brown, Matthew
R. Ochs, Michael Neuling, Naveen N. Rao, Nicholas Piggin, Oliver
O'Halloran, Pan Xinhui, Paul Mackerras, Rashmica Gupta, Russell
Currey, Sukadev Bhattiprolu, Thadeu Lima de Souza Cascardo, Tobin C.
Harding, Tyrel Datwyler, Uma Krishnan, Vaibhav Jain, Vipin K Parashar,
Yang Shi"
* tag 'powerpc-4.12-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (214 commits)
powerpc/64s: Power9 has no LPCR[VRMASD] field so don't set it
powerpc/powernv: Fix TCE kill on NVLink2
powerpc/mm/radix: Drop support for CPUs without lockless tlbie
powerpc/book3s/mce: Move add_taint() later in virtual mode
powerpc/sysfs: Move #ifdef CONFIG_HOTPLUG_CPU out of the function body
powerpc/smp: Document irq enable/disable after migrating IRQs
powerpc/mpc52xx: Don't select user-visible RTAS_PROC
powerpc/powernv: Document cxl dependency on special case in pnv_eeh_reset()
powerpc/eeh: Clean up and document event handling functions
powerpc/eeh: Avoid use after free in eeh_handle_special_event()
cxl: Mask slice error interrupts after first occurrence
cxl: Route eeh events to all drivers in cxl_pci_error_detected()
cxl: Force context lock during EEH flow
powerpc/64: Allow CONFIG_RELOCATABLE if COMPILE_TEST
powerpc/xmon: Teach xmon oops about radix vectors
powerpc/mm/hash: Fix off-by-one in comment about kernel contexts ids
powerpc/pseries: Enable VFIO
powerpc/powernv: Fix iommu table size calculation hook for small tables
powerpc/powernv: Check kzalloc() return value in pnv_pci_table_alloc
powerpc: Add arch/powerpc/tools directory
...
Diffstat (limited to 'arch/powerpc/include')
49 files changed, 997 insertions, 456 deletions
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index f6c5264..7330150 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -17,6 +17,8 @@ #include <asm/checksum.h> #include <linux/uaccess.h> #include <asm/epapr_hcalls.h> +#include <asm/dcr.h> +#include <asm/mmu_context.h> #include <uapi/asm/ucontext.h> @@ -120,6 +122,8 @@ extern s64 __ashrdi3(s64, int); extern int __cmpdi2(s64, s64); extern int __ucmpdi2(u64, u64); +/* tracing */ void _mcount(void); +unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip); #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */ diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index bc5fdfd..33a24fd 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -55,6 +55,14 @@ #define PPC_BITEXTRACT(bits, ppc_bit, dst_bit) \ ((((bits) >> PPC_BITLSHIFT(ppc_bit)) & 1) << (dst_bit)) +#define PPC_BITLSHIFT32(be) (32 - 1 - (be)) +#define PPC_BIT32(bit) (1UL << PPC_BITLSHIFT32(bit)) +#define PPC_BITMASK32(bs, be) ((PPC_BIT32(bs) - PPC_BIT32(be))|PPC_BIT32(bs)) + +#define PPC_BITLSHIFT8(be) (8 - 1 - (be)) +#define PPC_BIT8(bit) (1UL << PPC_BITLSHIFT8(bit)) +#define PPC_BITMASK8(bs, be) ((PPC_BIT8(bs) - PPC_BIT8(be))|PPC_BIT8(bs)) + #include <asm/barrier.h> /* Macro for generating the ***_bits() functions */ diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 0c4e470..b4b5e6b 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 9 +#define H_PGD_INDEX_SIZE 12 #ifndef __ASSEMBLY__ #define H_PTE_TABLE_SIZE (sizeof(pte_t) << H_PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index f3dd21e..214219d 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -4,10 +4,14 @@ #define H_PTE_INDEX_SIZE 8 #define H_PMD_INDEX_SIZE 5 #define H_PUD_INDEX_SIZE 5 -#define H_PGD_INDEX_SIZE 12 +#define H_PGD_INDEX_SIZE 15 -#define H_PAGE_COMBO 0x00001000 /* this is a combo 4k page */ -#define H_PAGE_4K_PFN 0x00002000 /* PFN is for a single 4k page */ +/* + * 64k aligned address free up few of the lower bits of RPN for us + * We steal that here. For more deatils look at pte_pfn/pfn_pte() + */ +#define H_PAGE_COMBO _RPAGE_RPN0 /* this is a combo 4k page */ +#define H_PAGE_4K_PFN _RPAGE_RPN1 /* PFN is for a single 4k page */ /* * We need to differentiate between explicit huge page and THP huge * page, since THP huge page also need to track real subpage details diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index f7b721b..4e957b0 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -6,19 +6,13 @@ * Common bits between 4K and 64K pages in a linux-style PTE. * Additional bits may be defined in pgtable-hash64-*.h * - * Note: We only support user read/write permissions. Supervisor always - * have full read/write to pages above PAGE_OFFSET (pages below that - * always use the user access permissions). - * - * We could create separate kernel read-only if we used the 3 PP bits - * combinations that newer processors provide but we currently don't. */ -#define H_PAGE_BUSY 0x00800 /* software: PTE & hash are busy */ #define H_PTE_NONE_MASK _PAGE_HPTEFLAGS -#define H_PAGE_F_GIX_SHIFT 57 -#define H_PAGE_F_GIX (7ul << 57) /* HPTE index within HPTEG */ -#define H_PAGE_F_SECOND (1ul << 60) /* HPTE is in 2ndary HPTEG */ -#define H_PAGE_HASHPTE (1ul << 61) /* PTE has associated HPTE */ +#define H_PAGE_F_GIX_SHIFT 56 +#define H_PAGE_BUSY _RPAGE_RSV1 /* software: PTE & hash are busy */ +#define H_PAGE_F_SECOND _RPAGE_RSV2 /* HPTE is in 2ndary HPTEG */ +#define H_PAGE_F_GIX (_RPAGE_RSV3 | _RPAGE_RSV4 | _RPAGE_RPN44) +#define H_PAGE_HASHPTE _RPAGE_RPN43 /* PTE has associated HPTE */ #ifdef CONFIG_PPC_64K_PAGES #include <asm/book3s/64/hash-64k.h> diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h index c62f14d..6666cd3 100644 --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h @@ -46,7 +46,7 @@ static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, */ VM_WARN_ON(page_shift == mmu_psize_defs[MMU_PAGE_1G].shift); if (page_shift == mmu_psize_defs[MMU_PAGE_2M].shift) - return __pte(pte_val(entry) | _PAGE_LARGE); + return __pte(pte_val(entry) | R_PAGE_LARGE); else return entry; } diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 52d8d1e..6981a52 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -39,6 +39,7 @@ /* Bits in the SLB VSID word */ #define SLB_VSID_SHIFT 12 +#define SLB_VSID_SHIFT_256M SLB_VSID_SHIFT #define SLB_VSID_SHIFT_1T 24 #define SLB_VSID_SSIZE_SHIFT 62 #define SLB_VSID_B ASM_CONST(0xc000000000000000) @@ -408,7 +409,7 @@ static inline unsigned long hpt_vpn(unsigned long ea, static inline unsigned long hpt_hash(unsigned long vpn, unsigned int shift, int ssize) { - int mask; + unsigned long mask; unsigned long hash, vsid; /* VPN_SHIFT can be atmost 12 */ @@ -491,13 +492,14 @@ extern void slb_set_size(u16 size); * We first generate a 37-bit "proto-VSID". Proto-VSIDs are generated * from mmu context id and effective segment id of the address. * - * For user processes max context id is limited to ((1ul << 19) - 5) - * for kernel space, we use the top 4 context ids to map address as below + * For user processes max context id is limited to MAX_USER_CONTEXT. + + * For kernel space, we use context ids 1-4 to map addresses as below: * NOTE: each context only support 64TB now. - * 0x7fffc - [ 0xc000000000000000 - 0xc0003fffffffffff ] - * 0x7fffd - [ 0xd000000000000000 - 0xd0003fffffffffff ] - * 0x7fffe - [ 0xe000000000000000 - 0xe0003fffffffffff ] - * 0x7ffff - [ 0xf000000000000000 - 0xf0003fffffffffff ] + * 0x00001 - [ 0xc000000000000000 - 0xc0003fffffffffff ] + * 0x00002 - [ 0xd000000000000000 - 0xd0003fffffffffff ] + * 0x00003 - [ 0xe000000000000000 - 0xe0003fffffffffff ] + * 0x00004 - [ 0xf000000000000000 - 0xf0003fffffffffff ] * * The proto-VSIDs are then scrambled into real VSIDs with the * multiplicative hash: @@ -511,20 +513,28 @@ extern void slb_set_size(u16 size); * robust scattering in the hash table (at least based on some initial * results). * - * We also consider VSID 0 special. We use VSID 0 for slb entries mapping - * bad address. This enables us to consolidate bad address handling in - * hash_page. + * We use VSID 0 to indicate an invalid VSID. The means we can't use context id + * 0, because a context id of 0 and an EA of 0 gives a proto-VSID of 0, which + * will produce a VSID of 0. * * We also need to avoid the last segment of the last context, because that * would give a protovsid of 0x1fffffffff. That will result in a VSID 0 - * because of the modulo operation in vsid scramble. But the vmemmap - * (which is what uses region 0xf) will never be close to 64TB in size - * (it's 56 bytes per page of system memory). + * because of the modulo operation in vsid scramble. */ +/* + * Max Va bits we support as of now is 68 bits. We want 19 bit + * context ID. + * Restrictions: + * GPU has restrictions of not able to access beyond 128TB + * (47 bit effective address). We also cannot do more than 20bit PID. + * For p4 and p5 which can only do 65 bit VA, we restrict our CONTEXT_BITS + * to 16 bits (ie, we can only have 2^16 pids at the same time). + */ +#define VA_BITS 68 #define CONTEXT_BITS 19 -#define ESID_BITS 18 -#define ESID_BITS_1T 6 +#define ESID_BITS (VA_BITS - (SID_SHIFT + CONTEXT_BITS)) +#define ESID_BITS_1T (VA_BITS - (SID_SHIFT_1T + CONTEXT_BITS)) #define ESID_BITS_MASK ((1 << ESID_BITS) - 1) #define ESID_BITS_1T_MASK ((1 << ESID_BITS_1T) - 1) @@ -532,63 +542,70 @@ extern void slb_set_size(u16 size); /* * 256MB segment * The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments - * available for user + kernel mapping. The top 4 contexts are used for - * kernel mapping. Each segment contains 2^28 bytes. Each - * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts - * (19 == 37 + 28 - 46). + * available for user + kernel mapping. VSID 0 is reserved as invalid, contexts + * 1-4 are used for kernel mapping. Each segment contains 2^28 bytes. Each + * context maps 2^49 bytes (512TB). + * + * We also need to avoid the last segment of the last context, because that + * would give a protovsid of 0x1fffffffff. That will result in a VSID 0 + * because of the modulo operation in vsid scramble. + */ +#define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 2) +#define MIN_USER_CONTEXT (5) + +/* Would be nice to use KERNEL_REGION_ID here */ +#define KERNEL_REGION_CONTEXT_OFFSET (0xc - 1) + +/* + * For platforms that support on 65bit VA we limit the context bits */ -#define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 5) +#define MAX_USER_CONTEXT_65BIT_VA ((ASM_CONST(1) << (65 - (SID_SHIFT + ESID_BITS))) - 2) /* * This should be computed such that protovosid * vsid_mulitplier - * doesn't overflow 64 bits. It should also be co-prime to vsid_modulus + * doesn't overflow 64 bits. The vsid_mutliplier should also be + * co-prime to vsid_modulus. We also need to make sure that number + * of bits in multiplied result (dividend) is less than twice the number of + * protovsid bits for our modulus optmization to work. + * + * The below table shows the current values used. + * |-------+------------+----------------------+------------+-------------------| + * | | Prime Bits | proto VSID_BITS_65VA | Total Bits | 2* prot VSID_BITS | + * |-------+------------+----------------------+------------+-------------------| + * | 