From 9859f0c7e05b424a7a42032e639a8c44dd537328 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 14 Dec 2016 10:09:45 +0530 Subject: powerpc/mm: Remove the debug hugepd_ok check We don't do this for other page table entries. So lets keep this simple and always return false for hugepd check on a 64K page size config. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/pgtable-64k.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h index 0d2845b44763..198aff33c380 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h @@ -35,10 +35,6 @@ static inline int pgd_huge(pgd_t pgd) } #define pgd_huge pgd_huge -#ifdef CONFIG_DEBUG_VM -extern int hugepd_ok(hugepd_t hpd); -#define is_hugepd(hpd) (hugepd_ok(hpd)) -#else /* * With 64k page size, we have hugepage ptes in the pgd and pmd entries. We don't * need to setup hugepage directory for them. Our pte and page directory format @@ -49,7 +45,6 @@ static inline int hugepd_ok(hugepd_t hpd) return 0; } #define is_hugepd(pdep) 0 -#endif /* CONFIG_DEBUG_VM */ #endif /* CONFIG_HUGETLB_PAGE */ -- cgit v1.2.3 From 8ad43336b5c1ad9ac945148cb5e26a1200ccd45c Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 4 Jan 2017 08:19:12 +0530 Subject: powerpc/mm/4k: don't allocate larger pmd page table for 4k We now support THP with both 64k and 4K page size configuration for radix. (hash only support THP with 64K page size). Hence we will have CONFIG_TRANSPARENT_HUGEPAGE enabled for both PPC_64K and PPC_4K config. Since we only need large pmd page table with hash configuration (to store the slot information in the second half of the table) restrict the large pmd page table to THP and 64K configs. Signed-off-by: Aneesh Kumar K.V Reviewed-by: Anshuman Khandual Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/hash.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index 4c935f7504f7..f7b721bbf918 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -33,9 +33,9 @@ H_PUD_INDEX_SIZE + H_PGD_INDEX_SIZE + PAGE_SHIFT) #define H_PGTABLE_RANGE (ASM_CONST(1) << H_PGTABLE_EADDR_SIZE) -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_PPC_64K_PAGES) /* - * only with hash we need to use the second half of pmd page table + * only with hash 64k we need to use the second half of pmd page table * to store pointer to deposited pgtable_t */ #define H_PMD_CACHE_INDEX (H_PMD_INDEX_SIZE + 1) -- cgit v1.2.3 From b492f7e4e07a28e706db26cf4943bb0911435426 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Thu, 3 Nov 2016 16:10:55 +1100 Subject: powerpc/64: Fix checksum folding in csum_tcpudp_nofold and ip_fast_csum_nofold These functions compute an IP checksum by computing a 64-bit sum and folding it to 32 bits (the "nofold" in their names refers to folding down to 16 bits). However, doing (u32) (s + (s >> 32)) is not sufficient to fold a 64-bit sum to 32 bits correctly. The addition can produce a carry out from bit 31, which needs to be added in to the sum to produce the correct result. To fix this, we copy the from64to32() function from lib/checksum.c and use that. Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/checksum.h | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h index 1e8fceb308a5..5b1a6e39afa7 100644 --- a/arch/powerpc/include/asm/checksum.h +++ b/arch/powerpc/include/asm/checksum.h @@ -53,17 +53,25 @@ static inline __sum16 csum_fold(__wsum sum) return (__force __sum16)(~((__force u32)sum + tmp) >> 16); } +static inline u32 from64to32(u64 x) +{ + /* add up 32-bit and 32-bit for 32+c bit */ + x = (x & 0xffffffff) + (x >> 32); + /* add up carry.. */ + x = (x & 0xffffffff) + (x >> 32); + return (u32)x; +} + static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __wsum sum) { #ifdef __powerpc64__ - unsigned long s = (__force u32)sum; + u64 s = (__force u32)sum; s += (__force u32)saddr; s += (__force u32)daddr; s += proto + len; - s += (s >> 32); - return (__force __wsum) s; + return (__force __wsum) from64to32(s); #else __asm__("\n\ addc %0,%0,%1 \n\ @@ -123,8 +131,7 @@ static inline __wsum ip_fast_csum_nofold(const void *iph, unsigned int ihl) for (i = 0; i < ihl - 1; i++, ptr++) s += *ptr; - s += (s >> 32); - return (__force __wsum)s; + return (__force __wsum)from64to32(s); #else __wsum sum, tmp; -- cgit v1.2.3 From d4fde568a34a93897dfb9ae64cfe9dda9d5c908c Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Thu, 3 Nov 2016 16:15:42 +1100 Subject: powerpc/64: Use optimized checksum routines on little-endian Currently we have optimized hand-coded assembly checksum routines for big-endian 64-bit systems, but for little-endian we use the generic C routines. This modifies the optimized routines to work for little-endian. With this, we no longer need to enable CONFIG_GENERIC_CSUM. This also fixes a couple of comments in checksum_64.S so they accurately reflect what the associated instruction does. Signed-off-by: Paul Mackerras [mpe: Use the more common __BIG_ENDIAN__] Signed-off-by: Michael Ellerman --- arch/powerpc/Kconfig | 2 +- arch/powerpc/include/asm/checksum.h | 4 ++++ arch/powerpc/lib/Makefile | 2 -- arch/powerpc/lib/checksum_64.S | 12 ++++++++++-- 4 files changed, 15 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index a8ee573fe610..e022859340b7 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -167,7 +167,7 @@ config PPC select HAVE_CC_STACKPROTECTOR config GENERIC_CSUM - def_bool CPU_LITTLE_ENDIAN + def_bool n config EARLY_PRINTK bool diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h index 5b1a6e39afa7..4e63787dc3be 100644 --- a/arch/powerpc/include/asm/checksum.h +++ b/arch/powerpc/include/asm/checksum.h @@ -70,7 +70,11 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, s += (__force u32)saddr; s += (__force u32)daddr; +#ifdef __BIG_ENDIAN__ s += proto + len; +#else + s += (proto + len) << 8; +#endif return (__force __wsum) from64to32(s); #else __asm__("\n\ diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 309361e86523..0e649d72fe8d 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -21,9 +21,7 @@ obj64-y += copypage_64.o copyuser_64.o usercopy_64.o mem_64.o hweight_64.o \ obj64-$(CONFIG_SMP) += locks.o obj64-$(CONFIG_ALTIVEC) += vmx-helper.o -ifeq ($(CONFIG_GENERIC_CSUM),) obj-y += checksum_$(BITS).o checksum_wrappers.o -endif obj-$(CONFIG_PPC_EMULATE_SSTEP) += sstep.o ldstfp.o diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S index d0d311e108ff..d7f1a966136e 100644 --- a/arch/powerpc/lib/checksum_64.S +++ b/arch/powerpc/lib/checksum_64.S @@ -36,7 +36,7 @@ _GLOBAL(__csum_partial) * work to calculate the correct checksum, we ignore that case * and take the potential slowdown of unaligned loads. */ - rldicl. r6,r3,64-1,64-2 /* r6 = (r3 & 0x3) >> 1 */ + rldicl. r6,r3,64-1,64-2 /* r6 = (r3 >> 1) & 0x3 */ beq .Lcsum_aligned li r7,4 @@ -168,8 +168,12 @@ _GLOBAL(__csum_partial) beq .Lcsum_finish lbz r6,0(r3) +#ifdef __BIG_ENDIAN__ sldi r9,r6,8 /* Pad the byte out to 16 bits */ adde r0,r0,r9 +#else + adde r0,r0,r6 +#endif .Lcsum_finish: addze r0,r0 /* add in final carry */ @@ -224,7 +228,7 @@ _GLOBAL(csum_partial_copy_generic) * If the source and destination are relatively unaligned we only * align the source. This keeps things simple. */ - rldicl. r6,r3,64-1,64-2 /* r6 = (r3 & 0x3) >> 1 */ + rldicl. r6,r3,64-1,64-2 /* r6 = (r3 >> 1) & 0x3 */ beq .Lcopy_aligned li r9,4 @@ -386,8 +390,12 @@ dstnr; sth r6,0(r4) beq .Lcopy_finish srcnr; lbz r6,0(r3) +#ifdef __BIG_ENDIAN__ sldi r9,r6,8 /* Pad the byte out to 16 bits */ adde r0,r0,r9 +#else + adde r0,r0,r6 +#endif dstnr; stb r6,0(r4) .Lcopy_finish: -- cgit v1.2.3 From 4ab2537c4204b976e4ca350bbdc193b4649cad28 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 8 Dec 2016 09:12:13 +0530 Subject: powerpc/mm: Fixup wrong LPCR_VRMASD value In commit a4b349540a26af ("powerpc/mm: Cleanup LPCR defines") we updated LPCR_VRMASD wrongly as below. -#define LPCR_VRMASD (0x1ful << (63-16)) +#define LPCR_VRMASD_SH 47 +#define LPCR_VRMASD (ASM_CONST(1) << LPCR_VRMASD_SH) We initialize the VRMA bits in LPCR to 0x00 in kvm. Hence using a different mask value as above while updating lpcr should not have any impact. This patch updates it to the correct value. Fixes: a4b349540a26 ("powerpc/mm: Cleanup LPCR defines") Reported-by: Ram Pai Signed-off-by: Aneesh Kumar K.V Signed-off-by: Jia He Acked-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/reg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 0d4531aa2052..818c4e878e60 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -338,7 +338,7 @@ #define LPCR_DPFD_SH 52 #define LPCR_DPFD (ASM_CONST(7) << LPCR_DPFD_SH) #define LPCR_VRMASD_SH 47 -#define LPCR_VRMASD (ASM_CONST(1) << LPCR_VRMASD_SH) +#define LPCR_VRMASD (ASM_CONST(0x1f) << LPCR_VRMASD_SH) #define LPCR_VRMA_L ASM_CONST(0x0008000000000000) #define LPCR_VRMA_LP0 ASM_CONST(0x0001000000000000) #define LPCR_VRMA_LP1 ASM_CONST(0x0000800000000000) -- cgit v1.2.3 From d3918e7fd4a27564f93ec46d0359a9739c5deb8d Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 22 Dec 2016 04:29:25 +1000 Subject: KVM: PPC: Book3S: Change interrupt call to reduce scratch space use on HV Change the calling convention to put the trap number together with CR in two halves of r12, which frees up HSTATE_SCRATCH2 in the HV handler. The 64-bit PR handler entry translates the calling convention back to match the previous call convention (i.e., shared with 32-bit), for simplicity. Signed-off-by: Nicholas Piggin Acked-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/exception-64s.h | 24 +++++++++++------------- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 16 +++++++++------- arch/powerpc/kvm/book3s_segment.S | 25 ++++++++++++++++++------- 3 files changed, 38 insertions(+), 27 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 9a3eee661297..a02a268bde6b 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -233,7 +233,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) #endif -#define __KVM_HANDLER_PROLOG(area, n) \ +#define __KVM_HANDLER(area, h, n) \ BEGIN_FTR_SECTION_NESTED(947) \ ld r10,area+EX_CFAR(r13); \ std r10,HSTATE_CFAR(r13); \ @@ -243,30 +243,28 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) std r10,HSTATE_PPR(r13); \ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948); \ ld r10,area+EX_R10(r13); \ - stw r9,HSTATE_SCRATCH1(r13); \ - ld r9,area+EX_R9(r13); \ std r12,HSTATE_SCRATCH0(r13); \ - -#define __KVM_HANDLER(area, h, n) \ - __KVM_HANDLER_PROLOG(area, n) \ - li r12,n; \ + sldi