1T | 24 | 25 | 49 | 50 | + * |-------+------------+----------------------+------------+-------------------| + * | 256MB | 24 | 37 | 61 | 74 | + * |-------+------------+----------------------+------------+-------------------| + * + * |-------+------------+----------------------+------------+--------------------| + * | | Prime Bits | proto VSID_BITS_68VA | Total Bits | 2* proto VSID_BITS | + * |-------+------------+----------------------+------------+--------------------| + * | 1T | 24 | 28 | 52 | 56 | + * |-------+------------+----------------------+------------+--------------------| + * | 256MB | 24 | 40 | 64 | 80 | + * |-------+------------+----------------------+------------+--------------------| + * */ #define VSID_MULTIPLIER_256M ASM_CONST(12538073) /* 24-bit prime */ -#define VSID_BITS_256M (CONTEXT_BITS + ESID_BITS) -#define VSID_MODULUS_256M ((1UL<<VSID_BITS_256M)-1) +#define VSID_BITS_256M (VA_BITS - SID_SHIFT) +#define VSID_BITS_65_256M (65 - SID_SHIFT) +/* + * Modular multiplicative inverse of VSID_MULTIPLIER under modulo VSID_MODULUS + */ +#define VSID_MULINV_256M ASM_CONST(665548017062) #define VSID_MULTIPLIER_1T ASM_CONST(12538073) /* 24-bit prime */ -#define VSID_BITS_1T (CONTEXT_BITS + ESID_BITS_1T) -#define VSID_MODULUS_1T ((1UL<<VSID_BITS_1T)-1) - +#define VSID_BITS_1T (VA_BITS - SID_SHIFT_1T) +#define VSID_BITS_65_1T (65 - SID_SHIFT_1T) +#define VSID_MULINV_1T ASM_CONST(209034062) +/* 1TB VSID reserved for VRMA */ +#define VRMA_VSID 0x1ffffffUL #define USER_VSID_RANGE (1UL << (ESID_BITS + SID_SHIFT)) -/* - * This macro generates asm code to compute the VSID scramble - * function. Used in slb_allocate() and do_stab_bolted. The function - * computed is: (protovsid*VSID_MULTIPLIER) % VSID_MODULUS - * - * rt = register containing the proto-VSID and into which the - * VSID will be stored - * rx = scratch register (clobbered) - * - * - rt and rx must be different registers - * - The answer will end up in the low VSID_BITS bits of rt. The higher - * bits may contain other garbage, so you may need to mask the - * result. - */ -#define ASM_VSID_SCRAMBLE(rt, rx, size) \ - lis rx,VSID_MULTIPLIER_##size@h; \ - ori rx,rx,VSID_MULTIPLIER_##size@l; \ - mulld rt,rt,rx; /* rt = rt * MULTIPLIER */ \ - \ - srdi rx,rt,VSID_BITS_##size; \ - clrldi rt,rt,(64-VSID_BITS_##size); \ - add rt,rt,rx; /* add high and low bits */ \ - /* NOTE: explanation based on VSID_BITS_##size = 36 \ - * Now, r3 == VSID (mod 2^36-1), and lies between 0 and \ - * 2^36-1+2^28-1. That in particular means that if r3 >= \ - * 2^36-1, then r3+1 has the 2^36 bit set. So, if r3+1 has \ - * the bit clear, r3 already has the answer we want, if it \ - * doesn't, the answer is the low 36 bits of r3+1. So in all \ - * cases the answer is the low 36 bits of (r3 + ((r3+1) >> 36))*/\ - addi rx,rt,1; \ - srdi rx,rx,VSID_BITS_##size; /* extract 2^VSID_BITS bit */ \ - add rt,rt,rx - /* 4 bits per slice and we have one slice per 1TB */ -#define SLICE_ARRAY_SIZE (H_PGTABLE_RANGE >> 41) +#define SLICE_ARRAY_SIZE (H_PGTABLE_RANGE >> 41) +#define TASK_SLICE_ARRAY_SZ(x) ((x)->context.addr_limit >> 41) #ifndef __ASSEMBLY__ @@ -634,7 +651,7 @@ static inline void subpage_prot_init_new_context(struct mm_struct *mm) { } #define vsid_scramble(protovsid, size) \ ((((protovsid) * VSID_MULTIPLIER_##size) % VSID_MODULUS_##size)) -#else /* 1 */ +/* simplified form avoiding mod operation */ #define vsid_scramble(protovsid, size) \ ({ \ unsigned long x; \ @@ -642,6 +659,21 @@ static inline void subpage_prot_init_new_context(struct mm_struct *mm) { } x = (x >> VSID_BITS_##size) + (x & VSID_MODULUS_##size); \ (x + ((x+1) >> VSID_BITS_##size)) & VSID_MODULUS_##size; \ }) + +#else /* 1 */ +static inline unsigned long vsid_scramble(unsigned long protovsid, + unsigned long vsid_multiplier, int vsid_bits) +{ + unsigned long vsid; + unsigned long vsid_modulus = ((1UL << vsid_bits) - 1); + /* + * We have same multipler for both 256 and 1T segements now + */ + vsid = protovsid * vsid_multiplier; + vsid = (vsid >> vsid_bits) + (vsid & vsid_modulus); + return (vsid + ((vsid + 1) >> vsid_bits)) & vsid_modulus; +} + #endif /* 1 */ /* Returns the segment size indicator for a user address */ @@ -656,36 +688,56 @@ static inline int user_segment_size(unsigned long addr) static inline unsigned long get_vsid(unsigned long context, unsigned long ea, int ssize) { + unsigned long va_bits = VA_BITS; + unsigned long vsid_bits; + unsigned long protovsid; + /* * Bad address. We return VSID 0 for that */ if ((ea & ~REGION_MASK) >= H_PGTABLE_RANGE) return 0; - if (ssize == MMU_SEGSIZE_256M) - return vsid_scramble((context << ESID_BITS) - | ((ea >> SID_SHIFT) & ESID_BITS_MASK), 256M); - return vsid_scramble((context << ESID_BITS_1T) - | ((ea >> SID_SHIFT_1T) & ESID_BITS_1T_MASK), 1T); + if (!mmu_has_feature(MMU_FTR_68_BIT_VA)) + va_bits = 65; + + if (ssize == MMU_SEGSIZE_256M) { + vsid_bits = va_bits - SID_SHIFT; + protovsid = (context << ESID_BITS) | + ((ea >> SID_SHIFT) & ESID_BITS_MASK); + return vsid_scramble(protovsid, VSID_MULTIPLIER_256M, vsid_bits); + } + /* 1T segment */ + vsid_bits = va_bits - SID_SHIFT_1T; + protovsid = (context << ESID_BITS_1T) | + ((ea >> SID_SHIFT_1T) & ESID_BITS_1T_MASK); + return vsid_scramble(protovsid, VSID_MULTIPLIER_1T, vsid_bits); } /* * This is only valid for addresses >= PAGE_OFFSET - * - * For kernel space, we use the top 4 context ids to map address as below - * 0x7fffc - [ 0xc000000000000000 - 0xc0003fffffffffff ] - * 0x7fffd - [ 0xd000000000000000 - 0xd0003fffffffffff ] - * 0x7fffe - [ 0xe000000000000000 - 0xe0003fffffffffff ] - * 0x7ffff - [ 0xf000000000000000 - 0xf0003fffffffffff ] */ static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize) { unsigned long context; + if (!is_kernel_addr(ea)) + return 0; + /* - * kernel take the top 4 context from the available range + * For kernel space, we use context ids 1-4 to map the address space as + * below: + * + * 0x00001 - [ 0xc000000000000000 - 0xc0003fffffffffff ] + * 0x00002 - [ 0xd000000000000000 - 0xd0003fffffffffff ] + * 0x00003 - [ 0xe000000000000000 - 0xe0003fffffffffff ] + * 0x00004 - [ 0xf000000000000000 - 0xf0003fffffffffff ] + * + * So we can compute the context from the region (top nibble) by + * subtracting 11, or 0xc - 1. */ - context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1; + context = (ea >> 60) - KERNEL_REGION_CONTEXT_OFFSET; + return get_vsid(context, ea, ssize); } diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index 805d4105..77529a3 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -65,6 +65,8 @@ extern struct patb_entry *partition_tb; * MAX_USER_CONTEXT * 16 bytes of space. */ #define PRTB_SIZE_SHIFT (CONTEXT_BITS + 4) +#define PRTB_ENTRIES (1ul << CONTEXT_BITS) + /* * Power9 currently only support 64K partition table size. */ @@ -73,13 +75,20 @@ extern struct patb_entry *partition_tb; typedef unsigned long mm_context_id_t; struct spinlock; +/* Maximum possible number of NPUs in a system. */ +#define NV_MAX_NPUS 8 + typedef struct { mm_context_id_t id; u16 user_psize; /* page size index */ + /* NPU NMMU context */ + struct npu_context *npu_context; + #ifdef CONFIG_PPC_MM_SLICES u64 low_slices_psize; /* SLB page size encodings */ unsigned char high_slices_psize[SLICE_ARRAY_SIZE]; + unsigned long addr_limit; #else u16 sllp; /* SLB page size encoding */ #endif diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 8f4d419..85bc987 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -13,6 +13,7 @@ #define _PAGE_BIT_SWAP_TYPE 0 #define _PAGE_RO 0 +#define _PAGE_SHARED 0 #define _PAGE_EXEC 0x00001 /* execute permission */ #define _PAGE_WRITE 0x00002 /* write access allowed */ @@ -37,21 +38,47 @@ #define _RPAGE_RSV3 0x0400000000000000UL #define _RPAGE_RSV4 0x0200000000000000UL -#ifdef CONFIG_MEM_SOFT_DIRTY -#define _PAGE_SOFT_DIRTY _RPAGE_SW3 /* software: software dirty tracking */ -#else -#define _PAGE_SOFT_DIRTY 0x00000 -#endif -#define _PAGE_SPECIAL _RPAGE_SW2 /* software: special page */ +#define _PAGE_PTE 0x4000000000000000UL /* distinguishes PTEs from pointers */ +#define _PAGE_PRESENT 0x8000000000000000UL /* pte contains a translation */ /* - * For P9 DD1 only, we need to track whether the pte's huge. + * Top and bottom bits of RPN which can be used by hash + * translation mode, because we expect them to be zero + * otherwise. */ -#define _PAGE_LARGE _RPAGE_RSV1 +#define _RPAGE_RPN0 0x01000 +#define _RPAGE_RPN1 0x02000 +#define _RPAGE_RPN44 0x0100000000000000UL +#define _RPAGE_RPN43 0x0080000000000000UL +#define _RPAGE_RPN42 0x0040000000000000UL +#define _RPAGE_RPN41 0x0020000000000000UL + +/* Max physical address bit as per radix table */ +#define _RPAGE_PA_MAX 57 +/* + * Max physical address bit we will use for now. + * + * This is mostly a hardware limitation and for now Power9 has + * a 51 bit limit. + * + * This is different from the number of physical bit required to address + * the last byte of memory. That is defined by MAX_PHYSMEM_BITS. + * MAX_PHYSMEM_BITS is a linux limitation imposed by the maximum + * number of sections we can support (SECTIONS_SHIFT). + * + * This is different from Radix page table limitation above and + * should always be less than that. The limit is done such that + * we can overload the bits between _RPAGE_PA_MAX and _PAGE_PA_MAX + * for hash linux page table specific bits. + * + * In order to be compatible with future hardware generations we keep + * some offsets and limit this for now to 53 + */ +#define _PAGE_PA_MAX 53 -#define _PAGE_PTE (1ul << 62) /* distinguishes PTEs from pointers */ -#define _PAGE_PRESENT (1ul << 63) /* pte contains a translation */ +#define _PAGE_SOFT_DIRTY _RPAGE_SW3 /* software: software dirty tracking */ +#define _PAGE_SPECIAL _RPAGE_SW2 /* software: special page */ /* * Drivers request for cache inhibited pte mapping using _PAGE_NO_CACHE * Instead of fixing all of them, add an alternate define which @@ -59,10 +86,11 @@ */ #define _PAGE_NO_CACHE _PAGE_TOLERANT /* - * We support 57 bit real address in pte. Clear everything above 57, and - * every thing below PAGE_SHIFT; + * We support _RPAGE_PA_MAX bit real address in pte. On the linux side + * we are limited by _PAGE_PA_MAX. Clear everything above _PAGE_PA_MAX + * and every thing below PAGE_SHIFT; */ -#define PTE_RPN_MASK (((1UL << 57) - 1) & (PAGE_MASK)) +#define PTE_RPN_MASK (((1UL << _PAGE_PA_MAX) - 1) & (PAGE_MASK)) /* * set of bits not changed in pmd_modify. Even though we have hash specific bits * in here, on radix we expect them to be zero. @@ -205,10 +233,6 @@ extern unsigned long __pte_frag_nr; extern unsigned long __pte_frag_size_shift; #define PTE_FRAG_SIZE_SHIFT __pte_frag_size_shift #define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT) -/* - * Pgtable size used by swapper, init in asm code - */ -#define MAX_PGD_TABLE_SIZE (sizeof(pgd_t) << RADIX_PGD_INDEX_SIZE) #define PTRS_PER_PTE (1 << PTE_INDEX_SIZE) #define PTRS_PER_PMD (1 << PMD_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 9e0bb7c..ac16d19 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -11,6 +11,12 @@ #include <asm/book3s/64/radix-4k.h> #endif +/* + * For P9 DD1 only, we need to track whether the pte's huge. + */ +#define R_PAGE_LARGE _RPAGE_RSV1 + + #ifndef __ASSEMBLY__ #include <asm/book3s/64/tlbflush-radix.h> #include <asm/cpu_has_feature.h> @@ -252,7 +258,7 @@ static inline int radix__pmd_trans_huge(pmd_t pmd) static inline pmd_t radix__pmd_mkhuge(pmd_t pmd) { if (cpu_has_feature(CPU_FTR_POWER9_DD1)) - return __pmd(pmd_val(pmd) | _PAGE_PTE | _PAGE_LARGE); + return __pmd(pmd_val(pmd) | _PAGE_PTE | R_PAGE_LARGE); return __pmd(pmd_val(pmd) | _PAGE_PTE); } static inline void radix__pmdp_huge_split_prepare(struct vm_area_struct *vma, diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index 8ab9377..abef812 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -12,6 +12,8 @@ #include <asm/types.h> #include <asm/ppc-opcode.h> +#include <linux/string.h> +#include <linux/kallsyms.h> /* Flags for create_branch: * "b" == create_branch(addr, target, 0); @@ -99,6 +101,45 @@ static inline unsigned long ppc_global_function_entry(void *func) #endif } +/* + * Wrapper around kallsyms_lookup() to return function entry address: + * - For ABIv1, we lookup the dot variant. + * - For ABIv2, we return the local entry point. + */ +static inline unsigned long ppc_kallsyms_lookup_name(const char *name) +{ + unsigned long addr; +#ifdef PPC64_ELF_ABI_v1 + /* check for dot variant */ + char dot_name[1 + KSYM_NAME_LEN]; + bool dot_appended = false; + + if (strnlen(name, KSYM_NAME_LEN) >= KSYM_NAME_LEN) + return 0; + + if (name[0] != '.') { + dot_name[0] = '.'; + dot_name[1] = '\0'; + strlcat(dot_name, name, sizeof(dot_name)); + dot_appended = true; + } else { + dot_name[0] = '\0'; + strlcat(dot_name, name, sizeof(dot_name)); + } + addr = kallsyms_lookup_name(dot_name); + if (!addr && dot_appended) + /* Let's try the original non-dot symbol lookup */ + addr = kallsyms_lookup_name(name); +#elif defined(PPC64_ELF_ABI_v2) + addr = kallsyms_lookup_name(name); + if (addr) + addr = ppc_function_entry((void *)addr); +#else + addr = kallsyms_lookup_name(name); +#endif + return addr; +} + #ifdef CONFIG_PPC64 /* * Some instruction encodings commonly used in dynamic ftracing diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h index 1557315..52586f9 100644 --- a/arch/powerpc/include/asm/cpuidle.h +++ b/arch/powerpc/include/asm/cpuidle.h @@ -2,13 +2,39 @@ #define _ASM_POWERPC_CPUIDLE_H #ifdef CONFIG_PPC_POWERNV -/* Used in powernv idle state management */ +/* Thread state used in powernv idle state management */ #define PNV_THREAD_RUNNING 0 #define PNV_THREAD_NAP 1 #define PNV_THREAD_SLEEP 2 #define PNV_THREAD_WINKLE 3 -#define PNV_CORE_IDLE_LOCK_BIT 0x100 -#define PNV_CORE_IDLE_THREAD_BITS 0x0FF + +/* + * Core state used in powernv idle for POWER8. + * + * The lock bit synchronizes updates to the state, as well as parts of the + * sleep/wake code (see kernel/idle_book3s.S). + * + * Bottom 8 bits track the idle state of each thread. Bit is cleared before + * the thread executes an idle instruction (nap/sleep/winkle). + * + * Then there is winkle tracking. A core does not lose complete state + * until every thread is in winkle. So the winkle count field counts the + * number of threads in winkle (small window of false positives is okay + * around the sleep/wake, so long as there are no false negatives). + * + * When the winkle count reaches 8 (the COUNT_ALL_BIT becomes set), then + * the THREAD_WINKLE_BITS are set, which indicate which threads have not + * yet woken from the winkle state. + */ +#define PNV_CORE_IDLE_LOCK_BIT 0x10000000 + +#define PNV_CORE_IDLE_WINKLE_COUNT 0x00010000 +#define PNV_CORE_IDLE_WINKLE_COUNT_ALL_BIT 0x00080000 +#define PNV_CORE_IDLE_WINKLE_COUNT_BITS 0x000F0000 +#define PNV_CORE_IDLE_THREAD_WINKLE_BITS_SHIFT 8 +#define PNV_CORE_IDLE_THREAD_WINKLE_BITS 0x0000FF00 + +#define PNV_CORE_IDLE_THREAD_BITS 0x000000FF /* * ============================ NOTE ================================= @@ -46,6 +72,7 @@ extern u32 pnv_fastsleep_workaround_at_exit[]; extern u64 pnv_first_deep_stop_state; +unsigned long pnv_cpu_offline(unsigned int cpu); int validate_psscr_val_mask(u64 *psscr_val, u64 *psscr_mask, u32 flags); static inline void report_invalid_psscr_val(u64 psscr_val, int err) { diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index ab68d0e..1f6847b 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -471,10 +471,11 @@ enum { CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ CPU_FTR_DSCR | CPU_FTR_SAO | \ 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_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_ARCH_300) -#define CPU_FTRS_POWER9_DD1 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1) +#define CPU_FTRS_POWER9_DD1 ((CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1) & \ + (~CPU_FTR_SAO)) #define CPU_FTRS_CELL (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \ diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h index 3781673..f70cbfe 100644 --- a/arch/powerpc/include/asm/dbell.h +++ b/arch/powerpc/include/asm/dbell.h @@ -35,33 +35,53 @@ enum ppc_dbell { #ifdef CONFIG_PPC_BOOK3S #define PPC_DBELL_MSGTYPE PPC_DBELL_SERVER -#define SPRN_DOORBELL_CPUTAG SPRN_TIR -#define PPC_DBELL_TAG_MASK 0x7f static inline void _ppc_msgsnd(u32 msg) { - if (cpu_has_feature(CPU_FTR_HVMODE)) - __asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg)); - else - __asm__ __volatile__ (PPC_MSGSNDP(%0) : : "r" (msg)); + __asm__ __volatile__ (ASM_FTR_IFSET(PPC_MSGSND(%1), PPC_MSGSNDP(%1), %0) + : : "i" (CPU_FTR_HVMODE), "r" (msg)); +} + +/* sync before sending message */ +static inline void ppc_msgsnd_sync(void) +{ + __asm__ __volatile__ ("sync" : : : "memory"); +} + +/* sync after taking message interrupt */ +static inline void ppc_msgsync(void) +{ + /* sync is not required when taking messages from the same core */ + __asm__ __volatile__ (ASM_FTR_IFSET(PPC_MSGSYNC " ; lwsync", "", %0) + : : "i" (CPU_FTR_HVMODE|CPU_FTR_ARCH_300)); } #else /* CONFIG_PPC_BOOK3S */ #define PPC_DBELL_MSGTYPE PPC_DBELL -#define SPRN_DOORBELL_CPUTAG SPRN_PIR -#define PPC_DBELL_TAG_MASK 0x3fff static inline void _ppc_msgsnd(u32 msg) { __asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg)); } +/* sync before sending message */ +static inline void ppc_msgsnd_sync(void) +{ + __asm__ __volatile__ ("sync" : : : "memory"); +} + +/* sync after taking message interrupt */ +static inline void ppc_msgsync(void) +{ +} + #endif /* CONFIG_PPC_BOOK3S */ -extern void doorbell_cause_ipi(int cpu, unsigned long data); +extern void doorbell_global_ipi(int cpu); +extern void doorbell_core_ipi(int cpu); +extern int doorbell_try_core_ipi(int cpu); extern void doorbell_exception(struct pt_regs *regs); -extern void doorbell_setup_this_cpu(void); static inline void ppc_msgsnd(enum ppc_dbell type, u32 flags, u32 tag) { diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h index 86308f1..5d5af3f 100644 --- a/arch/powerpc/include/asm/debug.h +++ b/arch/powerpc/include/asm/debug.h @@ -8,8 +8,6 @@ struct pt_regs; -extern struct dentry *powerpc_debugfs_root; - #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE) extern int (*__debugger)(struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/debugfs.h b/arch/powerpc/include/asm/debugfs.h new file mode 100644 index 0000000..4f3b39f --- /dev/null +++ b/arch/powerpc/include/asm/debugfs.h @@ -0,0 +1,17 @@ +#ifndef _ASM_POWERPC_DEBUGFS_H +#define _ASM_POWERPC_DEBUGFS_H + +/* + * Copyright 2017, Michael Ellerman, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/debugfs.h> + +extern struct dentry *powerpc_debugfs_root; + +#endif /* _ASM_POWERPC_DEBUGFS_H */ diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index ed3bead..183d73b 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -167,17 +167,14 @@ BEGIN_FTR_SECTION_NESTED(943) \ std ra,offset(r13); \ END_FTR_SECTION_NESTED(ftr,ftr,943) -#define EXCEPTION_PROLOG_0_PACA(area) \ +#define EXCEPTION_PROLOG_0(area) \ + GET_PACA(r13); \ std r9,area+EX_R9(r13); /* save r9 */ \ OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR); \ HMT_MEDIUM; \ std r10,area+EX_R10(r13); /* save r10 - r12 */ \ OPT_GET_SPR(r10, SPRN_CFAR, CPU_FTR_CFAR) -#define EXCEPTION_PROLOG_0(area) \ - GET_PACA(r13); \ - EXCEPTION_PROLOG_0_PACA(area) - #define __EXCEPTION_PROLOG_1(area, extra, vec) \ OPT_SAVE_REG_TO_PACA(area+EX_PPR, r9, CPU_FTR_HAS_PPR); \ OPT_SAVE_REG_TO_PACA(area+EX_CFAR, r10, CPU_FTR_CFAR); \ @@ -203,17 +200,26 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) #define EXCEPTION_PROLOG_PSERIES_1(label, h) \ __EXCEPTION_PROLOG_PSERIES_1(label, h) +/* _NORI variant keeps MSR_RI clear */ +#define __EXCEPTION_PROLOG_PSERIES_1_NORI(label, h) \ + ld r10,PACAKMSR(r13); /* get MSR value for kernel */ \ + xori r10,r10,MSR_RI; /* Clear MSR_RI */ \ + mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \ + LOAD_HANDLER(r12,label) \ + mtspr SPRN_##h##SRR0,r12; \ + mfspr r12,SPRN_##h##SRR1; /* and SRR1 */ \ + mtspr SPRN_##h##SRR1,r10; \ + h##rfid; \ + b . /* prevent speculative execution */ + +#define EXCEPTION_PROLOG_PSERIES_1_NORI(label, h) \ + __EXCEPTION_PROLOG_PSERIES_1_NORI(label, h) + #define EXCEPTION_PROLOG_PSERIES(area, label, h, extra, vec) \ EXCEPTION_PROLOG_0(area); \ EXCEPTION_PROLOG_1(area, extra, vec); \ EXCEPTION_PROLOG_PSERIES_1(label, h); -/* Have the PACA in r13 already */ -#define EXCEPTION_PROLOG_PSERIES_PACA(area, label, h, extra, vec) \ - EXCEPTION_PROLOG_0_PACA(area); \ - EXCEPTION_PROLOG_1(area, extra, vec); \ - EXCEPTION_PROLOG_PSERIES_1(label, h); - #define __KVMTEST(h, n) \ lbz r10,HSTATE_IN_GUEST(r13); \ cmpwi r10,0; \ @@ -256,11 +262,6 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) ld r9,area+EX_R9(r13); \ bctr -#define BRANCH_TO_KVM(reg, label) \ - __LOAD_FAR_HANDLER(reg, label); \ - mtctr reg; \ - bctr - #else #define BRANCH_TO_COMMON(reg, label) \ b label @@ -268,15 +269,18 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) #define BRANCH_LINK_TO_FAR(label) \ bl label -#define BRANCH_TO_KVM(reg, label) \ - b label - #define __BRANCH_TO_KVM_EXIT(area, label) \ ld r9,area+EX_R9(r13); \ b label #endif +/* Do not enable RI */ +#define EXCEPTION_PROLOG_PSERIES_NORI(area, label, h, extra, vec) \ + EXCEPTION_PROLOG_0(area); \ + EXCEPTION_PROLOG_1(area, extra, vec); \ + EXCEPTION_PROLOG_PSERIES_1_NORI(label, h); + #define __KVM_HANDLER(area, h, n) \ BEGIN_FTR_SECTION_NESTED(947) \ @@ -325,6 +329,15 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) #define NOTEST(n) +#define EXCEPTION_PROLOG_COMMON_1() \ + std r9,_CCR(r1); /* save CR in stackframe */ \ + std