r12,r9,32; \ + ori r12,r12,(n); \ + ld r9,area+EX_R9(r13); \ b kvmppc_interrupt #define __KVM_HANDLER_SKIP(area, h, n) \ cmpwi r10,KVM_GUEST_MODE_SKIP; \ - ld r10,area+EX_R10(r13); \ beq 89f; \ - stw r9,HSTATE_SCRATCH1(r13); \ BEGIN_FTR_SECTION_NESTED(948) \ - ld r9,area+EX_PPR(r13); \ - std r9,HSTATE_PPR(r13); \ + ld r10,area+EX_PPR(r13); \ + std r10,HSTATE_PPR(r13); \ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948); \ - ld r9,area+EX_R9(r13); \ + ld r10,area+EX_R10(r13); \ std r12,HSTATE_SCRATCH0(r13); \ - li r12,n; \ + sldi r12,r9,32; \ + ori r12,r12,(n); \ + ld r9,area+EX_R9(r13); \ b kvmppc_interrupt; \ 89: mtocrf 0x80,r9; \ ld r9,area+EX_R9(r13); \ + ld r10,area+EX_R10(r13); \ b kvmppc_skip_##h##interrupt #ifdef CONFIG_KVM_BOOK3S_64_HANDLER diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 9338a818e05c..11882aac8216 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1057,19 +1057,18 @@ hdec_soon: kvmppc_interrupt_hv: /* * Register contents: - * R12 = interrupt vector + * R12 = (guest CR << 32) | interrupt vector * R13 = PACA - * guest CR, R12 saved in shadow VCPU SCRATCH1/0 + * guest R12 saved in shadow VCPU SCRATCH0 * guest R13 saved in SPRN_SCRATCH0 */ - std r9, HSTATE_SCRATCH2(r13) - + std r9, HSTATE_SCRATCH1(r13) lbz r9, HSTATE_IN_GUEST(r13) cmpwi r9, KVM_GUEST_MODE_HOST_HV beq kvmppc_bad_host_intr #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE cmpwi r9, KVM_GUEST_MODE_GUEST - ld r9, HSTATE_SCRATCH2(r13) + ld r9, HSTATE_SCRATCH1(r13) beq kvmppc_interrupt_pr #endif /* We're now back in the host but in guest MMU context */ @@ -1089,13 +1088,14 @@ kvmppc_interrupt_hv: std r6, VCPU_GPR(R6)(r9) std r7, VCPU_GPR(R7)(r9) std r8, VCPU_GPR(R8)(r9) - ld r0, HSTATE_SCRATCH2(r13) + ld r0, HSTATE_SCRATCH1(r13) std r0, VCPU_GPR(R9)(r9) std r10, VCPU_GPR(R10)(r9) std r11, VCPU_GPR(R11)(r9) ld r3, HSTATE_SCRATCH0(r13) - lwz r4, HSTATE_SCRATCH1(r13) std r3, VCPU_GPR(R12)(r9) + /* CR is in the high half of r12 */ + srdi r4, r12, 32 stw r4, VCPU_CR(r9) BEGIN_FTR_SECTION ld r3, HSTATE_CFAR(r13) @@ -1114,6 +1114,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) mfspr r11, SPRN_SRR1 std r10, VCPU_SRR0(r9) std r11, VCPU_SRR1(r9) + /* trap is in the low half of r12, clear CR from the high half */ + clrldi r12, r12, 32 andi. r0, r12, 2 /* need to read HSRR0/1? */ beq 1f mfspr r10, SPRN_HSRR0 diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S index ca8f174289bb..68e45080cf93 100644 --- a/arch/powerpc/kvm/book3s_segment.S +++ b/arch/powerpc/kvm/book3s_segment.S @@ -167,20 +167,31 @@ kvmppc_handler_trampoline_enter_end: * * *****************************************************************************/ -.global kvmppc_handler_trampoline_exit -kvmppc_handler_trampoline_exit: - .global kvmppc_interrupt_pr kvmppc_interrupt_pr: + /* 64-bit entry. Register usage at this point: + * + * SPRG_SCRATCH0 = guest R13 + * R12 = (guest CR << 32) | exit handler id + * R13 = PACA + * HSTATE.SCRATCH0 = guest R12 + */ +#ifdef CONFIG_PPC64 + /* Match 32-bit entry */ + rotldi r12, r12, 32 /* Flip R12 halves for stw */ + stw r12, HSTATE_SCRATCH1(r13) /* CR is now in the low half */ + srdi r12, r12, 32 /* shift trap into low half */ +#endif +.global kvmppc_handler_trampoline_exit +kvmppc_handler_trampoline_exit: /* Register usage at this point: * - * SPRG_SCRATCH0 = guest R13 - * R12 = exit handler id - * R13 = shadow vcpu (32-bit) or PACA (64-bit) + * SPRG_SCRATCH0 = guest R13 + * R12 = exit handler id + * R13 = shadow vcpu (32-bit) or PACA (64-bit) * HSTATE.SCRATCH0 = guest R12 * HSTATE.SCRATCH1 = guest CR - * */ /* Save registers */ -- cgit v1.2.3 From 7ede531773ea69fa56b02a873ed83ce3507eb8d5 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 22 Dec 2016 04:29:26 +1000 Subject: KVM: PPC: Book3S: Move 64-bit KVM interrupt handler out from alt section A subsequent patch to make KVM handlers relocation-safe makes them unusable from within alt section "else" cases (due to the way fixed addresses are taken from within fixed section head code). Stop open-coding the KVM handlers, and add them both as normal. A more optimal fix may be to allow some level of alternate feature patching in the exception macros themselves, but for now this will do. The TRAMP_KVM handlers must be moved to the "virt" fixed section area (name is arbitrary) in order to be closer to .text and avoid the dreaded "relocation truncated to fit" error. Signed-off-by: Nicholas Piggin Acked-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/head-64.h | 2 +- arch/powerpc/kernel/exceptions-64s.S | 6 ++---- 2 files changed, 3 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h index fca7033839a9..9bd81619d090 100644 --- a/arch/powerpc/include/asm/head-64.h +++ b/arch/powerpc/include/asm/head-64.h @@ -218,7 +218,7 @@ name: #ifdef CONFIG_KVM_BOOK3S_64_HANDLER #define TRAMP_KVM_BEGIN(name) \ - TRAMP_REAL_BEGIN(name) + TRAMP_VIRT_BEGIN(name) #else #define TRAMP_KVM_BEGIN(name) #endif diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index d39d6118c6e9..89b4f122aec6 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -717,13 +717,9 @@ hardware_interrupt_hv: BEGIN_FTR_SECTION _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, EXC_HV, SOFTEN_TEST_HV) -do_kvm_H0x500: - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x502) FTR_SECTION_ELSE _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, EXC_STD, SOFTEN_TEST_PR) -do_kvm_0x500: - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500) ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) EXC_REAL_END(hardware_interrupt, 0x500, 0x600) @@ -737,6 +733,8 @@ hardware_interrupt_relon_hv: ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) EXC_VIRT_END(hardware_interrupt, 0x4500, 0x4600) +TRAMP_KVM(PACA_EXGEN, 0x500) +TRAMP_KVM_HV(PACA_EXGEN, 0x500) EXC_COMMON_ASYNC(hardware_interrupt_common, 0x500, do_IRQ) -- cgit v1.2.3 From 79270e0a3fd124388a0407f9edbd6ace75eacb69 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Sat, 28 Jan 2017 21:18:40 +0530 Subject: powerpc/mm/hash: Properly mask the ESID bits when building proto VSID The proto VSID is built using both the MMU context id and effective segment ID (ESID). We should not have overlapping bits between those. That could result in us having a VSID collision. With the current code we missed masking the top bits of the ESID. This implies for kernel address we ended up using the top 4 bits of the ESID as part of the proto VSID, which is wrong. The current code use the top 4 context values (0x7fffc - 0x7ffff) for the kernel. With those context IDs used for the kernel, we don't run into VSID collisions because we get the same proto VSID irrespective of whether we mask the ESID bits or not. eg: ea = 0xf000000000000000 context = 0x7ffff w/out masking: proto_vsid = (0x7ffff << 6 | 0xf000000000000000 >> 40) = (0x1ffffc0 | 0xf00000) = 0x1ffffc0 with masking: proto_vsid = (0x7ffff << 6 | ((0xf000000000000000 >> 40) & 0x3f)) = (0x1ffffc0 | (0xf00000 & 0x3f)) = 0x1ffffc0 | 0) = 0x1ffffc0 So although there is no bug, the code is still overly subtle, so fix it to save ourselves pain in future. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/mmu-hash.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 2e6a823fa502..823015cff149 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -525,6 +525,9 @@ extern void slb_set_size(u16 size); #define ESID_BITS 18 #define ESID_BITS_1T 6 +#define ESID_BITS_MASK ((1 << ESID_BITS) - 1) +#define ESID_BITS_1T_MASK ((1 << ESID_BITS_1T) - 1) + /* * 256MB segment * The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments @@ -660,9 +663,9 @@ static inline unsigned long get_vsid(unsigned long context, unsigned long ea, if (ssize == MMU_SEGSIZE_256M) return vsid_scramble((context << ESID_BITS) - | (ea >> SID_SHIFT), 256M); + | ((ea >> SID_SHIFT) & ESID_BITS_MASK), 256M); return vsid_scramble((context << ESID_BITS_1T) - | (ea >> SID_SHIFT_1T), 1T); + | ((ea >> SID_SHIFT_1T) & ESID_BITS_1T_MASK), 1T); } /* -- cgit v1.2.3 From 1d0761d2557d1540727723e4f05395d53321d555 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 14 Dec 2016 13:36:51 +1100 Subject: powerpc/powernv: Initialise nest mmu POWER9 contains an off core mmu called the nest mmu (NMMU). This is used by other hardware units on the chip to translate virtual addresses into real addresses. The unit attempting an address translation provides the majority of the context required for the translation request except for the base address of the partition table (ie. the PTCR) which needs to be programmed into the NMMU. This patch adds a call to OPAL to set the PTCR for the nest mmu in opal_init(). Signed-off-by: Alistair Popple Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/opal-api.h | 3 ++- arch/powerpc/include/asm/opal.h | 1 + arch/powerpc/include/asm/powernv.h | 19 +++++++++++++++++++ arch/powerpc/mm/pgtable-radix.c | 2 ++ arch/powerpc/mm/pgtable_64.c | 6 +++++- arch/powerpc/platforms/powernv/opal-wrappers.S | 1 + arch/powerpc/platforms/powernv/opal.c | 11 +++++++++++ 7 files changed, 41 insertions(+), 2 deletions(-) create mode 100644 arch/powerpc/include/asm/powernv.h (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index 0e2e57bcab50..a0aa285869b5 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -167,7 +167,8 @@ #define OPAL_INT_EOI 124 #define OPAL_INT_SET_MFRR 125 #define OPAL_PCI_TCE_KILL 126 -#define OPAL_LAST 126 +#define OPAL_NMMU_SET_PTCR 127 +#define OPAL_LAST 127 /* Device tree flags */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 5c7db0f1a708..08ddea966601 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -232,6 +232,7 @@ int64_t opal_pci_tce_kill(uint64_t phb_id, uint32_t kill_type, int64_t opal_rm_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); /* Internal functions */ extern int early_init_dt_scan_opal(unsigned long node, const char *uname, diff --git a/arch/powerpc/include/asm/powernv.h b/arch/powerpc/include/asm/powernv.h new file mode 100644 index 000000000000..0e9c2402dd20 --- /dev/null +++ b/arch/powerpc/include/asm/powernv.h @@ -0,0 +1,19 @@ +/* + * Copyright 2017 IBM Corp. + * + * 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_POWERNV_H +#define _ASM_POWERNV_H + +#ifdef CONFIG_PPC_POWERNV +extern void powernv_set_nmmu_ptcr(unsigned long ptcr); +#else +static inline void powernv_set_nmmu_ptcr(unsigned long ptcr) { } +#endif + +#endif /* _ASM_POWERNV_H */ diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index cfa53ccc8baf..086522b7c60f 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -18,6 +18,7 @@ #include #include #include +#include #include @@ -438,6 +439,7 @@ void radix__mmu_cleanup_all(void) lpcr = mfspr(SPRN_LPCR); mtspr(SPRN_LPCR, lpcr & ~LPCR_UPRT); mtspr(SPRN_PTCR, 0); + powernv_set_nmmu_ptcr(0); radix__flush_tlb_all(); } } diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 8bca7f58afc4..4ee9c9d18760 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -52,6 +52,7 @@ #include #include #include +#include #include "mmu_decl.h" @@ -436,6 +437,7 @@ void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) void __init mmu_partition_table_init(void) { unsigned long patb_size = 1UL << PATB_SIZE_SHIFT; + unsigned long ptcr; BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 36), "Partition table size too large."); partition_tb = __va(memblock_alloc_base(patb_size, patb_size, @@ -448,7 +450,9 @@ void __init mmu_partition_table_init(void) * update partition table control register, * 64 K size. */ - mtspr(SPRN_PTCR, __pa(partition_tb) | (PATB_SIZE_SHIFT - 12)); + ptcr = __pa(partition_tb) | (PATB_SIZE_SHIFT - 12); + mtspr(SPRN_PTCR, ptcr); + powernv_set_nmmu_ptcr(ptcr); } void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0, diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 3aa40f1b20f5..f7c19c9c57ed 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -311,4 +311,5 @@ OPAL_CALL_REAL(opal_rm_int_eoi, OPAL_INT_EOI); OPAL_CALL(opal_int_set_mfrr, OPAL_INT_SET_MFRR); OPAL_CALL_REAL(opal_rm_int_set_mfrr, OPAL_INT_SET_MFRR); OPAL_CALL(opal_pci_tce_kill, OPAL_PCI_TCE_KILL); +OPAL_CALL(opal_nmmu_set_ptcr, OPAL_NMMU_SET_PTCR); OPAL_CALL_REAL(opal_rm_pci_tce_kill, OPAL_PCI_TCE_KILL); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 282293572dc8..86d9fde93c17 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -875,6 +875,17 @@ int opal_error_code(int rc) } } +void powernv_set_nmmu_ptcr(unsigned long ptcr) +{ + int rc; + + if (firmware_has_feature(FW_FEATURE_OPAL)) { + rc = opal_nmmu_set_ptcr(-1UL, ptcr); + if (rc != OPAL_SUCCESS && rc != OPAL_UNSUPPORTED) + pr_warn("%s: Unable to set nest mmu ptcr\n", __func__); + } +} + EXPORT_SYMBOL_GPL(opal_poll_events); EXPORT_SYMBOL_GPL(opal_rtc_read); EXPORT_SYMBOL_GPL(opal_rtc_write); -- cgit v1.2.3 From 823b7bd5156a93872d9561b3f033dfe5cb80204e Mon Sep 17 00:00:00 2001 From: "Gautham R. Shenoy" Date: Wed, 25 Jan 2017 14:06:25 +0530 Subject: powernv:idle: Add IDLE_STATE_ENTER_SEQ_NORET macro Currently all the low-power idle states are expected to wake up at reset vector 0x100. Which is why the macro IDLE_STATE_ENTER_SEQ that puts the CPU to an idle state and never returns. On ISA v3.0, when the ESL and EC bits in the PSSCR are zero, the CPU is expected to wake up at the next instruction of the idle instruction. This patch adds a new macro named IDLE_STATE_ENTER_SEQ_NORET for the no-return variant and reuses the name IDLE_STATE_ENTER_SEQ for a variant that allows resuming operation at the instruction next to the idle-instruction. Acked-by: Balbir Singh Signed-off-by: Gautham R. Shenoy Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/cpuidle.h | 5 ++++- arch/powerpc/kernel/exceptions-64s.S | 6 +++--- arch/powerpc/kernel/idle_book3s.S | 10 +++++----- 3 files changed, 12 insertions(+), 9 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h index 3919332965af..0a3255b12587 100644 --- a/arch/powerpc/include/asm/cpuidle.h +++ b/arch/powerpc/include/asm/cpuidle.h @@ -21,7 +21,7 @@ extern u64 pnv_first_deep_stop_state; /* Idle state entry routines */ #ifdef CONFIG_PPC_P7_NAP -#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \ +#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \ /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \ std r0,0(r1); \ ptesync; \ @@ -29,6 +29,9 @@ extern u64 pnv_first_deep_stop_state; 1: cmpd cr0,r0,r0; \ bne 1b; \ IDLE_INST; \ + +#define IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST) \ + IDLE_STATE_ENTER_SEQ(IDLE_INST) \ b . #endif /* CONFIG_PPC_P7_NAP */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index d39d6118c6e9..069aac8af909 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -381,12 +381,12 @@ EXC_COMMON_BEGIN(machine_check_handle_early) lbz r3,PACA_THREAD_IDLE_STATE(r13) cmpwi r3,PNV_THREAD_NAP bgt 10f - IDLE_STATE_ENTER_SEQ(PPC_NAP) + IDLE_STATE_ENTER_SEQ_NORET(PPC_NAP) /* No return */ 10: cmpwi r3,PNV_THREAD_SLEEP bgt 2f - IDLE_STATE_ENTER_SEQ(PPC_SLEEP) + IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP) /* No return */ 2: @@ -400,7 +400,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early) */ ori r13,r13,1 SET_PACA(r13) - IDLE_STATE_ENTER_SEQ(PPC_WINKLE) + IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE) /* No return */ 4: #endif diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 72dac0b58061..be90e2f62bba 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -205,7 +205,7 @@ pnv_enter_arch207_idle_mode: stb r3,PACA_THREAD_IDLE_STATE(r13) cmpwi cr3,r3,PNV_THREAD_SLEEP bge cr3,2f - IDLE_STATE_ENTER_SEQ(PPC_NAP) + IDLE_STATE_ENTER_SEQ_NORET(PPC_NAP) /* No return */ 2: /* Sleep or winkle */ @@ -239,7 +239,7 @@ pnv_fastsleep_workaround_at_entry: common_enter: /* common code for all the threads entering sleep or winkle */ bgt cr3,enter_winkle - IDLE_STATE_ENTER_SEQ(PPC_SLEEP) + IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP) fastsleep_workaround_at_entry: ori r15,r15,PNV_CORE_IDLE_LOCK_BIT @@ -261,7 +261,7 @@ fastsleep_workaround_at_entry: enter_winkle: bl save_sprs_to_stack - IDLE_STATE_ENTER_SEQ(PPC_WINKLE) + IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE) /* * r3 - requested stop state @@ -280,7 +280,7 @@ power_enter_stop: ld r4,ADDROFF(pnv_first_deep_stop_state)(r5) cmpd r3,r4 bge 2f - IDLE_STATE_ENTER_SEQ(PPC_STOP) + IDLE_STATE_ENTER_SEQ_NORET(PPC_STOP) 2: /* * Entering deep idle state. @@ -302,7 +302,7 @@ lwarx_loop_stop: bl save_sprs_to_stack - IDLE_STATE_ENTER_SEQ(PPC_STOP) + IDLE_STATE_ENTER_SEQ_NORET(PPC_STOP) _GLOBAL(power7_idle) /* Now check if user or arch enabled NAP mode */ -- cgit v1.2.3 From 09206b600c76f20984e80d99f3b5343c79332a97 Mon Sep 17 00:00:00 2001 From: "Gautham R. Shenoy" Date: Wed, 25 Jan 2017 14:06:28 +0530 Subject: powernv: Pass PSSCR value and mask to power9_idle_stop The power9_idle_stop method currently takes only the requested stop level as a parameter and picks up the rest of the PSSCR bits from a hand-coded macro. This is not a very flexible design, especially when the firmware has the capability to communicate the psscr value and the mask associated with a particular stop state via device tree. This patch modifies the power9_idle_stop API to take as parameters the PSSCR value and the PSSCR mask corresponding to the stop state that needs to be set. These PSSCR value and mask are respectively obtained by parsing the "ibm,cpu-idle-state-psscr" and "ibm,cpu-idle-state-psscr-mask" fields from the device tree. In addition to this, the patch adds support for handling stop states for which ESL and EC bits in the PSSCR are zero. As per the architecture, a wakeup from these stop states resumes execution from the subsequent instruction as opposed to waking up at the System Vector. The older firmware sets only the Requested Level (RL) field in the psscr and psscr-mask exposed in the device tree. For older firmware where psscr-mask=0xf, this patch will set the default sane values that the set for for remaining PSSCR fields (i.e PSLL, MTL, ESL, EC, and TR). For the new firmware, the patch will validate that the invariants required by the ISA for the psscr values are maintained by the firmware. This skiboot patch that exports fully populated PSSCR values and the mask for all the stop states can be found here: https://lists.ozlabs.org/pipermail/skiboot/2016-September/004869.html [Optimize the number of instructions before entering STOP with ESL=EC=0, validate the PSSCR values provided by the firimware maintains the invariants required as per the ISA suggested by Balbir Singh] Acked-by: Balbir Singh Signed-off-by: Gautham R. Shenoy Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/cpuidle.h | 44 ++++++++++ arch/powerpc/include/asm/processor.h | 3 +- arch/powerpc/kernel/idle_book3s.S | 30 ++++--- arch/powerpc/platforms/powernv/idle.c | 138 ++++++++++++++++++++++++++++--- arch/powerpc/platforms/powernv/powernv.h | 3 +- arch/powerpc/platforms/powernv/smp.c | 14 ++-- drivers/cpuidle/cpuidle-powernv.c | 52 +++++++++--- 7 files changed, 241 insertions(+), 43 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h index 0a3255b12587..fd321eb423cb 100644 --- a/arch/powerpc/include/asm/cpuidle.h +++ b/arch/powerpc/include/asm/cpuidle.h @@ -10,11 +10,55 @@ #define PNV_CORE_IDLE_LOCK_BIT 0x100 #define PNV_CORE_IDLE_THREAD_BITS 0x0FF +/* + * ============================ NOTE ================================= + * The older firmware populates only the RL field in the psscr_val and + * sets the psscr_mask to 0xf. On such a firmware, the kernel sets the + * remaining PSSCR fields to default values as follows: + * + * - ESL and EC bits are to 1. So wakeup from any stop state will be + * at vector 0x100. + * + * - MTL and PSLL are set to the maximum allowed value as per the ISA, + * i.e. 15. + * + * - The Transition Rate, TR is set to the Maximum value 3. + */ +#define PSSCR_HV_DEFAULT_VAL (PSSCR_ESL | PSSCR_EC | \ + PSSCR_PSLL_MASK | PSSCR_TR_MASK | \ + PSSCR_MTL_MASK) + +#define PSSCR_HV_DEFAULT_MASK (PSSCR_ESL | PSSCR_EC | \ + PSSCR_PSLL_MASK | PSSCR_TR_MASK | \ + PSSCR_MTL_MASK | PSSCR_RL_MASK) +#define PSSCR_EC_SHIFT 20 +#define PSSCR_ESL_SHIFT 21 +#define GET_PSSCR_EC(x) (((x) & PSSCR_EC) >> PSSCR_EC_SHIFT) +#define GET_PSSCR_ESL(x) (((x) & PSSCR_ESL) >> PSSCR_ESL_SHIFT) +#define GET_PSSCR_RL(x) ((x) & PSSCR_RL_MASK) + +#define ERR_EC_ESL_MISMATCH -1 +#define ERR_DEEP_STATE_ESL_MISMATCH -2 + #ifndef __ASSEMBLY__ extern u32 pnv_fastsleep_workaround_at_entry[]; extern u32 pnv_fastsleep_workaround_at_exit[]; extern u64 pnv_first_deep_stop_state; + +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) +{ + switch (err) { + case ERR_EC_ESL_MISMATCH: + pr_warn("Invalid psscr 0x%016llx : ESL,EC bits unequal", + psscr_val); + break; + case ERR_DEEP_STATE_ESL_MISMATCH: + pr_warn("Invalid psscr 0x%016llx : ESL cleared for deep stop-state", + psscr_val); + } +} #endif #endif diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 