r11,_NIP(r1); /* save SRR0 in stackframe */ \ + std r12,_MSR(r1); /* save SRR1 in stackframe */ \ + std r10,0(r1); /* make stack chain pointer */ \ + std r0,GPR0(r1); /* save r0 in stackframe */ \ + std r10,GPR1(r1); /* save r1 in stackframe */ \ + + /* * The common exception prolog is used for all except a few exceptions * such as a segment miss on a kernel address. We have to be prepared @@ -349,12 +362,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) addi r3,r13,area; /* r3 -> where regs are saved*/ \ RESTORE_CTR(r1, area); \ b bad_stack; \ -3: std r9,_CCR(r1); /* save CR in stackframe */ \ - std r11,_NIP(r1); /* save SRR0 in stackframe */ \ - std r12,_MSR(r1); /* save SRR1 in stackframe */ \ - std r10,0(r1); /* make stack chain pointer */ \ - std r0,GPR0(r1); /* save r0 in stackframe */ \ - std r10,GPR1(r1); /* save r1 in stackframe */ \ +3: EXCEPTION_PROLOG_COMMON_1(); \ beq 4f; /* if from kernel mode */ \ ACCOUNT_CPU_USER_ENTRY(r13, r9, r10); \ SAVE_PPR(area, r9, r10); \ @@ -522,7 +530,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) #define MASKABLE_RELON_EXCEPTION_HV_OOL(vec, label) \ EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec); \ - EXCEPTION_PROLOG_PSERIES_1(label, EXC_HV) + EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_HV) /* * Our exception common code can be passed various "additions" @@ -547,26 +555,39 @@ BEGIN_FTR_SECTION \ beql ppc64_runlatch_on_trampoline; \ END_FTR_SECTION_IFSET(CPU_FTR_CTRL) -#define EXCEPTION_COMMON(trap, label, hdlr, ret, additions) \ - EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN); \ +#define EXCEPTION_COMMON(area, trap, label, hdlr, ret, additions) \ + EXCEPTION_PROLOG_COMMON(trap, area); \ /* Volatile regs are potentially clobbered here */ \ additions; \ addi r3,r1,STACK_FRAME_OVERHEAD; \ bl hdlr; \ b ret +/* + * Exception where stack is already set in r1, r1 is saved in r10, and it + * continues rather than returns. + */ +#define EXCEPTION_COMMON_NORET_STACK(area, trap, label, hdlr, additions) \ + EXCEPTION_PROLOG_COMMON_1(); \ + EXCEPTION_PROLOG_COMMON_2(area); \ + EXCEPTION_PROLOG_COMMON_3(trap); \ + /* Volatile regs are potentially clobbered here */ \ + additions; \ + addi r3,r1,STACK_FRAME_OVERHEAD; \ + bl hdlr + #define STD_EXCEPTION_COMMON(trap, label, hdlr) \ - EXCEPTION_COMMON(trap, label, hdlr, ret_from_except, \ - ADD_NVGPRS;ADD_RECONCILE) + EXCEPTION_COMMON(PACA_EXGEN, trap, label, hdlr, \ + ret_from_except, ADD_NVGPRS;ADD_RECONCILE) /* * Like STD_EXCEPTION_COMMON, but for exceptions that can occur * in the idle task and therefore need the special idle handling * (finish nap and runlatch) */ -#define STD_EXCEPTION_COMMON_ASYNC(trap, label, hdlr) \ - EXCEPTION_COMMON(trap, label, hdlr, ret_from_except_lite, \ - FINISH_NAP;ADD_RECONCILE;RUNLATCH_ON) +#define STD_EXCEPTION_COMMON_ASYNC(trap, label, hdlr) \ + EXCEPTION_COMMON(PACA_EXGEN, trap, label, hdlr, \ + ret_from_except_lite, FINISH_NAP;ADD_RECONCILE;RUNLATCH_ON) /* * When the idle code in power4_idle puts the CPU into NAP mode, diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index ddf54f5..2de2319 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -66,6 +66,9 @@ label##5: \ #define END_FTR_SECTION(msk, val) \ END_FTR_SECTION_NESTED(msk, val, 97) +#define END_FTR_SECTION_NESTED_IFSET(msk, label) \ + END_FTR_SECTION_NESTED((msk), (msk), label) + #define END_FTR_SECTION_IFSET(msk) END_FTR_SECTION((msk), (msk)) #define END_FTR_SECTION_IFCLR(msk) END_FTR_SECTION((msk), 0) diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h index 5067048..86eb8738 100644 --- a/arch/powerpc/include/asm/head-64.h +++ b/arch/powerpc/include/asm/head-64.h @@ -213,6 +213,7 @@ name: USE_TEXT_SECTION(); \ .balign IFETCH_ALIGN_BYTES; \ .global name; \ + _ASM_NOKPROBE_SYMBOL(name); \ DEFINE_FIXED_SYMBOL(name); \ name: diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 3cc12a8..d73755f 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -377,16 +377,6 @@ long plpar_hcall_raw(unsigned long opcode, unsigned long *retbuf, ...); long plpar_hcall9(unsigned long opcode, unsigned long *retbuf, ...); long plpar_hcall9_raw(unsigned long opcode, unsigned long *retbuf, ...); -/* For hcall instrumentation. One structure per-hcall, per-CPU */ -struct hcall_stats { - unsigned long num_calls; /* number of calls (on this CPU) */ - unsigned long tb_total; /* total wall time (mftb) of calls. */ - unsigned long purr_total; /* total cpu time (PURR) of calls. */ - unsigned long tb_start; - unsigned long purr_start; -}; -#define HCALL_STAT_ARRAY_SIZE ((MAX_HCALL_OPCODE >> 2) + 1) - struct hvcall_mpp_data { unsigned long entitled_mem; unsigned long mapped_mem; diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 5ed2924..422f99c 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -25,8 +25,6 @@ extern struct pci_dev *isa_bridge_pcidev; #endif #include <linux/device.h> -#include <linux/io.h> - #include <linux/compiler.h> #include <asm/page.h> #include <asm/byteorder.h> @@ -192,24 +190,8 @@ DEF_MMIO_OUT_D(out_le32, 32, stw); #endif /* __BIG_ENDIAN */ -/* - * Cache inhibitied accessors for use in real mode, you don't want to use these - * unless you know what you're doing. - * - * NB. These use the cpu byte ordering. - */ -DEF_MMIO_OUT_X(out_rm8, 8, stbcix); -DEF_MMIO_OUT_X(out_rm16, 16, sthcix); -DEF_MMIO_OUT_X(out_rm32, 32, stwcix); -DEF_MMIO_IN_X(in_rm8, 8, lbzcix); -DEF_MMIO_IN_X(in_rm16, 16, lhzcix); -DEF_MMIO_IN_X(in_rm32, 32, lwzcix); - #ifdef __powerpc64__ -DEF_MMIO_OUT_X(out_rm64, 64, stdcix); -DEF_MMIO_IN_X(in_rm64, 64, ldcix); - #ifdef __BIG_ENDIAN__ DEF_MMIO_OUT_D(out_be64, 64, std); DEF_MMIO_IN_D(in_be64, 64, ld); @@ -242,35 +224,6 @@ static inline void out_be64(volatile u64 __iomem *addr, u64 val) #endif #endif /* __powerpc64__ */ - -/* - * Simple Cache inhibited accessors - * Unlike the DEF_MMIO_* macros, these don't include any h/w memory - * barriers, callers need to manage memory barriers on their own. - * These can only be used in hypervisor real mode. - */ - -static inline u32 _lwzcix(unsigned long addr) -{ - u32 ret; - - __asm__ __volatile__("lwzcix %0,0, %1" - : "=r" (ret) : "r" (addr) : "memory"); - return ret; -} - -static inline void _stbcix(u64 addr, u8 val) -{ - __asm__ __volatile__("stbcix %0,0,%1" - : : "r" (val), "r" (addr) : "memory"); -} - -static inline void _stwcix(u64 addr, u32 val) -{ - __asm__ __volatile__("stwcix %0,0,%1" - : : "r" (val), "r" (addr) : "memory"); -} - /* * Low level IO stream instructions are defined out of line for now */ @@ -417,15 +370,64 @@ static inline void __raw_writeq(unsigned long v, volatile void __iomem *addr) } /* - * Real mode version of the above. stdcix is only supposed to be used - * in hypervisor real mode as per the architecture spec. + * Real mode versions of the above. Those instructions are only supposed + * to be used in hypervisor real mode as per the architecture spec. */ +static inline void __raw_rm_writeb(u8 val, volatile void __iomem *paddr) +{ + __asm__ __volatile__("stbcix %0,0,%1" + : : "r" (val), "r" (paddr) : "memory"); +} + +static inline void __raw_rm_writew(u16 val, volatile void __iomem *paddr) +{ + __asm__ __volatile__("sthcix %0,0,%1" + : : "r" (val), "r" (paddr) : "memory"); +} + +static inline void __raw_rm_writel(u32 val, volatile void __iomem *paddr) +{ + __asm__ __volatile__("stwcix %0,0,%1" + : : "r" (val), "r" (paddr) : "memory"); +} + static inline void __raw_rm_writeq(u64 val, volatile void __iomem *paddr) { __asm__ __volatile__("stdcix %0,0,%1" : : "r" (val), "r" (paddr) : "memory"); } +static inline u8 __raw_rm_readb(volatile void __iomem *paddr) +{ + u8 ret; + __asm__ __volatile__("lbzcix %0,0, %1" + : "=r" (ret) : "r" (paddr) : "memory"); + return ret; +} + +static inline u16 __raw_rm_readw(volatile void __iomem *paddr) +{ + u16 ret; + __asm__ __volatile__("lhzcix %0,0, %1" + : "=r" (ret) : "r" (paddr) : "memory"); + return ret; +} + +static inline u32 __raw_rm_readl(volatile void __iomem *paddr) +{ + u32 ret; + __asm__ __volatile__("lwzcix %0,0, %1" + : "=r" (ret) : "r" (paddr) : "memory"); + return ret; +} + +static inline u64 __raw_rm_readq(volatile void __iomem *paddr) +{ + u64 ret; + __asm__ __volatile__("ldcix %0,0, %1" + : "=r" (ret) : "r" (paddr) : "memory"); + return ret; +} #endif /* __powerpc64__ */ /* @@ -757,6 +759,8 @@ extern void __iomem *ioremap_prot(phys_addr_t address, unsigned long size, extern void __iomem *ioremap_wc(phys_addr_t address, unsigned long size); #define ioremap_nocache(addr, size) ioremap((addr), (size)) #define ioremap_uc(addr, size) ioremap((addr), (size)) +#define ioremap_cache(addr, size) \ + ioremap_prot((addr), (size), pgprot_val(PAGE_KERNEL)) extern void iounmap(volatile void __iomem *addr); diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 2c1d507..d961425 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -64,6 +64,11 @@ struct iommu_table_ops { long index, unsigned long *hpa, enum dma_data_direction *direction); + /* Real mode */ + int (*exchange_rm)(struct iommu_table *tbl, + long index, + unsigned long *hpa, + enum dma_data_direction *direction); #endif void (*clear)(struct iommu_table *tbl, long index, long npages); @@ -114,6 +119,7 @@ struct iommu_table { struct list_head it_group_list;/* List of iommu_table_group_link */ unsigned long *it_userspace; /* userspace view of the table */ struct iommu_table_ops *it_ops; + struct kref it_kref; }; #define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \ @@ -146,8 +152,8 @@ static inline void *get_iommu_table_base(struct device *dev) extern int dma_iommu_dma_supported(struct device *dev, u64 mask); -/* Frees table for an individual device node */ -extern void iommu_free_table(struct iommu_table *tbl, const char *node_name); +extern struct iommu_table *iommu_tce_table_get(struct iommu_table *tbl); +extern int iommu_tce_table_put(struct iommu_table *tbl); /* Initializes an iommu_table based in values set in the passed-in * structure @@ -208,6 +214,8 @@ extern void iommu_del_device(struct device *dev); extern int __init tce_iommu_bus_notifier_init(void); extern long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry, unsigned long *hpa, enum dma_data_direction *direction); +extern long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry, + unsigned long *hpa, enum dma_data_direction *direction); #else static inline void iommu_register_group(struct iommu_table_group *table_group, int pci_domain_number, diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h index 0503c98..a83821f 100644 --- a/arch/powerpc/include/asm/kprobes.h +++ b/arch/powerpc/include/asm/kprobes.h @@ -61,59 +61,6 @@ extern kprobe_opcode_t optprobe_template_end[]; #define MAX_OPTINSN_SIZE (optprobe_template_end - optprobe_template_entry) #define RELATIVEJUMP_SIZE sizeof(kprobe_opcode_t) /* 4 bytes */ -#ifdef PPC64_ELF_ABI_v2 -/* PPC64 