1ba814436c73..21e0b52685b5 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -454,7 +454,8 @@ extern int powersave_nap; /* set if nap mode can be used in idle loop */ extern unsigned long power7_nap(int check_irq); extern unsigned long power7_sleep(void); extern unsigned long power7_winkle(void); -extern unsigned long power9_idle_stop(unsigned long stop_level); +extern unsigned long power9_idle_stop(unsigned long stop_psscr_val, + unsigned long stop_psscr_mask); extern void flush_instruction_cache(void); extern void hard_reset_now(void); diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index be90e2f62bba..4f6cf5596235 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -40,9 +40,7 @@ #define _WORC GPR11 #define _PTCR GPR12 -#define PSSCR_HV_TEMPLATE PSSCR_ESL | PSSCR_EC | \ - PSSCR_PSLL_MASK | PSSCR_TR_MASK | \ - PSSCR_MTL_MASK +#define PSSCR_EC_ESL_MASK_SHIFTED (PSSCR_EC | PSSCR_ESL) >> 16 .text @@ -264,7 +262,7 @@ enter_winkle: IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE) /* - * r3 - requested stop state + * r3 - PSSCR value corresponding to the requested stop state. */ power_enter_stop: #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE @@ -273,10 +271,19 @@ power_enter_stop: /* DO THIS IN REAL MODE! See comment above. */ stb r4,HSTATE_HWTHREAD_STATE(r13) #endif +/* + * Check if we are executing the lite variant with ESL=EC=0 + */ + andis. r4,r3,PSSCR_EC_ESL_MASK_SHIFTED + clrldi r3,r3,60 /* r3 = Bits[60:63] = Requested Level (RL) */ + bne 1f + IDLE_STATE_ENTER_SEQ(PPC_STOP) + li r3,0 /* Since we didn't lose state, return 0 */ + b pnv_wakeup_noloss /* * Check if the requested state is a deep idle state. */ - LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state) +1: LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state) ld r4,ADDROFF(pnv_first_deep_stop_state)(r5) cmpd r3,r4 bge 2f @@ -353,16 +360,17 @@ ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66); \ ld r3,ORIG_GPR3(r1); /* Restore original r3 */ \ 20: nop; - /* - * r3 - requested stop state + * r3 - The PSSCR value corresponding to the stop state. + * r4 - The PSSCR mask corrresonding to the stop state. */ _GLOBAL(power9_idle_stop) - LOAD_REG_IMMEDIATE(r4, PSSCR_HV_TEMPLATE) - or r4,r4,r3 - mtspr SPRN_PSSCR, r4 - li r4, 1 + mfspr r5,SPRN_PSSCR + andc r5,r5,r4 + or r3,r3,r5 + mtspr SPRN_PSSCR,r3 LOAD_REG_ADDR(r5,power_enter_stop) + li r4,1 b pnv_powersave_common /* No return */ /* diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 57bec031291b..4ee837e6391a 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -237,15 +237,21 @@ static DEVICE_ATTR(fastsleep_workaround_applyonce, 0600, show_fastsleep_workaround_applyonce, store_fastsleep_workaround_applyonce); +/* + * The default stop state that will be used by ppc_md.power_save + * function on platforms that support stop instruction. + */ +u64 pnv_default_stop_val; +u64 pnv_default_stop_mask; /* * Used for ppc_md.power_save which needs a function with no parameters */ static void power9_idle(void) { - /* Requesting stop state 0 */ - power9_idle_stop(0); + power9_idle_stop(pnv_default_stop_val, pnv_default_stop_mask); } + /* * First deep stop state. Used to figure out when to save/restore * hypervisor context. @@ -253,9 +259,11 @@ static void power9_idle(void) u64 pnv_first_deep_stop_state = MAX_STOP_STATE; /* - * Deepest stop idle state. Used when a cpu is offlined + * psscr value and mask of the deepest stop idle state. + * Used when a cpu is offlined. */ -u64 pnv_deepest_stop_state; +u64 pnv_deepest_stop_psscr_val; +u64 pnv_deepest_stop_psscr_mask; /* * Power ISA 3.0 idle initialization. @@ -292,6 +300,44 @@ u64 pnv_deepest_stop_state; * Bits 60:63 - Requested Level * Used to specify which power-saving level must be entered on executing * stop instruction + */ + +int validate_psscr_val_mask(u64 *psscr_val, u64 *psscr_mask, u32 flags) +{ + int err = 0; + + /* + * psscr_mask == 0xf indicates an older firmware. + * Set remaining fields of psscr to the default values. + * See NOTE above definition of PSSCR_HV_DEFAULT_VAL + */ + if (*psscr_mask == 0xf) { + *psscr_val = *psscr_val | PSSCR_HV_DEFAULT_VAL; + *psscr_mask = PSSCR_HV_DEFAULT_MASK; + return err; + } + + /* + * New firmware is expected to set the psscr_val bits correctly. + * Validate that the following invariants are correctly maintained by + * the new firmware. + * - ESL bit value matches the EC bit value. + * - ESL bit is set for all the deep stop states. + */ + if (GET_PSSCR_ESL(*psscr_val) != GET_PSSCR_EC(*psscr_val)) { + err = ERR_EC_ESL_MISMATCH; + } else if ((flags & OPAL_PM_LOSE_FULL_CONTEXT) && + GET_PSSCR_ESL(*psscr_val) == 0) { + err = ERR_DEEP_STATE_ESL_MISMATCH; + } + + return err; +} + +/* + * pnv_arch300_idle_init: Initializes the default idle state, first + * deep idle state and deepest idle state on + * ISA 3.0 CPUs. * * @np: /ibm,opal/power-mgt device node * @flags: cpu-idle-state-flags array @@ -302,43 +348,109 @@ static int __init pnv_power9_idle_init(struct device_node *np, u32 *flags, int dt_idle_states) { u64 *psscr_val = NULL; + u64 *psscr_mask = NULL; + u32 *residency_ns = NULL; + u64 max_residency_ns = 0; int rc = 0, i; + bool default_stop_found = false, deepest_stop_found = false; - psscr_val = kcalloc(dt_idle_states, sizeof(*psscr_val), - GFP_KERNEL); - if (!psscr_val) { + psscr_val = kcalloc(dt_idle_states, sizeof(*psscr_val), GFP_KERNEL); + psscr_mask = kcalloc(dt_idle_states, sizeof(*psscr_mask), GFP_KERNEL); + residency_ns = kcalloc(dt_idle_states, sizeof(*residency_ns), + GFP_KERNEL); + + if (!psscr_val || !psscr_mask || !residency_ns) { rc = -1; goto out; } + if (of_property_read_u64_array(np, "ibm,cpu-idle-state-psscr", psscr_val, dt_idle_states)) { - pr_warn("cpuidle-powernv: missing ibm,cpu-idle-states-psscr in DT\n"); + pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-psscr in DT\n"); + rc = -1; + goto out; + } + + if (of_property_read_u64_array(np, + "ibm,cpu-idle-state-psscr-mask", + psscr_mask, dt_idle_states)) { + pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-psscr-mask in DT\n"); + rc = -1; + goto out; + } + + if (of_property_read_u32_array(np, + "ibm,cpu-idle-state-residency-ns", + residency_ns, dt_idle_states)) { + pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-residency-ns in DT\n"); rc = -1; goto out; } /* - * Set pnv_first_deep_stop_state and pnv_deepest_stop_state. + * Set pnv_first_deep_stop_state, pnv_deepest_stop_psscr_{val,mask}, + * and the pnv_default_stop_{val,mask}. + * * pnv_first_deep_stop_state should be set to the first stop * level to cause hypervisor state loss. - * pnv_deepest_stop_state should be set to the deepest stop - * stop state. + * + * pnv_deepest_stop_{val,mask} should be set to values corresponding to + * the deepest stop state. + * + * pnv_default_stop_{val,mask} should be set to values corresponding to + * the shallowest (OPAL_PM_STOP_INST_FAST) loss-less stop state. */ pnv_first_deep_stop_state = MAX_STOP_STATE; for (i = 0; i < dt_idle_states; i++) { + int err; u64 psscr_rl = psscr_val[i] & PSSCR_RL_MASK; if ((flags[i] & OPAL_PM_LOSE_FULL_CONTEXT) && (pnv_first_deep_stop_state > psscr_rl)) pnv_first_deep_stop_state = psscr_rl; - if (pnv_deepest_stop_state < psscr_rl) - pnv_deepest_stop_state = psscr_rl; + err = validate_psscr_val_mask(&psscr_val[i], &psscr_mask[i], + flags[i]); + if (err) { + report_invalid_psscr_val(psscr_val[i], err); + continue; + } + + if (max_residency_ns < residency_ns[i]) { + max_residency_ns = residency_ns[i]; + pnv_deepest_stop_psscr_val = psscr_val[i]; + pnv_deepest_stop_psscr_mask = psscr_mask[i]; + deepest_stop_found = true; + } + + if (!default_stop_found && + (flags[i] & OPAL_PM_STOP_INST_FAST)) { + pnv_default_stop_val = psscr_val[i]; + pnv_default_stop_mask = psscr_mask[i]; + default_stop_found = true; + } + } + + if (!default_stop_found) { + pnv_default_stop_val = PSSCR_HV_DEFAULT_VAL; + pnv_default_stop_mask = PSSCR_HV_DEFAULT_MASK; + pr_warn("Setting default stop psscr val=0x%016llx,mask=0x%016llx\n", + pnv_default_stop_val, pnv_default_stop_mask); + } + + if (!deepest_stop_found) { + pnv_deepest_stop_psscr_val = PSSCR_HV_DEFAULT_VAL; + pnv_deepest_stop_psscr_mask = PSSCR_HV_DEFAULT_MASK; + pr_warn("Setting default stop psscr val=0x%016llx,mask=0x%016llx\n", + pnv_deepest_stop_psscr_val, + pnv_deepest_stop_psscr_mask); } out: kfree(psscr_val); + kfree(psscr_mask); + kfree(residency_ns); return rc; } diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index da7c843ac7f1..613052232475 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -18,7 +18,8 @@ static inline void pnv_pci_shutdown(void) { } #endif extern u32 pnv_get_supported_cpuidle_states(void); -extern u64 pnv_deepest_stop_state; +extern u64 pnv_deepest_stop_psscr_val; +extern u64 pnv_deepest_stop_psscr_mask; extern void pnv_lpc_init(void); diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index c789258ae1e1..1c6405fb769a 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -182,15 +182,17 @@ static void pnv_smp_cpu_kill_self(void) ppc64_runlatch_off(); - if (cpu_has_feature(CPU_FTR_ARCH_300)) - srr1 = power9_idle_stop(pnv_deepest_stop_state); - else if (idle_states & OPAL_PM_WINKLE_ENABLED) + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + srr1 = power9_idle_stop(pnv_deepest_stop_psscr_val, + pnv_deepest_stop_psscr_mask); + } else if (idle_states & OPAL_PM_WINKLE_ENABLED) { srr1 = power7_winkle(); - else if ((idle_states & OPAL_PM_SLEEP_ENABLED) || - (idle_states & OPAL_PM_SLEEP_ENABLED_ER1)) + } else if ((idle_states & OPAL_PM_SLEEP_ENABLED) || + (idle_states & OPAL_PM_SLEEP_ENABLED_ER1)) { srr1 = power7_sleep(); - else + } else { srr1 = power7_nap(1); + } ppc64_runlatch_on(); diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c index 6871b7f34dc8..370593006f5f 100644 --- a/drivers/cpuidle/cpuidle-powernv.c +++ b/drivers/cpuidle/cpuidle-powernv.c @@ -19,6 +19,7 @@ #include #include #include +#include /* * Expose only those Hardware idle states via the cpuidle framework @@ -34,7 +35,12 @@ static struct cpuidle_driver powernv_idle_driver = { static int max_idle_state; static struct cpuidle_state *cpuidle_state_table; -static u64 stop_psscr_table[CPUIDLE_STATE_MAX]; +struct stop_psscr_table { + u64 val; + u64 mask; +}; + +static struct stop_psscr_table stop_psscr_table[CPUIDLE_STATE_MAX]; static u64 snooze_timeout; static bool snooze_timeout_en; @@ -106,7 +112,8 @@ static int stop_loop(struct cpuidle_device *dev, int index) { ppc64_runlatch_off(); - power9_idle_stop(stop_psscr_table[index]); + power9_idle_stop(stop_psscr_table[index].val, + stop_psscr_table[index].mask); ppc64_runlatch_on(); return index; } @@ -178,7 +185,7 @@ static inline void add_powernv_state(int index, const char *name, int), unsigned int target_residency, unsigned int exit_latency, - u64 psscr_val) + u64 psscr_val, u64 psscr_mask) { strlcpy(powernv_states[index].name, name, CPUIDLE_NAME_LEN); strlcpy(powernv_states[index].desc, name, CPUIDLE_NAME_LEN); @@ -186,7 +193,8 @@ static inline void add_powernv_state(int index, const char *name, powernv_states[index].target_residency = target_residency; powernv_states[index].exit_latency = exit_latency; powernv_states[index].enter = idle_fn; - stop_psscr_table[index] = psscr_val; + stop_psscr_table[index].val = psscr_val; + stop_psscr_table[index].mask = psscr_mask; } static int powernv_add_idle_states(void) @@ -198,7 +206,9 @@ static int powernv_add_idle_states(void) u32 residency_ns[CPUIDLE_STATE_MAX]; u32 flags[CPUIDLE_STATE_MAX]; u64 psscr_val[CPUIDLE_STATE_MAX]; + u64 psscr_mask[CPUIDLE_STATE_MAX]; const char *names[CPUIDLE_STATE_MAX]; + u32 has_stop_states = 0; int i, rc; /* Currently we have snooze statically defined */ @@ -245,15 +255,25 @@ static int powernv_add_idle_states(void) /* * If the idle states use stop instruction, probe for psscr values - * which are necessary to specify required stop level. + * and psscr mask which are necessary to specify required stop level. */ - if (flags[0] & (OPAL_PM_STOP_INST_FAST | OPAL_PM_STOP_INST_DEEP)) + has_stop_states = (flags[0] & + (OPAL_PM_STOP_INST_FAST | OPAL_PM_STOP_INST_DEEP)); + if (has_stop_states) { if (of_property_read_u64_array(power_mgt, "ibm,cpu-idle-state-psscr", psscr_val, dt_idle_states)) { - pr_warn("cpuidle-powernv: missing ibm,cpu-idle-states-psscr in DT\n"); + pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-psscr in DT\n"); goto out; } + if (of_property_read_u64_array(power_mgt, + "ibm,cpu-idle-state-psscr-mask", + psscr_mask, dt_idle_states)) { + pr_warn("cpuidle-powernv:Missing ibm,cpu-idle-state-psscr-mask in DT\n"); + goto out; + } + } + rc = of_property_read_u32_array(power_mgt, "ibm,cpu-idle-state-residency-ns", residency_ns, dt_idle_states); @@ -276,6 +296,16 @@ static int powernv_add_idle_states(void) else target_residency = 0; + if (has_stop_states) { + int err = validate_psscr_val_mask(&psscr_val[i], + &psscr_mask[i], + flags[i]); + if (err) { + report_invalid_psscr_val(psscr_val[i], err); + continue; + } + } + /* * For nap and fastsleep, use default target_residency * values if f/w does not expose it. @@ -286,13 +316,13 @@ static int powernv_add_idle_states(void) /* Add NAP state */ add_powernv_state(nr_idle_states, "Nap", CPUIDLE_FLAG_NONE, nap_loop, - target_residency, exit_latency, 0); + target_residency, exit_latency, 0, 0); } else if ((flags[i] & OPAL_PM_STOP_INST_FAST) && !(flags[i] & OPAL_PM_TIMEBASE_STOP)) { add_powernv_state(nr_idle_states, names[i], CPUIDLE_FLAG_NONE, stop_loop, target_residency, exit_latency, - psscr_val[i]); + psscr_val[i], psscr_mask[i]); } /* @@ -308,13 +338,13 @@ static int powernv_add_idle_states(void) add_powernv_state(nr_idle_states, "FastSleep", CPUIDLE_FLAG_TIMER_STOP, fastsleep_loop, - target_residency, exit_latency, 0); + target_residency, exit_latency, 0, 0); } else if ((flags[i] & OPAL_PM_STOP_INST_DEEP) && (flags[i] & OPAL_PM_TIMEBASE_STOP)) { add_powernv_state(nr_idle_states, names[i], CPUIDLE_FLAG_TIMER_STOP, stop_loop, target_residency, exit_latency, - psscr_val[i]); + psscr_val[i], psscr_mask[i]); } #endif nr_idle_states++; -- cgit v1.2.3 From 38e9d36bc149932964dcd25818c7f7283239592d Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 30 Jan 2017 18:11:55 +1100 Subject: powerpc: Move isa bridge definitions to separate include We'll be adding non-PCI isa bridge support so let's not have all the definition in pci-bridge.h Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/isa-bridge.h | 28 ++++++++++++++++++++++++++++ arch/powerpc/include/asm/pci-bridge.h | 18 ------------------ arch/powerpc/kernel/iomap.c | 1 + arch/powerpc/kernel/isa-bridge.c | 1 + arch/powerpc/platforms/maple/pci.c | 1 + arch/powerpc/platforms/powernv/opal-lpc.c | 1 + arch/powerpc/platforms/pseries/setup.c | 1 + 7 files changed, 33 insertions(+), 18 deletions(-) create mode 100644 arch/powerpc/include/asm/isa-bridge.h (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/isa-bridge.h b/arch/powerpc/include/asm/isa-bridge.h new file mode 100644 index 000000000000..94d9c1c9706d --- /dev/null +++ b/arch/powerpc/include/asm/isa-bridge.h @@ -0,0 +1,28 @@ +#ifndef __ISA_BRIDGE_H +#define __ISA_BRIDGE_H + +#ifdef CONFIG_PPC64 + +extern void isa_bridge_find_early(struct pci_controller *hose); + +static inline int isa_vaddr_is_ioport(void __iomem *address) +{ + /* Check if address hits the reserved legacy IO range */ + unsigned long ea = (unsigned long)address; + return ea >= ISA_IO_BASE && ea < ISA_IO_END; +} + +#else + +static inline int isa_vaddr_is_ioport(void __iomem *address) +{ + /* No specific ISA handling on ppc32 at this stage, it + * all goes through PCI + */ + return 0; +} + +#endif + +#endif /* __ISA_BRIDGE_H */ + diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index c0309c59bed8..56c67d3f0108 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -174,14 +174,6 @@ extern int pci_device_from_OF_node(struct device_node *node, u8 *bus, u8 *devfn); extern void pci_create_OF_bus_map(void); -static inline int isa_vaddr_is_ioport(void __iomem *address) -{ - /* No specific ISA handling on ppc32 at this stage, it - * all goes through PCI - */ - return 0; -} - #else /* CONFIG_PPC64 */ /* @@ -269,16 +261,6 @@ extern void pci_hp_remove_devices(struct pci_bus *bus); /** Discover new pci devices under this bus, and add them */ extern void pci_hp_add_devices(struct pci_bus *bus); - -extern void isa_bridge_find_early(struct pci_controller *hose); - -static inline int isa_vaddr_is_ioport(void __iomem *address) -{ - /* Check if address hits the reserved legacy IO range */ - unsigned long ea = (unsigned long)address; - return ea >= ISA_IO_BASE && ea < ISA_IO_END; -} - extern int pcibios_unmap_io_space(struct pci_bus *bus); extern int pcibios_map_io_space(struct pci_bus *bus); diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c index 3963f0b68d52..a1854d1ded8b 100644 --- a/arch/powerpc/kernel/iomap.c +++ b/arch/powerpc/kernel/iomap.c @@ -8,6 +8,7 @@ #include #include #include +#include /* * Here comes the ppc64 implementation of the IOMAP diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c index ae1316106e2b..c898ff0cafec 100644 --- a/arch/powerpc/kernel/isa-bridge.c +++ b/arch/powerpc/kernel/isa-bridge.c @@ -29,6 +29,7 @@ #include #include #include +#include unsigned long isa_io_base; /* NULL if no ISA bus */ EXPORT_SYMBOL(isa_io_base); diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c index a0589aac4163..69794d9389c2 100644 --- a/arch/powerpc/platforms/maple/pci.c +++ b/arch/powerpc/platforms/maple/pci.c @@ -24,6 +24,7 @@ #include #include #include +#include #include "maple.h" diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c index 4886eb8b6381..2048ce7912f4 100644 --- a/arch/powerpc/platforms/powernv/opal-lpc.c +++ b/arch/powerpc/platforms/powernv/opal-lpc.c @@ -23,6 +23,7 @@ #include #include #include +#include static int opal_lpc_chip_id = -1; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 7736352f7279..b4d362ed03a1 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -66,6 +66,7 @@ #include #include #include +#include #include "pseries.h" -- cgit v1.2.3 From b3c711a9e19eb2b300132f1712ff3d5afb4b02dc Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 30 Jan 2017 18:11:56 +1100 Subject: powerpc: Add support for non-PCI ISA bridges The POWER9 chip supports an LPC bus that isn't hanging off a PCI bus, so let's add support for that, mapping it to the reserved space at ISA_IO_BASE Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/isa-bridge.h | 1 + arch/powerpc/kernel/isa-bridge.c | 91 +++++++++++++++++++++++++++++++++++ 2 files changed, 92 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/isa-bridge.h b/arch/powerpc/include/asm/isa-bridge.h index 94d9c1c9706d..a3a7c1d63a7c 100644 --- a/arch/powerpc/include/asm/isa-bridge.h +++ b/arch/powerpc/include/asm/isa-bridge.h @@ -4,6 +4,7 @@ #ifdef CONFIG_PPC64 extern void isa_bridge_find_early(struct pci_controller *hose); +extern void isa_bridge_init_non_pci(struct device_node *np); static inline int isa_vaddr_is_ioport(void __iomem *address) { diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c index c898ff0cafec..bb6f8993412e 100644 --- a/arch/powerpc/kernel/isa-bridge.c +++ b/arch/powerpc/kernel/isa-bridge.c @@ -167,6 +167,97 @@ void __init isa_bridge_find_early(struct pci_controller *hose) pr_debug("ISA bridge (early) is %s\n", np->full_name); } +/** + * isa_bridge_find_early - Find and map the ISA IO space early before + * main PCI discovery. This is optionally called by + * the arch code when adding PCI PHBs to get early + * access to ISA IO ports + */ +void __init isa_bridge_init_non_pci(struct device_node *np) +{ + const __be32 *ranges, *pbasep = NULL; + int rlen, i, rs; + u32 na, ns, pna; + u64 cbase, pbase, size = 0; + + /* If we already have an ISA bridge, bail off */ + if (isa_bridge_devnode != NULL) + return; + + pna = of_n_addr_cells(np); + if (of_property_read_u32(np, "#address-cells", &na) || + of_property_read_u32(np, "#size-cells", &ns)) { + pr_warn("ISA: Non-PCI bridge %s is missing address format\n", + np->full_name); + return; + } + + /* Check it's a supported address format */ + if (na != 2 || ns != 1) { + pr_warn("ISA: Non-PCI bridge %s has unsupported address format\n", + np->full_name); + return; + } + rs = na + ns + pna; + + /* Grab the ranges property */ + ranges = of_get_property(np, "ranges", &rlen); + if (ranges == NULL || rlen < rs) { + pr_warn("ISA: Non-PCI bridge %s has absent or invalid ranges\n", + np->full_name); + return; + } + + /* Parse it. We are only looking for IO space */ + for (i = 0; (i + rs - 1) < rlen; i += rs) { + if (be32_to_cpup(ranges + i) != 1) + continue; + cbase = be32_to_cpup(ranges + i + 1); + size = of_read_number(ranges + i + na + pna, ns); + pbasep = ranges + i + na; + break; + } + + /* Got something ? */ + if (!size || !pbasep) { + pr_warn("ISA: Non-PCI bridge %s has no usable IO range\n", + np->full_name); + return; + } + + /* Align size and make sure it's cropped to 64K */ + size = PAGE_ALIGN(size); + if (size > 0x10000) + size = 0x10000; + + /* Map pbase */ + pbase = of_translate_address(np, pbasep); + if (pbase == OF_BAD_ADDR) { + pr_warn("ISA: Non-PCI bridge %s failed to translate IO base\n", + np->full_name); + return; + } + + /* We need page alignment */ + if ((cbase & ~PAGE_MASK) || (pbase & ~PAGE_MASK)) { + pr_warn("ISA: Non-PCI bridge %s has non aligned IO range\n", + np->full_name); + return; + } + + /* Got it */ + isa_bridge_devnode = np; + + /* Set the global ISA io base to indicate we have an ISA bridge + * and map it + */ + isa_io_base = ISA_IO_BASE; + __ioremap_at(pbase, (void *)ISA_IO_BASE, + size, pgprot_val(pgprot_noncached(__pgprot(0)))); + + pr_debug("ISA: Non-PCI bridge is %s\n", np->full_name); +} + /** * isa_bridge_find_late - Find and map the ISA IO space upon discovery of * a new ISA bridge -- cgit v1.2.3 From 6cc27341b21a81052f36c137bc44cf55f83e46ff Mon Sep 17 00:00:00 2001 From: Reza Arbab Date: Mon, 16 Jan 2017 13:07:44 -0600 Subject: powerpc/mm: add radix__create_section_mapping() Wire up memory hotplug page mapping for radix. Share the mapping function already used by radix_init_pgtable(). Signed-off-by: Reza Arbab Acked-by: Balbir Singh Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/radix.h | 4 ++++ arch/powerpc/mm/pgtable-book3s64.c | 2 +- arch/powerpc/mm/pgtable-radix.c | 7 +++++++ 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index b4d1302387a3..43c25718de61 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -291,5 +291,9 @@ static inline unsigned long radix__get_tree_size(void) } return rts_field; } + +#ifdef CONFIG_MEMORY_HOTPLUG +int radix__create_section_mapping(unsigned long start, unsigned long end); +#endif /* CONFIG_MEMORY_HOTPLUG */ #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index 653ff6c74ebe..2b13f6b87e25 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -131,7 +131,7 @@ void mmu_cleanup_all(void) int create_section_mapping(unsigned long start, unsigned long end) { if (radix_enabled()) - return -ENODEV; + return radix__create_section_mapping(start, end); return hash__create_section_mapping(start, end); } diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index c0365eca7f81..7829e09ab4dd 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -481,6 +481,13 @@ void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base, memblock_set_current_limit(first_memblock_base + first_memblock_size); } +#ifdef CONFIG_MEMORY_HOTPLUG +int __ref radix__create_section_mapping(unsigned long start, unsigned long end) +{ + return create_physical_mapping(start, end); +} +#endif /* CONFIG_MEMORY_HOTPLUG */ + #ifdef CONFIG_SPARSEMEM_VMEMMAP int __meminit radix__vmemmap_create_mapping(unsigned long start, unsigned long page_size, -- cgit v1.2.3 From 4b5d62ca17a1cd2ffc8399e1d1c3ebbabf16e78f Mon Sep 17 00:00:00 2001 From: Reza Arbab Date: Mon, 16 Jan 2017 13:07:45 -0600 Subject: powerpc/mm: add radix__remove_section_mapping() Tear down and free the four-level page tables of physical mappings during memory hotremove. Borrow the basic structure of remove_pagetable() and friends from the identically-named x86 functions. Reduce the frequency of tlb flushes and page_table_lock spinlocks by only doing them in the outermost function. There was some question as to whether the locking is needed at all. Leave it for now, but we could consider dropping it. Memory must be offline to be removed, thus not in use. So there shouldn't be the sort of concurrent page walking activity here that might prompt us to use RCU. Signed-off-by: Reza Arbab Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/radix.h | 1 + arch/powerpc/mm/pgtable-book3s64.c | 2 +- arch/powerpc/mm/pgtable-radix.c | 133 +++++++++++++++++++++++++++++ 3 files changed, 135 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 43c25718de61..0032b662284c 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -294,6 +294,7 @@ static inline unsigned long radix__get_tree_size(void) #ifdef CONFIG_MEMORY_HOTPLUG int radix__create_section_mapping(unsigned long start, unsigned long end); +int radix__remove_section_mapping(unsigned long start, unsigned long end); #endif /* CONFIG_MEMORY_HOTPLUG */ #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index 2b13f6b87e25..b798ff674fab 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -139,7 +139,7 @@ int create_section_mapping(unsigned long start, unsigned long end) int remove_section_mapping(unsigned long start, unsigned long end) { if (radix_enabled()) - return -ENODEV; + return radix__remove_section_mapping(start, end); return hash__remove_section_mapping(start, end); } diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 7829e09ab4dd..aef9d49f70ce 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -482,10 +482,143 @@ void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base, } #ifdef CONFIG_MEMORY_HOTPLUG +static void free_pte_table(pte_t *pte_start, pmd_t *pmd) +{ + pte_t *pte; + int i; + + for (i = 0; i < PTRS_PER_PTE; i++) { + pte = pte_start + i; + if (!pte_none(*pte)) + return; + } + + pte_free_kernel(&init_mm, pte_start); + pmd_clear(pmd); +} + +static void free_pmd_table(pmd_t *pmd_start, pud_t *pud) +{ + pmd_t *pmd; + int i; + + for (i = 0; i < PTRS_PER_PMD; i++) { + pmd = pmd_start + i; + if (!pmd_none(*pmd)) + return; + } + + pmd_free(&init_mm, pmd_start); + pud_clear(pud); +} + +static void remove_pte_table(pte_t *pte_start, unsigned long addr, + unsigned long end) +{ + unsigned long next; + pte_t *pte; + + pte = pte_start + pte_index(addr); + for (; addr < end; addr = next, pte++) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + if (next > end) + next = end; + + if (!pte_present(*pte)) + continue; + + pte_clear(&init_mm, addr, pte); + } +} + +static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr, + unsigned long end) +{ + unsigned long next; + pte_t *pte_base; + pmd_t *pmd; + + pmd = pmd_start + pmd_index(addr); + for (; addr < end; addr = next, pmd++) { + next = pmd_addr_end(addr, end); + + if (!pmd_present(*pmd)) + continue; + + if (pmd_huge(*pmd)) { + pte_clear(&init_mm, addr, (pte_t *)pmd); + continue; + } + + pte_base = (pte_t *)pmd_page_vaddr(*pmd); + remove_pte_table(pte_base, addr, next); + free_pte_table(pte_base, pmd); + } +} + +static void remove_pud_table(pud_t *pud_start, unsigned long addr, + unsigned long end) +{ + unsigned long next; + pmd_t *pmd_base; + pud_t *pud; + + pud = pud_start + pud_index(addr); + for (; addr < end; addr = next, pud++) { + next = pud_addr_end(addr, end); + + if (!pud_present(*pud)) + continue; + + if (pud_huge(*pud)) { + pte_clear(&init_mm, addr, (pte_t *)pud); + continue; + } + + pmd_base = (pmd_t *)pud_page_vaddr(*pud); + remove_pmd_table(pmd_base, addr, next); + free_pmd_table(pmd_base, pud); + } +} + +static void remove_pagetable(unsigned long start, unsigned long end) +{ + unsigned long addr, next; + pud_t *pud_base; + pgd_t *pgd; + + spin_lock(&init_mm.page_table_lock); + + for (addr = start; addr < end; addr = next) { + next = pgd_addr_end(addr, end); + + pgd = pgd_offset_k(addr); + if (!pgd_present(*pgd)) + continue; + + if (pgd_huge(*pgd)) { + pte_clear(&init_mm, addr, (pte_t *)pgd); + continue; + } + + pud_base = (pud_t *)pgd_page_vaddr(*pgd); + remove_pud_table(pud_base, addr, next); + } + + spin_unlock(&init_mm.page_table_lock); + radix__flush_tlb_kernel_range(start, end); +} + int __ref radix__create_section_mapping(unsigned long start, unsigned long end) { return create_physical_mapping(start, end); } + +int radix__remove_section_mapping(unsigned long start, unsigned long end) +{ + remove_pagetable(start, end); + return 0; +} #endif /* CONFIG_MEMORY_HOTPLUG */ #ifdef CONFIG_SPARSEMEM_VMEMMAP -- cgit v1.2.3 From a97a65d53d9f53b6897dc1b2aed381bc1707136b Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 27 Jan 2017 14:00:34 +1000 Subject: KVM: PPC: Book3S: 64-bit CONFIG_RELOCATABLE support for interrupts 64-bit Book3S exception handlers must find the dynamic kernel base to add to the target address when branching beyond __end_interrupts, in order to support kernel running at non-0 physical address. Support this in KVM by branching with CTR, similarly to regular interrupt handlers. The guest CTR saved in HSTATE_SCRATCH1 and restored after the branch. Without this, the host kernel hangs and crashes randomly when it is running at a non-0 address and a KVM guest is started. Signed-off-by: Nicholas Piggin Acked-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/exception-64s.h | 45 +++++++++++++++++++++++++++++--- arch/powerpc/kernel/exceptions-64s.S | 2 +- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 12 ++++++--- arch/powerpc/kvm/book3s_segment.S | 7 +++++ 4 files changed, 58 insertions(+), 8 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index a02a268bde6b..9a5dbfb2d9f2 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -97,6 +97,15 @@ ld reg,PACAKBASE(r13); \ ori reg,reg,(ABS_ADDR(label))@l; +/* + * Branches from unrelocated code (e.g., interrupts) to labels outside + * head-y require >64K offsets. + */ +#define __LOAD_FAR_HANDLER(reg, label) \ + ld reg,PACAKBASE(r13); \ + ori reg,reg,(ABS_ADDR(label))@l; \ + addis reg,reg,(ABS_ADDR(label))@h; + /* Exception register prefixes */ #define EXC_HV H #define EXC_STD @@ -227,12 +236,40 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) mtctr reg; \ bctr +/* + * KVM requires __LOAD_FAR_HANDLER. + * + * __BRANCH_TO_KVM_EXIT branches are also a special case because they + * explicitly use r9 then reload it from PACA before branching. Hence + * the double-underscore. + */ +#define __BRANCH_TO_KVM_EXIT(area, label) \ + mfctr r9; \ + std r9,HSTATE_SCRATCH1(r13); \ + __LOAD_FAR_HANDLER(r9, label); \ + mtctr r9; \ + 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 +#define BRANCH_TO_KVM(reg, label) \ + b label + +#define __BRANCH_TO_KVM_EXIT(area, label) \ + ld r9,area+EX_R9(r13); \ + b label + #endif + #define __KVM_HANDLER(area, h, n) \ BEGIN_FTR_SECTION_NESTED(947) \ ld r10,area+EX_CFAR(r13); \ @@ -246,8 +283,8 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) std r12,HSTATE_SCRATCH0(r13); \ sldi r12,r9,32; \ ori r12,r12,(n); \ - ld r9,area+EX_R9(r13); \ - b kvmppc_interrupt + /* This