ABIv2 needs local entry point */ -#define kprobe_lookup_name(name, addr) \ -{ \ - addr = (kprobe_opcode_t *)kallsyms_lookup_name(name); \ - if (addr) \ - addr = (kprobe_opcode_t *)ppc_function_entry(addr); \ -} -#elif defined(PPC64_ELF_ABI_v1) -/* - * 64bit powerpc ABIv1 uses function descriptors: - * - Check for the dot variant of the symbol first. - * - If that fails, try looking up the symbol provided. - * - * This ensures we always get to the actual symbol and not the descriptor. - * Also handle <module:symbol> format. - */ -#define kprobe_lookup_name(name, addr) \ -{ \ - char dot_name[MODULE_NAME_LEN + 1 + KSYM_NAME_LEN]; \ - const char *modsym; \ - bool dot_appended = false; \ - if ((modsym = strchr(name, ':')) != NULL) { \ - modsym++; \ - if (*modsym != '\0' && *modsym != '.') { \ - /* Convert to <module:.symbol> */ \ - strncpy(dot_name, name, modsym - name); \ - dot_name[modsym - name] = '.'; \ - dot_name[modsym - name + 1] = '\0'; \ - strncat(dot_name, modsym, \ - sizeof(dot_name) - (modsym - name) - 2);\ - dot_appended = true; \ - } else { \ - dot_name[0] = '\0'; \ - strncat(dot_name, name, sizeof(dot_name) - 1); \ - } \ - } else if (name[0] != '.') { \ - dot_name[0] = '.'; \ - dot_name[1] = '\0'; \ - strncat(dot_name, name, KSYM_NAME_LEN - 2); \ - dot_appended = true; \ - } else { \ - dot_name[0] = '\0'; \ - strncat(dot_name, name, KSYM_NAME_LEN - 1); \ - } \ - addr = (kprobe_opcode_t *)kallsyms_lookup_name(dot_name); \ - if (!addr && dot_appended) { \ - /* Let's try the original non-dot symbol lookup */ \ - addr = (kprobe_opcode_t *)kallsyms_lookup_name(name); \ - } \ -} -#endif - #define flush_insn_slot(p) do { } while (0) #define kretprobe_blacklist_size 0 @@ -156,6 +103,16 @@ extern int kprobe_exceptions_notify(struct notifier_block *self, extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr); extern int kprobe_handler(struct pt_regs *regs); extern int kprobe_post_handler(struct pt_regs *regs); +#ifdef CONFIG_KPROBES_ON_FTRACE +extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb); +#else +static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + return 0; +} +#endif #else static inline int kprobe_handler(struct pt_regs *regs) { return 0; } static inline int kprobe_post_handler(struct pt_regs *regs) { return 0; } diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index d9b48f5..d55c7f8 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -49,8 +49,6 @@ static inline bool kvm_is_radix(struct kvm *kvm) #define KVM_DEFAULT_HPT_ORDER 24 /* 16MB HPT by default */ #endif -#define VRMA_VSID 0x1ffffffUL /* 1TB VSID reserved for VRMA */ - /* * We use a lock bit in HPTE dword 0 to synchronize updates and * accesses to each HPTE, and another bit to indicate non-present diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index d318d43..0593d94 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -110,7 +110,7 @@ struct kvmppc_host_state { u8 ptid; struct kvm_vcpu *kvm_vcpu; struct kvmppc_vcore *kvm_vcore; - unsigned long xics_phys; + void __iomem *xics_phys; u32 saved_xirr; u64 dabr; u64 host_mmcr[7]; /* MMCR 0,1,A, SIAR, SDAR, MMCR2, SIER */ diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index dd11c4c..c387799 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -409,7 +409,7 @@ struct openpic; extern void kvm_cma_reserve(void) __init; static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr) { - paca[cpu].kvm_hstate.xics_phys = addr; + paca[cpu].kvm_hstate.xics_phys = (void __iomem *)addr; } static inline u32 kvmppc_get_xics_latch(void) @@ -478,8 +478,6 @@ extern void kvmppc_free_host_rm_ops(void); extern void kvmppc_free_pimap(struct kvm *kvm); extern int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall); extern void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu); -extern int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu, unsigned long server); -extern int kvm_vm_ioctl_xics_irq(struct kvm *kvm, struct kvm_irq_level *args); extern int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd); extern u64 kvmppc_xics_get_icp(struct kvm_vcpu *vcpu); extern int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 icpval); @@ -507,12 +505,6 @@ static inline int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall) static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu) { return 0; } static inline void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu) { } -static inline int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu, - unsigned long server) - { return -EINVAL; } -static inline int kvm_vm_ioctl_xics_irq(struct kvm *kvm, - struct kvm_irq_level *args) - { return -ENOTTY; } static inline int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd) { return 0; } #endif diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h index ed62efe..81eff86 100644 --- a/arch/powerpc/include/asm/mce.h +++ b/arch/powerpc/include/asm/mce.h @@ -24,97 +24,6 @@ #include <linux/bitops.h> -/* - * Machine Check bits on power7 and power8 - */ -#define P7_SRR1_MC_LOADSTORE(srr1) ((srr1) & PPC_BIT(42)) /* P8 too */ - -/* SRR1 bits for machine check (On Power7 and Power8) */ -#define P7_SRR1_MC_IFETCH(srr1) ((srr1) & PPC_BITMASK(43, 45)) /* P8 too */ - -#define P7_SRR1_MC_IFETCH_UE (0x1 << PPC_BITLSHIFT(45)) /* P8 too */ -#define P7_SRR1_MC_IFETCH_SLB_PARITY (0x2 << PPC_BITLSHIFT(45)) /* P8 too */ -#define P7_SRR1_MC_IFETCH_SLB_MULTIHIT (0x3 << PPC_BITLSHIFT(45)) /* P8 too */ -#define P7_SRR1_MC_IFETCH_SLB_BOTH (0x4 << PPC_BITLSHIFT(45)) -#define P7_SRR1_MC_IFETCH_TLB_MULTIHIT (0x5 << PPC_BITLSHIFT(45)) /* P8 too */ -#define P7_SRR1_MC_IFETCH_UE_TLB_RELOAD (0x6 << PPC_BITLSHIFT(45)) /* P8 too */ -#define P7_SRR1_MC_IFETCH_UE_IFU_INTERNAL (0x7 << PPC_BITLSHIFT(45)) - -/* SRR1 bits for machine check (On Power8) */ -#define P8_SRR1_MC_IFETCH_ERAT_MULTIHIT (0x4 << PPC_BITLSHIFT(45)) - -/* DSISR bits for machine check (On Power7 and Power8) */ -#define P7_DSISR_MC_UE (PPC_BIT(48)) /* P8 too */ -#define P7_DSISR_MC_UE_TABLEWALK (PPC_BIT(49)) /* P8 too */ -#define P7_DSISR_MC_ERAT_MULTIHIT (PPC_BIT(52)) /* P8 too */ -#define P7_DSISR_MC_TLB_MULTIHIT_MFTLB (PPC_BIT(53)) /* P8 too */ -#define P7_DSISR_MC_SLB_PARITY_MFSLB (PPC_BIT(55)) /* P8 too */ -#define P7_DSISR_MC_SLB_MULTIHIT (PPC_BIT(56)) /* P8 too */ -#define P7_DSISR_MC_SLB_MULTIHIT_PARITY (PPC_BIT(57)) /* P8 too */ - -/* - * DSISR bits for machine check (Power8) in addition to above. - * Secondary DERAT Multihit - */ -#define P8_DSISR_MC_ERAT_MULTIHIT_SEC (PPC_BIT(54)) - -/* SLB error bits */ -#define P7_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_ERAT_MULTIHIT | \ - P7_DSISR_MC_SLB_PARITY_MFSLB | \ - P7_DSISR_MC_SLB_MULTIHIT | \ - P7_DSISR_MC_SLB_MULTIHIT_PARITY) - -#define P8_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_SLB_ERRORS | \ - P8_DSISR_MC_ERAT_MULTIHIT_SEC) - -/* - * Machine Check bits on power9 - */ -#define P9_SRR1_MC_LOADSTORE(srr1) (((srr1) >> PPC_BITLSHIFT(42)) & 1) - -#define P9_SRR1_MC_IFETCH(srr1) ( \ - PPC_BITEXTRACT(srr1, 45, 0) | \ - PPC_BITEXTRACT(srr1, 44, 1) | \ - PPC_BITEXTRACT(srr1, 43, 2) | \ - PPC_BITEXTRACT(srr1, 36, 3) ) - -/* 0 is reserved */ -#define P9_SRR1_MC_IFETCH_UE 1 -#define P9_SRR1_MC_IFETCH_SLB_PARITY 2 -#define P9_SRR1_MC_IFETCH_SLB_MULTIHIT 3 -#define P9_SRR1_MC_IFETCH_ERAT_MULTIHIT 4 -#define P9_SRR1_MC_IFETCH_TLB_MULTIHIT 5 -#define P9_SRR1_MC_IFETCH_UE_TLB_RELOAD 6 -/* 7 is reserved */ -#define P9_SRR1_MC_IFETCH_LINK_TIMEOUT 8 -#define P9_SRR1_MC_IFETCH_LINK_TABLEWALK_TIMEOUT 9 -/* 10 ? */ -#define P9_SRR1_MC_IFETCH_RA 11 -#define P9_SRR1_MC_IFETCH_RA_TABLEWALK 12 -#define P9_SRR1_MC_IFETCH_RA_ASYNC_STORE 13 -#define P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT 14 -#define P9_SRR1_MC_IFETCH_RA_TABLEWALK_FOREIGN 15 - -/* DSISR bits for machine check (On Power9) */ -#define P9_DSISR_MC_UE (PPC_BIT(48)) -#define P9_DSISR_MC_UE_TABLEWALK (PPC_BIT(49)) -#define P9_DSISR_MC_LINK_LOAD_TIMEOUT (PPC_BIT(50)) -#define P9_DSISR_MC_LINK_TABLEWALK_TIMEOUT (PPC_BIT(51)) -#define P9_DSISR_MC_ERAT_MULTIHIT (PPC_BIT(52)) -#define P9_DSISR_MC_TLB_MULTIHIT_MFTLB (PPC_BIT(53)) -#define P9_DSISR_MC_USER_TLBIE (PPC_BIT(54)) -#define P9_DSISR_MC_SLB_PARITY_MFSLB (PPC_BIT(55)) -#define P9_DSISR_MC_SLB_MULTIHIT_MFSLB (PPC_BIT(56)) -#define P9_DSISR_MC_RA_LOAD (PPC_BIT(57)) -#define P9_DSISR_MC_RA_TABLEWALK (PPC_BIT(58)) -#define P9_DSISR_MC_RA_TABLEWALK_FOREIGN (PPC_BIT(59)) -#define P9_DSISR_MC_RA_FOREIGN (PPC_BIT(60)) - -/* SLB error bits */ -#define P9_DSISR_MC_SLB_ERRORS (P9_DSISR_MC_ERAT_MULTIHIT | \ - P9_DSISR_MC_SLB_PARITY_MFSLB | \ - P9_DSISR_MC_SLB_MULTIHIT_MFSLB) - enum MCE_Version { MCE_V1 = 1, }; @@ -298,7 +207,8 @@ extern void save_mce_event(struct pt_regs *regs, long handled, extern int get_mce_event(struct machine_check_event *mce, bool release); extern void release_mce_event(void); extern void machine_check_queue_event(void); -extern void machine_check_print_event_info(struct machine_check_event *evt); +extern void machine_check_print_event_info(struct machine_check_event *evt, + bool user_mode); extern uint64_t get_mce_fault_addr(struct machine_check_event *evt); #endif /* __ASM_PPC64_MCE_H__ */ diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h index b62a8d4..7ca8d8e 100644 --- a/arch/powerpc/include/asm/mmu-book3e.h +++ b/arch/powerpc/include/asm/mmu-book3e.h @@ -229,11 +229,6 @@ typedef struct { unsigned int id; unsigned int active; unsigned long vdso_base; -#ifdef CONFIG_PPC_MM_SLICES - u64 low_slices_psize; /* SLB page size encodings */ - u64 high_slices_psize; /* 4 bits per slice for now */ - u16 user_psize; /* page size index */ -#endif #ifdef CONFIG_PPC_64K_PAGES /* for 4K PTE fragment support */ void *pte_frag; diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 065e762..7826040 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -29,6 +29,10 @@ */ /* + * Support for 68 bit VA space. We added that from ISA 2.05 + */ +#define MMU_FTR_68_BIT_VA ASM_CONST(0x00002000) +/* * Kernel read only support. * We added the ppp value 0b110 in ISA 2.04. */ @@ -109,10 +113,10 @@ #define MMU_FTRS_POWER4 MMU_FTRS_DEFAULT_HPTE_ARCH_V2 #define MMU_FTRS_PPC970 MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA #define MMU_FTRS_POWER5 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE -#define MMU_FTRS_POWER6 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_KERNEL_RO -#define MMU_FTRS_POWER7 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_KERNEL_RO -#define MMU_FTRS_POWER8 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_KERNEL_RO -#define MMU_FTRS_POWER9 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_KERNEL_RO +#define MMU_FTRS_POWER6 MMU_FTRS_POWER5 | MMU_FTR_KERNEL_RO | MMU_FTR_68_BIT_VA +#define MMU_FTRS_POWER7 MMU_FTRS_POWER6 +#define MMU_FTRS_POWER8 MMU_FTRS_POWER6 +#define MMU_FTRS_POWER9 MMU_FTRS_POWER6 #define MMU_FTRS_CELL MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \ MMU_FTR_CI_LARGE_PAGE #define MMU_FTRS_PA6T MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \ @@ -136,7 +140,7 @@ enum { MMU_FTR_NO_SLBIE_B | MMU_FTR_16M_PAGE | MMU_FTR_TLBIEL | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_CI_LARGE_PAGE | MMU_FTR_1T_SEGMENT | MMU_FTR_TLBIE_CROP_VA | - MMU_FTR_KERNEL_RO | + MMU_FTR_KERNEL_RO | MMU_FTR_68_BIT_VA | #ifdef CONFIG_PPC_RADIX_MMU MMU_FTR_TYPE_RADIX | #endif @@ -290,7 +294,10 @@ static inline bool early_radix_enabled(void) #define MMU_PAGE_16G 14 #define MMU_PAGE_64G 15 -/* N.B. we need to change the type of hpte_page_sizes if this gets to be > 16 */ +/* + * N.B. we need to change the type of hpte_page_sizes if this gets to be > 16 + * Also we need to change he type of mm_context.low/high_slices_psize. + */ #define MMU_PAGE_COUNT 16 #ifdef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index ecf9885..da7e943 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -29,10 +29,14 @@ extern void mm_iommu_init(struct mm_struct *mm); extern void mm_iommu_cleanup(struct mm_struct *mm); extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm, unsigned long ua, unsigned long size); +extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm( + struct mm_struct *mm, unsigned long ua, unsigned long size); extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm, unsigned long ua, unsigned long entries); extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, unsigned long ua, unsigned long *hpa); +extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, + unsigned long ua, unsigned long *hpa); extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem); extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem); #endif @@ -51,7 +55,8 @@ static inline void switch_mmu_context(struct mm_struct *prev, return switch_slb(tsk, next); } -extern int __init_new_context(void); +extern int hash__alloc_context_id(void); +extern void hash__reserve_context_id(int id); extern void __destroy_context(int context_id); static inline void mmu_context_init(void) { } #else @@ -70,8 +75,9 @@ extern void drop_cop(unsigned long acop, struct mm_struct *mm); * switch_mm is the entry point called from the architecture independent * code in kernel/sched/core.c */ -static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, - struct task_struct *tsk) +static inline void switch_mm_irqs_off(struct mm_struct *prev, + struct mm_struct *next, + struct task_struct *tsk) { /* Mark this context has been used on the new CPU */ if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next))) @@ -110,6 +116,18 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, switch_mmu_context(prev, next, tsk); } +static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, + struct task_struct *tsk) +{ + unsigned long flags; + + local_irq_save(flags); + switch_mm_irqs_off(prev, next, tsk); + local_irq_restore(flags); +} +#define switch_mm_irqs_off switch_mm_irqs_off + + #define deactivate_mm(tsk,mm) do { } while (0) /* diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index c7f927e..f0ff384 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -88,11 +88,6 @@ #include <asm/nohash/pte-book3e.h> #include <asm/pte-common.h> -#ifdef CONFIG_PPC_MM_SLICES -#define HAVE_ARCH_UNMAPPED_AREA -#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN -#endif /* CONFIG_PPC_MM_SLICES */ - #ifndef __ASSEMBLY__ /* pte_clear moved to later in this file */ diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index a0aa285..cb3e624 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -40,6 +40,8 @@ #define OPAL_I2C_ARBT_LOST -22 #define OPAL_I2C_NACK_RCVD -23 #define OPAL_I2C_STOP_ERR -24 +#define OPAL_XIVE_PROVISIONING -31 +#define OPAL_XIVE_FREE_ACTIVE -32 /* API Tokens (in r0) */ #define OPAL_INVALID_CALL -1 @@ -168,7 +170,27 @@ #define OPAL_INT_SET_MFRR 125 #define OPAL_PCI_TCE_KILL 126 #define OPAL_NMMU_SET_PTCR 127 -#define OPAL_LAST 127 +#define OPAL_XIVE_RESET 128 +#define OPAL_XIVE_GET_IRQ_INFO 129 +#define OPAL_XIVE_GET_IRQ_CONFIG 130 +#define OPAL_XIVE_SET_IRQ_CONFIG 131 +#define OPAL_XIVE_GET_QUEUE_INFO 132 +#define OPAL_XIVE_SET_QUEUE_INFO 133 +#define OPAL_XIVE_DONATE_PAGE 134 +#define OPAL_XIVE_ALLOCATE_VP_BLOCK 135 +#define OPAL_XIVE_FREE_VP_BLOCK 136 +#define OPAL_XIVE_GET_VP_INFO 137 +#define OPAL_XIVE_SET_VP_INFO 138 +#define OPAL_XIVE_ALLOCATE_IRQ 139 +#define OPAL_XIVE_FREE_IRQ 140 +#define OPAL_XIVE_SYNC 141 +#define OPAL_XIVE_DUMP 142 +#define OPAL_XIVE_RESERVED3 143 +#define OPAL_XIVE_RESERVED4 144 +#define OPAL_NPU_INIT_CONTEXT 146 +#define OPAL_NPU_DESTROY_CONTEXT 147 +#define OPAL_NPU_MAP_LPAR 148 +#define OPAL_LAST 148 /* Device tree flags */ @@ -928,6 +950,59 @@ enum { OPAL_PCI_TCE_KILL_ALL, }; +/* The xive operation mode indicates the active "API" and + * corresponds to the "mode" parameter of the opal_xive_reset() + * call + */ +enum { + OPAL_XIVE_MODE_EMU = 0, + OPAL_XIVE_MODE_EXPL = 1, +}; + +/* Flags for OPAL_XIVE_GET_IRQ_INFO */ +enum { + OPAL_XIVE_IRQ_TRIGGER_PAGE = 0x00000001, + OPAL_XIVE_IRQ_STORE_EOI = 0x00000002, + OPAL_XIVE_IRQ_LSI = 0x00000004, + OPAL_XIVE_IRQ_SHIFT_BUG = 0x00000008, + OPAL_XIVE_IRQ_MASK_VIA_FW = 0x00000010, + OPAL_XIVE_IRQ_EOI_VIA_FW = 0x00000020, +}; + +/* Flags for OPAL_XIVE_GET/SET_QUEUE_INFO */ +enum { + OPAL_XIVE_EQ_ENABLED = 0x00000001, + OPAL_XIVE_EQ_ALWAYS_NOTIFY = 0x00000002, + OPAL_XIVE_EQ_ESCALATE = 0x00000004, +}; + +/* Flags for OPAL_XIVE_GET/SET_VP_INFO */ +enum { + OPAL_XIVE_VP_ENABLED = 0x00000001, +}; + +/* "Any chip" replacement for chip ID for allocation functions */ +enum { + OPAL_XIVE_ANY_CHIP = 0xffffffff, +}; + +/* Xive sync options */ +enum { + /* This bits are cumulative, arg is a girq */ + XIVE_SYNC_EAS = 0x00000001, /* Sync irq source */ + XIVE_SYNC_QUEUE = 0x00000002, /* Sync irq target */ +}; + +/* Dump options */ +enum { + XIVE_DUMP_TM_HYP = 0, + XIVE_DUMP_TM_POOL = 1, + XIVE_DUMP_TM_OS = 2, + XIVE_DUMP_TM_USER = 3, + XIVE_DUMP_VP = 4, + XIVE_DUMP_EMU_STATE = 5, +}; + #endif /* __ASSEMBLY__ */ #endif /* __OPAL_API_H */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 1ff03a6..588fb1c 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -29,6 +29,11 @@ extern struct device_node *opal_node; /* API functions */ int64_t opal_invalid_call(void); +int64_t opal_npu_destroy_context(uint64_t phb_id, uint64_t pid, uint64_t bdf); +int64_t opal_npu_init_context(uint64_t phb_id, int pasid, uint64_t msr, + uint64_t bdf); +int64_t opal_npu_map_lpar(uint64_t phb_id, uint64_t bdf, uint64_t lparid, + uint64_t lpcr); int64_t opal_console_write(int64_t term_number, __be64 *length, const uint8_t *buffer); int64_t opal_console_read(int64_t term_number, __be64 *length, @@ -226,6 +231,42 @@ int64_t opal_pci_tce_kill(uint64_t phb_id, uint32_t kill_type, uint32_t pe_num, uint32_t tce_size, uint64_t dma_addr, uint32_t npages); int64_t opal_nmmu_set_ptcr(uint64_t chip_id, uint64_t ptcr); +int64_t opal_xive_reset(uint64_t version); +int64_t opal_xive_get_irq_info(uint32_t girq, + __be64 *out_flags, + __be64 *out_eoi_page, + __be64 *out_trig_page, + __be32 *out_esb_shift, + __be32 *out_src_chip); +int64_t opal_xive_get_irq_config(uint32_t girq, __be64 *out_vp, + uint8_t *out_prio, __be32 *out_lirq); +int64_t opal_xive_set_irq_config(uint32_t girq, uint64_t vp, uint8_t prio, + uint32_t lirq); +int64_t opal_xive_get_queue_info(uint64_t vp, uint32_t prio, + __be64 *out_qpage, + __be64 *out_qsize, + __be64 *out_qeoi_page, + __be32 *out_escalate_irq, + __be64 *out_qflags); +int64_t opal_xive_set_queue_info(uint64_t vp, uint32_t prio, + uint64_t qpage, + uint64_t qsize, + uint64_t qflags); +int64_t opal_xive_donate_page(uint32_t chip_id, uint64_t addr); +int64_t opal_xive_alloc_vp_block(uint32_t alloc_order); +int64_t opal_xive_free_vp_block(uint64_t vp); +int64_t opal_xive_get_vp_info(uint64_t vp, + __be64 *out_flags, + __be64 *out_cam_value, + __be64 *out_report_cl_pair, + __be32 *out_chip_id); +int64_t opal_xive_set_vp_info(uint64_t vp, + uint64_t flags, + uint64_t report_cl_pair); +int64_t opal_xive_allocate_irq(uint32_t chip_id); +int64_t opal_xive_free_irq(uint32_t girq); +int64_t opal_xive_sync(uint32_t type, uint32_t id); +int64_t opal_xive_dump(uint32_t type, uint32_t id); /* Internal functions */ extern int early_init_dt_scan_opal(unsigned long node, const char *uname, diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 708c3e5..1c09f8f 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -99,7 +99,6 @@ struct paca_struct { */ /* used for most interrupts/exceptions */ u64 exgen[13] __attribute__((aligned(0x80))); - u64 exmc[13]; /* used for machine checks */ u64 exslb[13]; /* used for SLB/segment table misses * on the linear mapping */ /* SLB related definitions */ @@ -139,6 +138,7 @@ struct paca_struct { #ifdef CONFIG_PPC_MM_SLICES u64 mm_ctx_low_slices_psize; unsigned char mm_ctx_high_slices_psize[SLICE_ARRAY_SIZE]; + unsigned long addr_limit; #else u16 mm_ctx_user_psize; u16 mm_ctx_sllp; @@ -172,17 +172,31 @@ struct paca_struct { u8 thread_mask; /* Mask to denote subcore sibling threads */ u8 subcore_sibling_mask; + /* + * Pointer to an array which contains pointer + * to the sibling threads' paca. + */ + struct paca_struct **thread_sibling_pacas; #endif +#ifdef CONFIG_PPC_STD_MMU_64 + /* Non-maskable exceptions that are not performance critical */ + u64 exnmi[13]; /* used for system reset (nmi) */ + u64 exmc[13]; /* used for machine checks */ +#endif #ifdef CONFIG_PPC_BOOK3S_64 - /* Exclusive emergency stack pointer for machine check exception. */ + /* Exclusive stacks for system reset and machine check exception. */ + void *nmi_emergency_sp; void *mc_emergency_sp; + + u16 in_nmi; /* In nmi handler */ + /* * Flag to check whether we are in machine check early handler * and already using emergency stack. */ u16 in_mce; - u8 hmi_event_available; /* HMI event is available */ + u8 hmi_event_available; /* HMI event is available */ #endif /* Stuff for accurate time accounting */ @@ -206,23 +220,7 @@ struct paca_struct { #endif }; -#ifdef CONFIG_PPC_BOOK3S -static inline void copy_mm_to_paca(mm_context_t *context) -{ - get_paca()->mm_ctx_id = context->id; -#ifdef CONFIG_PPC_MM_SLICES - get_paca()->mm_ctx_low_slices_psize = context->low_slices_psize; - memcpy(&get_paca()->mm_ctx_high_slices_psize, - &context->high_slices_psize, SLICE_ARRAY_SIZE); -#else - get_paca()->mm_ctx_user_psize = context->user_psize; - get_paca()->mm_ctx_sllp = context->sllp; -#endif -} -#else -static inline void copy_mm_to_paca(mm_context_t *context){} -#endif - +extern void copy_mm_to_paca(struct mm_struct *mm); extern struct paca_struct *paca; extern void initialise_paca(struct paca_struct *new_paca, int cpu); extern void setup_paca(struct paca_struct *new_paca); diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h index 3e83d2a..c4d9654 