reloads r9 before branching to kvmppc_interrupt */ \ + __BRANCH_TO_KVM_EXIT(area, kvmppc_interrupt) #define __KVM_HANDLER_SKIP(area, h, n) \ cmpwi r10,KVM_GUEST_MODE_SKIP; \ @@ -260,8 +297,8 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) std r12,HSTATE_SCRATCH0(r13); \ sldi r12,r9,32; \ ori r12,r12,(n); \ - ld r9,area+EX_R9(r13); \ - b kvmppc_interrupt; \ + /* This reloads r9 before branching to kvmppc_interrupt */ \ + __BRANCH_TO_KVM_EXIT(area, kvmppc_interrupt); \ 89: mtocrf 0x80,r9; \ ld r9,area+EX_R9(r13); \ ld r10,area+EX_R10(r13); \ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 89b4f122aec6..65a2559eeb7f 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -142,7 +142,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) lbz r0,HSTATE_HWTHREAD_REQ(r13) cmpwi r0,0 beq 1f - b kvm_start_guest + BRANCH_TO_KVM(r10, kvm_start_guest) 1: #endif diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 11882aac8216..264ac9ad4585 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1060,15 +1060,16 @@ kvmppc_interrupt_hv: * R12 = (guest CR << 32) | interrupt vector * R13 = PACA * guest R12 saved in shadow VCPU SCRATCH0 + * guest CTR saved in shadow VCPU SCRATCH1 if RELOCATABLE * guest R13 saved in SPRN_SCRATCH0 */ - std r9, HSTATE_SCRATCH1(r13) + std r9, HSTATE_SCRATCH2(r13) lbz r9, HSTATE_IN_GUEST(r13) cmpwi r9, KVM_GUEST_MODE_HOST_HV beq kvmppc_bad_host_intr #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE cmpwi r9, KVM_GUEST_MODE_GUEST - ld r9, HSTATE_SCRATCH1(r13) + ld r9, HSTATE_SCRATCH2(r13) beq kvmppc_interrupt_pr #endif /* We're now back in the host but in guest MMU context */ @@ -1088,7 +1089,7 @@ kvmppc_interrupt_hv: std r6, VCPU_GPR(R6)(r9) std r7, VCPU_GPR(R7)(r9) std r8, VCPU_GPR(R8)(r9) - ld r0, HSTATE_SCRATCH1(r13) + ld r0, HSTATE_SCRATCH2(r13) std r0, VCPU_GPR(R9)(r9) std r10, VCPU_GPR(R10)(r9) std r11, VCPU_GPR(R11)(r9) @@ -1151,7 +1152,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) 11: stw r3,VCPU_HEIR(r9) /* these are volatile across C function calls */ +#ifdef CONFIG_RELOCATABLE + ld r3, HSTATE_SCRATCH1(r13) + mtctr r3 +#else mfctr r3 +#endif mfxer r4 std r3, VCPU_CTR(r9) std r4, VCPU_XER(r9) diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S index 68e45080cf93..2a2b96d53999 100644 --- a/arch/powerpc/kvm/book3s_segment.S +++ b/arch/powerpc/kvm/book3s_segment.S @@ -175,9 +175,16 @@ kvmppc_interrupt_pr: * R12 = (guest CR << 32) | exit handler id * R13 = PACA * HSTATE.SCRATCH0 = guest R12 + * HSTATE.SCRATCH1 = guest CTR if RELOCATABLE */ #ifdef CONFIG_PPC64 /* Match 32-bit entry */ +#ifdef CONFIG_RELOCATABLE + std r9, HSTATE_SCRATCH2(r13) + ld r9, HSTATE_SCRATCH1(r13) + mtctr r9 + ld r9, HSTATE_SCRATCH2(r13) +#endif rotldi r12, r12, 32 /* Flip R12 halves for stw */ stw r12, HSTATE_SCRATCH1(r13) /* CR is now in the low half */ srdi r12, r12, 32 /* shift trap into low half */ -- cgit v1.2.3 From 3f4ab2f83b4e443c66549206eb88a9fa5a85d647 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 30 Jan 2017 21:21:35 +1100 Subject: powerpc/pseries: Fixes for the "ibm,architecture-vec-5" options This fixes the byte index values for some of the option bits in the "ibm,architectur-vec-5" property. The "platform facilities options" bits are in byte 17 not byte 14, so the upper 8 bits of their definitions need to be 0x11 not 0x0E. The "sub processor support" option is in byte 21 not byte 15. Note none of these options are actually looked up in "ibm,architecture-vec-5" at this time, so there is no bug. When checking whether option bits are set, we should check that the offset of the byte being checked is less than the vector length that we got from the hypervisor. Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/prom.h | 8 ++++---- arch/powerpc/platforms/pseries/firmware.c | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index 5e57705b4759..e6d83d0fada7 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -151,10 +151,10 @@ struct of_drconf_cell { #define OV5_XCMO 0x0440 /* Page Coalescing */ #define OV5_TYPE1_AFFINITY 0x0580 /* Type 1 NUMA affinity */ #define OV5_PRRN 0x0540 /* Platform Resource Reassignment */ -#define OV5_PFO_HW_RNG 0x0E80 /* PFO Random Number Generator */ -#define OV5_PFO_HW_842 0x0E40 /* PFO Compression Accelerator */ -#define OV5_PFO_HW_ENCR 0x0E20 /* PFO Encryption Accelerator */ -#define OV5_SUB_PROCESSORS 0x0F01 /* 1,2,or 4 Sub-Processors supported */ +#define OV5_PFO_HW_RNG 0x1180 /* PFO Random Number Generator */ +#define OV5_PFO_HW_842 0x1140 /* PFO Compression Accelerator */ +#define OV5_PFO_HW_ENCR 0x1120 /* PFO Encryption Accelerator */ +#define OV5_SUB_PROCESSORS 0x1501 /* 1,2,or 4 Sub-Processors supported */ /* Option Vector 6: IBM PAPR hints */ #define OV6_LINUX 0x02 /* Linux is our OS */ diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c index ea7f09bd73b1..7d67623203b8 100644 --- a/arch/powerpc/platforms/pseries/firmware.c +++ b/arch/powerpc/platforms/pseries/firmware.c @@ -126,7 +126,7 @@ static void __init fw_vec5_feature_init(const char *vec5, unsigned long len) index = OV5_INDX(vec5_fw_features_table[i].feature); feat = OV5_FEAT(vec5_fw_features_table[i].feature); - if (vec5[index] & feat) + if (index < len && (vec5[index] & feat)) powerpc_firmware_features |= vec5_fw_features_table[i].val; } -- cgit v1.2.3 From cc3d2940133d24000e2866b21e03ce32adfead0a Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 30 Jan 2017 21:21:36 +1100 Subject: powerpc/64: Enable use of radix MMU under hypervisor on POWER9 To use radix as a guest, we first need to tell the hypervisor via the ibm,client-architecture call first that we support POWER9 and architecture v3.00, and that we can do either radix or hash and that we would like to choose later using an hcall (the H_REGISTER_PROC_TBL hcall). Then we need to check whether the hypervisor agreed to us using radix. We need to do this very early on in the kernel boot process before any of the MMU initialization is done. If the hypervisor doesn't agree, we can't use radix and therefore clear the radix MMU feature bit. Later, when we have set up our process table, which points to the radix tree for each process, we need to install that using the H_REGISTER_PROC_TBL hcall. Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/mmu.h | 6 ++++++ arch/powerpc/include/asm/hvcall.h | 11 +++++++++++ arch/powerpc/include/asm/prom.h | 9 +++++++++ arch/powerpc/kernel/prom_init.c | 18 +++++++++++++++++- arch/powerpc/mm/init_64.c | 12 +++++++----- arch/powerpc/mm/pgtable-radix.c | 2 ++ arch/powerpc/platforms/pseries/lpar.c | 29 +++++++++++++++++++++++++++++ 7 files changed, 81 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index 8afb0e00f7d9..cea522c3bcae 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -138,5 +138,11 @@ static inline void setup_initial_memory_limit(phys_addr_t first_memblock_base, extern int (*register_process_table)(unsigned long base, unsigned long page_size, unsigned long tbl_size); +#ifdef CONFIG_PPC_PSERIES +extern void radix_init_pseries(void); +#else +static inline void radix_init_pseries(void) { }; +#endif + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_MMU_H_ */ diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 77ff1ba99d1f..54d11b3a6bf7 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -276,6 +276,7 @@ #define H_GET_MPP_X 0x314 #define H_SET_MODE 0x31C #define H_CLEAR_HPT 0x358 +#define H_REGISTER_PROC_TBL 0x37C #define H_SIGNAL_SYS_RESET 0x380 #define MAX_HCALL_OPCODE H_SIGNAL_SYS_RESET @@ -313,6 +314,16 @@ #define H_SIGNAL_SYS_RESET_ALL_OTHERS -2 /* >= 0 values are CPU number */ +/* Flag values used in H_REGISTER_PROC_TBL hcall */ +#define PROC_TABLE_OP_MASK 0x18 +#define PROC_TABLE_DEREG 0x10 +#define PROC_TABLE_NEW 0x18 +#define PROC_TABLE_TYPE_MASK 0x06 +#define PROC_TABLE_HPT_SLB 0x00 +#define PROC_TABLE_HPT_PT 0x02 +#define PROC_TABLE_RADIX 0x04 +#define PROC_TABLE_GTSE 0x01 + #ifndef __ASSEMBLY__ /** diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index e6d83d0fada7..8af2546ea593 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -121,6 +121,8 @@ struct of_drconf_cell { #define OV1_PPC_2_06 0x02 /* set if we support PowerPC 2.06 */ #define OV1_PPC_2_07 0x01 /* set if we support PowerPC 2.07 */ +#define OV1_PPC_3_00 0x80 /* set if we support PowerPC 3.00 */ + /* Option vector 2: Open Firmware options supported */ #define OV2_REAL_MODE 0x20 /* set if we want OF in real mode */ @@ -155,6 +157,13 @@ struct of_drconf_cell { #define OV5_PFO_HW_842 0x1140 /* PFO Compression Accelerator */ #define OV5_PFO_HW_ENCR 0x1120 /* PFO Encryption Accelerator */ #define OV5_SUB_PROCESSORS 0x1501 /* 1,2,or 4 Sub-Processors supported */ +#define OV5_XIVE_EXPLOIT 0x1701 /* XIVE exploitation supported */ +#define OV5_MMU_RADIX_300 0x1880 /* ISA v3.00 radix MMU supported */ +#define OV5_MMU_HASH_300 0x1840 /* ISA v3.00 hash MMU supported */ +#define OV5_MMU_SEGM_RADIX 0x1820 /* radix mode (no segmentation) */ +#define OV5_MMU_PROC_TBL 0x1810 /* hcall selects SLB or proc table */ +#define OV5_MMU_SLB 0x1800 /* always use SLB */ +#define OV5_MMU_GTSE 0x1808 /* Guest translation shootdown */ /* Option Vector 6: IBM PAPR hints */ #define OV6_LINUX 0x02 /* Linux is our OS */ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index ec47a939cbdd..358d43f8f84f 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -649,6 +649,7 @@ static void __init early_cmdline_parse(void) struct option_vector1 { u8 byte1; u8 arch_versions; + u8 arch_versions3; } __packed; struct option_vector2 { @@ -691,6 +692,9 @@ struct option_vector5 { u8 reserved2; __be16 reserved3; u8 subprocessors; + u8 byte22; + u8 intarch; + u8 mmu; } __packed; struct option_vector6 { @@ -700,7 +704,7 @@ struct option_vector6 { } __packed; struct ibm_arch_vec { - struct { u32 mask, val; } pvrs[10]; + struct { u32 mask, val; } pvrs[12]; u8 num_vectors; @@ -749,6 +753,14 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = { .mask = cpu_to_be32(0xffff0000), /* POWER8 */ .val = cpu_to_be32(0x004d0000), }, + { + .mask = cpu_to_be32(0xffff0000), /* POWER9 */ + .val = cpu_to_be32(0x004e0000), + }, + { + .mask = cpu_to_be32(0xffffffff), /* all 3.00-compliant */ + .val = cpu_to_be32(0x0f000005), + }, { .mask = cpu_to_be32(0xffffffff), /* all 2.07-compliant */ .val = cpu_to_be32(0x0f000004), @@ -774,6 +786,7 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = { .byte1 = 0, .arch_versions = OV1_PPC_2_00 | OV1_PPC_2_01 | OV1_PPC_2_02 | OV1_PPC_2_03 | OV1_PPC_2_04 | OV1_PPC_2_05 | OV1_PPC_2_06 | OV1_PPC_2_07, + .arch_versions3 = OV1_PPC_3_00, }, .vec2_len = VECTOR_LENGTH(sizeof(struct option_vector2)), @@ -836,6 +849,9 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = { .reserved2 = 0, .reserved3 = 0, .subprocessors = 1, + .intarch = 0, + .mmu = OV5_FEAT(OV5_MMU_RADIX_300) | OV5_FEAT(OV5_MMU_HASH_300) | + OV5_FEAT(OV5_MMU_PROC_TBL) | OV5_FEAT(OV5_MMU_GTSE), }, /* option vector 6: IBM PAPR hints */ diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 4d9481ec2468..10c9a545a646 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -347,10 +347,9 @@ static int __init parse_disable_radix(char *p) early_param("disable_radix", parse_disable_radix); /* - * If we're running under a hypervisor, we currently can't do radix - * since we don't have the code to do the H_REGISTER_PROC_TBL hcall. - * We tell that we're running under a hypervisor by looking for the - * /chosen/ibm,architecture-vec-5 property. + * If we're running under a hypervisor, we need to check the contents of + * /chosen/ibm,architecture-vec-5 to see if the hypervisor is willing to do + * radix. If not, we clear the radix feature bit so we fall back to hash. */ static void early_check_vec5(void) { @@ -365,7 +364,10 @@ static void early_check_vec5(void) vec5 = of_get_flat_dt_prop(chosen, "ibm,architecture-vec-5", &size); if (!vec5) return; - cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; + if (size <= OV5_INDX(OV5_MMU_RADIX_300) || + !