100644 --- a/arch/powerpc/include/asm/page_64.h +++ b/arch/powerpc/include/asm/page_64.h @@ -98,21 +98,7 @@ extern u64 ppc64_pft_size; #define GET_LOW_SLICE_INDEX(addr) ((addr) >> SLICE_LOW_SHIFT) #define GET_HIGH_SLICE_INDEX(addr) ((addr) >> SLICE_HIGH_SHIFT) -/* - * 1 bit per slice and we have one slice per 1TB - * Right now we support only 64TB. - * IF we change this we will have to change the type - * of high_slices - */ -#define SLICE_MASK_SIZE 8 - #ifndef __ASSEMBLY__ - -struct slice_mask { - u16 low_slices; - u64 high_slices; -}; - struct mm_struct; extern unsigned long slice_get_unmapped_area(unsigned long addr, diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h index ae0a230..723bf48 100644 --- a/arch/powerpc/include/asm/perf_event_server.h +++ b/arch/powerpc/include/asm/perf_event_server.h @@ -38,6 +38,9 @@ struct power_pmu { unsigned long *valp); int (*get_alternatives)(u64 event_id, unsigned int flags, u64 alt[]); + void (*get_mem_data_src)(union perf_mem_data_src *dsrc, + u32 flags, struct pt_regs *regs); + void (*get_mem_weight)(u64 *weight); u64 (*bhrb_filter_map)(u64 branch_sample_type); void (*config_bhrb)(u64 pmu_bhrb_filter); void (*disable_pmc)(unsigned int pmc, unsigned long mmcr[]); diff --git a/arch/powerpc/include/asm/powernv.h b/arch/powerpc/include/asm/powernv.h index 0e9c240..f627977 100644 --- a/arch/powerpc/include/asm/powernv.h +++ b/arch/powerpc/include/asm/powernv.h @@ -11,9 +11,31 @@ #define _ASM_POWERNV_H #ifdef CONFIG_PPC_POWERNV +#define NPU2_WRITE 1 extern void powernv_set_nmmu_ptcr(unsigned long ptcr); +extern struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, + unsigned long flags, + struct npu_context *(*cb)(struct npu_context *, void *), + void *priv); +extern void pnv_npu2_destroy_context(struct npu_context *context, + struct pci_dev *gpdev); +extern int pnv_npu2_handle_fault(struct npu_context *context, uintptr_t *ea, + unsigned long *flags, unsigned long *status, + int count); #else static inline void powernv_set_nmmu_ptcr(unsigned long ptcr) { } +static inline struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, + unsigned long flags, + struct npu_context *(*cb)(struct npu_context *, void *), + void *priv) { return ERR_PTR(-ENODEV); } +static inline void pnv_npu2_destroy_context(struct npu_context *context, + struct pci_dev *gpdev) { } + +static inline int pnv_npu2_handle_fault(struct npu_context *context, + uintptr_t *ea, unsigned long *flags, + unsigned long *status, int count) { + return -ENODEV; +} #endif #endif /* _ASM_POWERNV_H */ diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index e7d6d86..142d78d 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -161,6 +161,7 @@ #define PPC_INST_MFTMR 0x7c0002dc #define PPC_INST_MSGSND 0x7c00019c #define PPC_INST_MSGCLR 0x7c0001dc +#define PPC_INST_MSGSYNC 0x7c0006ec #define PPC_INST_MSGSNDP 0x7c00011c #define PPC_INST_MTTMR 0x7c0003dc #define PPC_INST_NOP 0x60000000 @@ -345,6 +346,7 @@ ___PPC_RB(b) | __PPC_EH(eh)) #define PPC_MSGSND(b) stringify_in_c(.long PPC_INST_MSGSND | \ ___PPC_RB(b)) +#define PPC_MSGSYNC stringify_in_c(.long PPC_INST_MSGSYNC) #define PPC_MSGCLR(b) stringify_in_c(.long PPC_INST_MSGCLR | \ ___PPC_RB(b)) #define PPC_MSGSNDP(b) stringify_in_c(.long PPC_INST_MSGSNDP | \ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index e0fecbc..a4b1d8d 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -102,11 +102,25 @@ void release_thread(struct task_struct *); #endif #ifdef CONFIG_PPC64 -/* 64-bit user address space is 46-bits (64TB user VM) */ -#define TASK_SIZE_USER64 (0x0000400000000000UL) +/* + * 64-bit user address space can have multiple limits + * For now supported values are: + */ +#define TASK_SIZE_64TB (0x0000400000000000UL) +#define TASK_SIZE_128TB (0x0000800000000000UL) +#define TASK_SIZE_512TB (0x0002000000000000UL) + +#ifdef CONFIG_PPC_BOOK3S_64 +/* + * Max value currently used: + */ +#define TASK_SIZE_USER64 TASK_SIZE_512TB +#else +#define TASK_SIZE_USER64 TASK_SIZE_64TB +#endif -/* - * 32-bit user address space is 4GB - 1 page +/* + * 32-bit user address space is 4GB - 1 page * (this 1 page is needed so referencing of 0xFFFFFFFF generates EFAULT */ #define TASK_SIZE_USER32 (0x0000000100000000UL - (1*PAGE_SIZE)) @@ -114,26 +128,37 @@ void release_thread(struct task_struct *); #define TASK_SIZE_OF(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT) ? \ TASK_SIZE_USER32 : TASK_SIZE_USER64) #define TASK_SIZE TASK_SIZE_OF(current) - /* This decides where the kernel will search for a free chunk of vm * space during mmap's. */ #define TASK_UNMAPPED_BASE_USER32 (PAGE_ALIGN(TASK_SIZE_USER32 / 4)) -#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(TASK_SIZE_USER64 / 4)) +#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(TASK_SIZE_128TB / 4)) #define TASK_UNMAPPED_BASE ((is_32bit_task()) ? \ TASK_UNMAPPED_BASE_USER32 : TASK_UNMAPPED_BASE_USER64 ) #endif +/* + * Initial task size value for user applications. For book3s 64 we start + * 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) +#else +#define DEFAULT_MAP_WINDOW TASK_SIZE +#endif + #ifdef __powerpc64__ -#define STACK_TOP_USER64 TASK_SIZE_USER64 +/* Limit stack to 128TB */ +#define STACK_TOP_USER64 TASK_SIZE_128TB #define STACK_TOP_USER32 TASK_SIZE_USER32 #define STACK_TOP (is_32bit_task() ? \ STACK_TOP_USER32 : STACK_TOP_USER64) -#define STACK_TOP_MAX STACK_TOP_USER64 +#define STACK_TOP_MAX TASK_SIZE_USER64 #else /* __powerpc64__ */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index fc879fd..d4f653c 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -310,6 +310,7 @@ #define SPRN_PMCR 0x374 /* Power Management Control Register */ /* HFSCR and FSCR bit numbers are the same */ +#define FSCR_SCV_LG 12 /* Enable System Call Vectored */ #define FSCR_MSGP_LG 10 /* Enable MSGP */ #define FSCR_TAR_LG 8 /* Enable Target Address Register */ #define FSCR_EBB_LG 7 /* Enable Event Based Branching */ @@ -320,6 +321,7 @@ #define FSCR_VECVSX_LG 1 /* Enable VMX/VSX */ #define FSCR_FP_LG 0 /* Enable Floating Point */ #define SPRN_FSCR 0x099 /* Facility Status & Control Register */ +#define FSCR_SCV __MASK(FSCR_SCV_LG) #define FSCR_TAR __MASK(FSCR_TAR_LG) #define FSCR_EBB __MASK(FSCR_EBB_LG) #define FSCR_DSCR __MASK(FSCR_DSCR_LG) @@ -365,6 +367,7 @@ #define LPCR_MER_SH 11 #define LPCR_GTSE ASM_CONST(0x0000000000000400) /* Guest Translation Shootdown Enable */ #define LPCR_TC ASM_CONST(0x0000000000000200) /* Translation control */ +#define LPCR_HEIC ASM_CONST(0x0000000000000010) /* Hypervisor External Interrupt Control */ #define LPCR_LPES 0x0000000c #define LPCR_LPES0 ASM_CONST(0x0000000000000008) /* LPAR Env selector 0 */ #define LPCR_LPES1 ASM_CONST(0x0000000000000004) /* LPAR Env selector 1 */ @@ -656,6 +659,7 @@ #define SRR1_ISI_PROT 0x08000000 /* ISI: Other protection fault */ #define SRR1_WAKEMASK 0x00380000 /* reason for wakeup */ #define SRR1_WAKEMASK_P8 0x003c0000 /* reason for wakeup on POWER8 and 9 */ +#define SRR1_WAKEMCE_RESVD 0x003c0000 /* Unused/reserved value used by MCE wakeup to indicate cause to idle wakeup handler */ #define SRR1_WAKESYSERR 0x00300000 /* System error */ #define SRR1_WAKEEE 0x00200000 /* External interrupt */ #define SRR1_WAKEHVI 0x00240000 /* Hypervisor Virtualization Interrupt (P9) */ diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index 7dc006b..7902d63 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -6,6 +6,8 @@ #include <linux/uaccess.h> #include <asm-generic/sections.h> +extern char __head_end[]; + #ifdef __powerpc64__ extern char __start_interrupts[]; diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 32db16d..ebddb21 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -40,10 +40,12 @@ extern int cpu_to_chip_id(int cpu); struct smp_ops_t { void (*message_pass)(int cpu, int msg); #ifdef CONFIG_PPC_SMP_MUXED_IPI - void (*cause_ipi)(int cpu, unsigned long data); + void (*cause_ipi)(int cpu); #endif + int (*cause_nmi_ipi)(int cpu); void (*probe)(void); int (*kick_cpu)(int nr); + int (*prepare_cpu)(int nr); void (*setup_cpu)(int nr); void (*bringup_done)(void); void (*take_timebase)(void); @@ -61,7 +63,6 @@ extern void smp_generic_take_timebase(void); DECLARE_PER_CPU(unsigned int, cpu_pvr); #ifdef CONFIG_HOTPLUG_CPU -extern void migrate_irqs(void); int generic_cpu_disable(void); void generic_cpu_die(unsigned int cpu); void generic_set_cpu_dead(unsigned int cpu); @@ -112,23 +113,31 @@ extern int cpu_to_core_id(int cpu); * * Make sure this matches openpic_request_IPIs in open_pic.c, or what shows up * in /proc/interrupts will be wrong!!! --Troy */ -#define PPC_MSG_CALL_FUNCTION 0 -#define PPC_MSG_RESCHEDULE 1 +#define PPC_MSG_CALL_FUNCTION 0 +#define PPC_MSG_RESCHEDULE 1 #define PPC_MSG_TICK_BROADCAST 2 -#define PPC_MSG_DEBUGGER_BREAK 3 +#define PPC_MSG_NMI_IPI 3 /* This is only used by the powernv kernel */ #define PPC_MSG_RM_HOST_ACTION 4 +#define NMI_IPI_ALL_OTHERS -2 + +#ifdef CONFIG_NMI_IPI +extern int smp_handle_nmi_ipi(struct pt_regs *regs); +#else +static inline int smp_handle_nmi_ipi(struct pt_regs *regs) { return 0; } +#endif + /* for irq controllers that have dedicated ipis per message (4) */ extern int smp_request_message_ipi(int virq, int message); extern const char *smp_ipi_name[]; /* for irq controllers with only a single ipi */ -extern void smp_muxed_ipi_set_data(int cpu, unsigned long data); extern void smp_muxed_ipi_message_pass(int cpu, int msg); extern void smp_muxed_ipi_set_message(int cpu, int msg); extern irqreturn_t smp_ipi_demux(void); +extern irqreturn_t smp_ipi_demux_relaxed(void); void smp_init_pSeries(void); void smp_init_cell(void); diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h index 23be8f1..16fab68 100644 --- a/arch/powerpc/include/asm/syscalls.h +++ b/arch/powerpc/include/asm/syscalls.h @@ -8,10 +8,10 @@ struct rtas_args; -asmlinkage unsigned long sys_mmap(unsigned long addr, size_t len, +asmlinkage long sys_mmap(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, unsigned long fd, off_t offset); -asmlinkage unsigned long sys_mmap2(unsigned long addr, size_t len, +asmlinkage long sys_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff); asmlinkage long ppc64_personality(unsigned long personality); diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 6fc6464..a941cc6 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -10,15 +10,7 @@ #ifdef __KERNEL__ -/* We have 8k stacks on ppc32 and 16k on ppc64 */ - -#if defined(CONFIG_PPC64) -#define THREAD_SHIFT 14 -#elif defined(CONFIG_PPC_256K_PAGES) -#define THREAD_SHIFT 15 -#else -#define THREAD_SHIFT 13 -#endif +#define THREAD_SHIFT CONFIG_THREAD_SHIFT #define THREAD_SIZE (1 << THREAD_SHIFT) diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h index e0b9e57..7ce2c3a 100644 --- a/arch/powerpc/include/asm/xics.h +++ b/arch/powerpc/include/asm/xics.h @@ -57,7 +57,7 @@ struct icp_ops { void (*teardown_cpu)(void); void (*flush_ipi)(void); #ifdef CONFIG_SMP - void (*cause_ipi)(int cpu, unsigned long data); + void (*cause_ipi)(int cpu); irq_handler_t ipi_action; #endif }; diff --git a/arch/powerpc/include/asm/xive-regs.h b/arch/powerpc/include/asm/xive-regs.h new file mode 100644 index 0000000..1d3f2be --- /dev/null +++ b/arch/powerpc/include/asm/xive-regs.h @@ -0,0 +1,97 @@ +/* + * Copyright 2016,2017 IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#ifndef _ASM_POWERPC_XIVE_REGS_H +#define _ASM_POWERPC_XIVE_REGS_H + +/* + * Thread Management (aka "TM") registers + */ + +/* TM register offsets */ +#define TM_QW0_USER 0x000 /* All rings */ +#define TM_QW1_OS 0x010 /* Ring 0..2 */ +#define TM_QW2_HV_POOL 0x020 /* Ring 0..1 */ +#define TM_QW3_HV_PHYS 0x030 /* Ring 0..1 */ + +/* Byte offsets inside a QW QW0 QW1 QW2 QW3 */ +#define TM_NSR 0x0 /* + + - + */ +#define TM_CPPR 0x1 /* - + - + */ +#define TM_IPB 0x2 /* - + + + */ +#define TM_LSMFB 0x3 /* - + + + */ +#define TM_ACK_CNT 0x4 /* - + - - */ +#define TM_INC 0x5 /* - + - + */ +#define TM_AGE 0x6 /* - + - + */ +#define TM_PIPR 0x7 /* - + - + */ + +#define TM_WORD0 0x0 +#define TM_WORD1 0x4 + +/* + * QW word 2 contains the valid bit at the top and other fields + * depending on the QW. + */ +#define TM_WORD2 0x8 +#define TM_QW0W2_VU PPC_BIT32(0) +#define TM_QW0W2_LOGIC_SERV PPC_BITMASK32(1,31) // XX 2,31 ? +#define TM_QW1W2_VO PPC_BIT32(0) +#define TM_QW1W2_OS_CAM PPC_BITMASK32(8,31) +#define TM_QW2W2_VP PPC_BIT32(0) +#define TM_QW2W2_POOL_CAM PPC_BITMASK32(8,31) +#define TM_QW3W2_VT PPC_BIT32(0) +#define TM_QW3W2_LP PPC_BIT32(6) +#define TM_QW3W2_LE PPC_BIT32(7) +#define TM_QW3W2_T PPC_BIT32(31) + +/* + * In addition to normal loads to "peek" and writes (only when invalid) + * using 4 and 8 bytes accesses, the above registers support these + * "special" byte operations: + * + * - Byte load from QW0[NSR] - User level NSR (EBB) + * - Byte store to QW0[NSR] - User level NSR (EBB) + * - Byte load/store to QW1[CPPR] and QW3[CPPR] - CPPR access + * - Byte load from QW3[TM_WORD2] - Read VT||00000||LP||LE on thrd 0 + * otherwise VT||0000000 + * - Byte store to QW3[TM_WORD2] - Set VT bit (and LP/LE if present) + * + * Then we have all these "special" CI ops at these offset that trigger + * all sorts of side effects: + */ +#define TM_SPC_ACK_EBB 0x800 /* Load8 ack EBB to reg*/ +#define TM_SPC_ACK_OS_REG 0x810 /* Load16 ack OS irq to reg */ +#define TM_SPC_PUSH_USR_CTX 0x808 /* Store32 Push/Validate user context */ +#define TM_SPC_PULL_USR_CTX 0x808 /* Load32 Pull/Invalidate user context */ +#define TM_SPC_SET_OS_PENDING 0x812 /* Store8 Set OS irq pending bit */ +#define TM_SPC_PULL_OS_CTX 0x818 /* Load32/Load64 Pull/Invalidate OS context to reg */ +#define TM_SPC_PULL_POOL_CTX 0x828 /* Load32/Load64 Pull/Invalidate Pool context to reg*/ +#define TM_SPC_ACK_HV_REG 0x830 /* Load16 ack HV irq to reg */ +#define TM_SPC_PULL_USR_CTX_OL 0xc08 /* Store8 Pull/Inval usr ctx to odd line */ +#define TM_SPC_ACK_OS_EL 0xc10 /* Store8 ack OS irq to even line */ +#define TM_SPC_ACK_HV_POOL_EL 0xc20 /* Store8 ack HV evt pool to even line */ +#define TM_SPC_ACK_HV_EL 0xc30 /* Store8 ack HV irq to even line */ +/* XXX more... */ + +/* NSR fields for the various QW ack types */ +#define TM_QW0_NSR_EB PPC_BIT8(0) +#define TM_QW1_NSR_EO PPC_BIT8(0) +#define TM_QW3_NSR_HE PPC_BITMASK8(0,1) +#define TM_QW3_NSR_HE_NONE 0 +#define TM_QW3_NSR_HE_POOL 1 +#define TM_QW3_NSR_HE_PHYS 2 +#define TM_QW3_NSR_HE_LSI 3 +#define TM_QW3_NSR_I PPC_BIT8(2) +#define TM_QW3_NSR_GRP_LVL PPC_BIT8(3,7) + +/* Utilities to manipulate these (originaly from OPAL) */ +#define MASK_TO_LSH(m) (__builtin_ffsl(m) - 1) +#define GETFIELD(m, v) (((v) & (m)) >> MASK_TO_LSH(m)) +#define SETFIELD(m, v, val) \ + (((v) & ~(m)) | ((((typeof(v))(val)) << MASK_TO_LSH(m)) & (m))) + +#endif /* _ASM_POWERPC_XIVE_REGS_H */ diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h new file mode 100644 index 0000000..3cdbeae --- /dev/null +++ b/arch/powerpc/include/asm/xive.h @@ -0,0 +1,163 @@ +/* + * Copyright 2016,2017 IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#ifndef _ASM_POWERPC_XIVE_H +#define _ASM_POWERPC_XIVE_H + +#define XIVE_INVALID_VP 0xffffffff + +#ifdef CONFIG_PPC_XIVE + +/* + * Thread Interrupt Management Area (TIMA) + * + * This is a global MMIO region divided in 4 pages of varying access + * permissions, providing access to per-cpu interrupt management + * functions. It always identifies the CPU doing the access based + * on the PowerBus initiator ID, thus we always access via the + * same offset regardless of where the code is executing + */ +extern void __iomem *xive_tima; + +/* + * Offset in the TM area of our current execution level (provided by + * the backend) + */ +extern u32 xive_tima_offset; + +/* + * Per-irq data (irq_get_handler_data for normal IRQs), IPIs + * have it stored in the xive_cpu structure. We also cache + * for normal interrupts the current target CPU. + * + * This structure is setup by the backend for each interrupt. + */ +struct xive_irq_data { + u64 flags; + u64 eoi_page; + void __iomem *eoi_mmio; + u64 trig_page; + void __iomem *trig_mmio; + u32 esb_shift; + int src_chip; + + /* Setup/used by frontend */ + int target; + bool saved_p; +}; +#define XIVE_IRQ_FLAG_STORE_EOI 0x01 +#define XIVE_IRQ_FLAG_LSI 0x02 +#define XIVE_IRQ_FLAG_SHIFT_BUG 0x04 +#define XIVE_IRQ_FLAG_MASK_FW 0x08 +#define XIVE_IRQ_FLAG_EOI_FW 0x10 + +#define XIVE_INVALID_CHIP_ID -1 + +/* A queue tracking structure in a CPU */ +struct xive_q { + __be32 *qpage; + u32 msk; + u32 idx; + u32 toggle; + u64 eoi_phys; + u32 esc_irq; + atomic_t count; + atomic_t pending_count; +}; + +/* + * "magic" Event State Buffer (ESB) MMIO offsets. + * + * Each interrupt source has a 2-bit state machine called ESB + * which can be controlled by MMIO. It's made of 2 bits, P and + * Q. P indicates that an interrupt is pending (has been sent + * to a queue and is waiting for an EOI). Q indicates that the + * interrupt has been triggered while pending. + * + * This acts as a coalescing mechanism in order to guarantee + * that a given interrupt only occurs at most once in a queue. + * + * When doing an EOI, the Q bit will indicate if the interrupt + * needs to be re-triggered. + * + * The following offsets into the ESB MMIO allow to read or + * manipulate the PQ bits. They must be used with an 8-bytes + * load instruction. They all return the previous state of the + * interrupt (atomically). + * + * Additionally, some ESB pages support doing an EOI via a + * store at 0 and some ESBs support doing a trigger via a + * separate trigger page. + */ +#define XIVE_ESB_GET 0x800 +#define XIVE_ESB_SET_PQ_00 0xc00 +#define XIVE_ESB_SET_PQ_01 0xd00 +#define XIVE_ESB_SET_PQ_10 0xe00 +#define XIVE_ESB_SET_PQ_11 0xf00 +#define XIVE_ESB_MASK XIVE_ESB_SET_PQ_01 + +#define XIVE_ESB_VAL_P 0x2 +#define XIVE_ESB_VAL_Q 0x1 + +/* Global enable flags for the XIVE support */ +extern bool __xive_enabled; + +static inline bool xive_enabled(void) { return __xive_enabled; } + +extern bool xive_native_init(void); +extern void xive_smp_probe(void); +extern int xive_smp_prepare_cpu(unsigned int cpu); +extern void xive_smp_setup_cpu(void); +extern void xive_smp_disable_cpu(void); +extern void xive_kexec_teardown_cpu(int secondary); +extern void xive_shutdown(void); +extern void xive_flush_interrupt(void); + +/* xmon hook */ +extern void xmon_xive_do_dump(int cpu); + +/* APIs used by KVM */ +extern u32 xive_native_default_eq_shift(void); +extern u32 xive_native_alloc_vp_block(u32 max_vcpus); +extern void xive_native_free_vp_block(u32 vp_base); +extern int xive_native_populate_irq_data(u32 hw_irq, + struct xive_irq_data *data); +extern void xive_cleanup_irq_data(struct xive_irq_data *xd); +extern u32 xive_native_alloc_irq(void); +extern void xive_native_free_irq(u32 irq); +extern int xive_native_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq); + +extern int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio, + __be32 *qpage, u32 order, bool can_escalate); +extern void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio); + +extern bool __xive_irq_trigger(struct xive_irq_data *xd); +extern bool __xive_irq_retrigger(struct xive_irq_data *xd); +extern void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd); + +extern bool is_xive_irq(struct irq_chip *chip); + +#else + +static inline bool xive_enabled(void) { return false; } + +static inline bool xive_native_init(void) { return false; } +static inline void xive_smp_probe(void) { } +extern inline int xive_smp_prepare_cpu(unsigned int cpu) { return -EINVAL; } +static inline void xive_smp_setup_cpu(void) { } +static inline void xive_smp_disable_cpu(void) { } +static inline void xive_kexec_teardown_cpu(int secondary) { } +static inline void xive_shutdown(void) { } +static inline void xive_flush_interrupt(void) { } + +static inline u32 xive_native_alloc_vp_block(u32 max_vcpus) { return XIVE_INVALID_VP; } +static inline void xive_native_free_vp_block(u32 vp_base) { } + +#endif + +#endif /* _ASM_POWERPC_XIVE_H */ diff --git a/arch/powerpc/include/asm/xmon.h b/arch/powerpc/include/asm/xmon.h index 5eb8e59..eb42a0c 100644 --- a/arch/powerpc/include/asm/xmon.h +++ b/arch/powerpc/include/asm/xmon.h @@ -29,5 +29,7 @@ static inline void xmon_register_spus(struct list_head *list) { }; extern int cpus_are_in_xmon(void); #endif +extern void xmon_printf(const char *format, ...); + #endif /* __KERNEL __ */ #endif /* __ASM_POWERPC_XMON_H */ diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h index 03c06ba..ab45cc2 100644 --- a/arch/powerpc/include/uapi/asm/mman.h +++ b/arch/powerpc/include/uapi/asm/mman.h @@ -29,4 +29,20 @@ #define MAP_STACK 0x20000 /* give out an address that is best suited for process/thread stacks */ #define MAP_HUGETLB 0x40000 /* create a huge page mapping */ +/* + * When MAP_HUGETLB is set, bits [26:31] of the flags argument to mmap(2), + * encode the log2 of the huge page size. A value of zero indicates that the + * default huge page size should be used. To use a non-default huge page size, + * one of these defines can be used, or the size can be encoded by hand. Note + * that on most systems only a subset, or possibly none, of these sizes will be + * available. + */ +#define MAP_HUGE_512KB (19 << MAP_HUGE_SHIFT) /* 512KB HugeTLB Page */ +#define MAP_HUGE_1MB (20 << MAP_HUGE_SHIFT) /* 1MB HugeTLB Page */ +#define MAP_HUGE_2MB (21 << MAP_HUGE_SHIFT) /* 2MB HugeTLB Page */ +#define MAP_HUGE_8MB (23 << MAP_HUGE_SHIFT) /* 8MB HugeTLB Page */ +#define MAP_HUGE_16MB (24 << MAP_HUGE_SHIFT) /* 16MB HugeTLB Page */ +#define MAP_HUGE_1GB (30 << MAP_HUGE_SHIFT) /* 1GB HugeTLB Page */ +#define MAP_HUGE_16GB (34 << MAP_HUGE_SHIFT) /* 16GB HugeTLB Page */ + #endif /* _UAPI_ASM_POWERPC_MMAN_H */ |