(vec5[OV5_INDX(OV5_MMU_RADIX_300)] & OV5_FEAT(OV5_MMU_RADIX_300))) + /* Hypervisor doesn't support radix */ + cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; } void __init mmu_early_init_devtree(void) diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index cfa53ccc8baf..94323c4ececc 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -401,6 +401,8 @@ void __init radix__early_init_mmu(void) mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR); radix_init_partition_table(); radix_init_amor(); + } else { + radix_init_pseries(); } memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE); diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 5dc1c3c6e716..0587655aea69 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -609,6 +609,29 @@ static int __init disable_bulk_remove(char *str) __setup("bulk_remove=", disable_bulk_remove); +/* Actually only used for radix, so far */ +static int pseries_lpar_register_process_table(unsigned long base, + unsigned long page_size, unsigned long table_size) +{ + long rc; + unsigned long flags = PROC_TABLE_NEW; + + if (radix_enabled()) + flags |= PROC_TABLE_RADIX | PROC_TABLE_GTSE; + for (;;) { + rc = plpar_hcall_norets(H_REGISTER_PROC_TBL, flags, base, + page_size, table_size); + if (!H_IS_LONG_BUSY(rc)) + break; + mdelay(get_longbusy_msecs(rc)); + } + if (rc != H_SUCCESS) { + pr_err("Failed to register process table (rc=%ld)\n", rc); + BUG(); + } + return rc; +} + void __init hpte_init_pseries(void) { mmu_hash_ops.hpte_invalidate = pSeries_lpar_hpte_invalidate; @@ -622,6 +645,12 @@ void __init hpte_init_pseries(void) mmu_hash_ops.hugepage_invalidate = pSeries_lpar_hugepage_invalidate; } +void radix_init_pseries(void) +{ + pr_info("Using radix MMU under hypervisor\n"); + register_process_table = pseries_lpar_register_process_table; +} + #ifdef CONFIG_PPC_SMLPAR #define CMO_FREE_HINT_DEFAULT 1 static int cmo_free_hint_flag = CMO_FREE_HINT_DEFAULT; -- cgit v1.2.3 From dbcbfee0c81c7938e40d7d6bc659a5191f490b50 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 30 Jan 2017 21:21:37 +1100 Subject: powerpc/64: More definitions for POWER9 This adds definitions for bits in the DSISR register which are used by POWER9 for various translation-related exception conditions, and for some more bits in the partition table entry that will be needed by KVM. Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/mmu.h | 12 +++++++++++- arch/powerpc/include/asm/reg.h | 4 ++++ 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index cea522c3bcae..d73e9dfa5237 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -44,10 +44,20 @@ struct patb_entry { }; extern struct patb_entry *partition_tb; +/* Bits in patb0 field */ #define PATB_HR (1UL << 63) -#define PATB_GR (1UL << 63) #define RPDB_MASK 0x0ffffffffffff00fUL #define RPDB_SHIFT (1UL << 8) +#define RTS1_SHIFT 61 /* top 2 bits of radix tree size */ +#define RTS1_MASK (3UL << RTS1_SHIFT) +#define RTS2_SHIFT 5 /* bottom 3 bits of radix tree size */ +#define RTS2_MASK (7UL << RTS2_SHIFT) +#define RPDS_MASK 0x1f /* root page dir. size field */ + +/* Bits in patb1 field */ +#define PATB_GR (1UL << 63) /* guest uses radix; must match HR */ +#define PRTS_MASK 0x1f /* process table size field */ + /* * Limit process table to PAGE_SIZE table. This * also limit the max pid we can support. diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 0d4531aa2052..aa44a83ad3ec 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -274,10 +274,14 @@ #define SPRN_DSISR 0x012 /* Data Storage Interrupt Status Register */ #define DSISR_NOHPTE 0x40000000 /* no translation found */ #define DSISR_PROTFAULT 0x08000000 /* protection fault */ +#define DSISR_BADACCESS 0x04000000 /* bad access to CI or G */ #define DSISR_ISSTORE 0x02000000 /* access was a store */ #define DSISR_DABRMATCH 0x00400000 /* hit data breakpoint */ #define DSISR_NOSEGMENT 0x00200000 /* SLB miss */ #define DSISR_KEYFAULT 0x00200000 /* Key fault */ +#define DSISR_UNSUPP_MMU 0x00080000 /* Unsupported MMU config */ +#define DSISR_SET_RC 0x00040000 /* Failed setting of R/C bits */ +#define DSISR_PGDIRFAULT 0x00020000 /* Fault on page directory */ #define SPRN_TBRL 0x10C /* Time Base Read Lower Register (user, R/O) */ #define SPRN_TBRU 0x10D /* Time Base Read Upper Register (user, R/O) */ #define SPRN_CIR 0x11B /* Chip Information Register (hyper, R/0) */ -- cgit v1.2.3 From bc3551257af837fc603d295e59f9e32953525b98 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 30 Jan 2017 21:21:40 +1100 Subject: powerpc/64: Allow for relocation-on interrupts from guest to host With host and guest both using radix translation, it is feasible for the host to take interrupts that come from the guest with relocation on, and that is in fact what the POWER9 hardware will do when LPCR[AIL] = 3. All such interrupts use HSRR0/1 not SRR0/1 except for system call with LEV=1 (hcall). Therefore this adds the KVM tests to the _HV variants of the relocation-on interrupt handlers, and adds the KVM test to the relocation-on system call entry point. We also instantiate the relocation-on versions of the hypervisor data storage and instruction interrupt handlers, since these can occur with relocation on in radix guests. Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/exception-64s.h | 10 +++--- arch/powerpc/kernel/exceptions-64s.S | 53 +++++++++++++++++--------------- 2 files changed, 34 insertions(+), 29 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 9a5dbfb2d9f2..8fa09fa500f0 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -428,12 +428,12 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_STD) #define STD_RELON_EXCEPTION_HV(loc, vec, label) \ - /* No guest interrupts come through here */ \ SET_SCRATCH0(r13); /* save r13 */ \ - EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label, EXC_HV, NOTEST, vec); + EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label, \ + EXC_HV, KVMTEST_HV, vec); #define STD_RELON_EXCEPTION_HV_OOL(vec, label) \ - EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, vec); \ + EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_HV, vec); \ EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_HV) /* This associate vector numbers with bits in paca->irq_happened */ @@ -510,10 +510,10 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) #define MASKABLE_RELON_EXCEPTION_HV(loc, vec, label) \ _MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, \ - EXC_HV, SOFTEN_NOTEST_HV) + EXC_HV, SOFTEN_TEST_HV) #define MASKABLE_RELON_EXCEPTION_HV_OOL(vec, label) \ - EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_HV, vec); \ + EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec); \ EXCEPTION_PROLOG_PSERIES_1(label, EXC_HV) /* diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 65a2559eeb7f..34a04a5fa468 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -830,6 +830,31 @@ EXC_VIRT(trap_0b, 0x4b00, 0x4c00, 0xb00) TRAMP_KVM(PACA_EXGEN, 0xb00) EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER + /* + * If CONFIG_KVM_BOOK3S_64_HANDLER is set, save the PPR (on systems + * that support it) before changing to HMT_MEDIUM. That allows the KVM + * code to save that value into the guest state (it is the guest's PPR + * value). Otherwise just change to HMT_MEDIUM as userspace has + * already saved the PPR. + */ +#define SYSCALL_KVMTEST \ + SET_SCRATCH0(r13); \ + GET_PACA(r13); \ + std r9,PACA_EXGEN+EX_R9(r13); \ + OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR); \ + HMT_MEDIUM; \ + std r10,PACA_EXGEN+EX_R10(r13); \ + OPT_SAVE_REG_TO_PACA(PACA_EXGEN+EX_PPR, r9, CPU_FTR_HAS_PPR); \ + mfcr r9; \ + KVMTEST_PR(0xc00); \ + GET_SCRATCH0(r13) + +#else +#define SYSCALL_KVMTEST \ + HMT_MEDIUM +#endif + #define LOAD_SYSCALL_HANDLER(reg) \ __LOAD_HANDLER(reg, system_call_common) @@ -883,34 +908,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \ #endif EXC_REAL_BEGIN(system_call, 0xc00, 0xd00) - /* - * If CONFIG_KVM_BOOK3S_64_HANDLER is set, save the PPR (on systems - * that support it) before changing to HMT_MEDIUM. That allows the KVM - * code to save that value into the guest state (it is the guest's PPR - * value). Otherwise just change to HMT_MEDIUM as userspace has - * already saved the PPR. - */ -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER - SET_SCRATCH0(r13) - GET_PACA(r13) - std r9,PACA_EXGEN+EX_R9(r13) - OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR); - HMT_MEDIUM; - std r10,PACA_EXGEN+EX_R10(r13) - OPT_SAVE_REG_TO_PACA(PACA_EXGEN+EX_PPR, r9, CPU_FTR_HAS_PPR); - mfcr r9 - KVMTEST_PR(0xc00) - GET_SCRATCH0(r13) -#else - HMT_MEDIUM; -#endif + SYSCALL_KVMTEST SYSCALL_PSERIES_1 SYSCALL_PSERIES_2_RFID SYSCALL_PSERIES_3 EXC_REAL_END(system_call, 0xc00, 0xd00) EXC_VIRT_BEGIN(system_call, 0x4c00, 0x4d00) - HMT_MEDIUM + SYSCALL_KVMTEST SYSCALL_PSERIES_1 SYSCALL_PSERIES_2_DIRECT SYSCALL_PSERIES_3 @@ -925,7 +930,7 @@ TRAMP_KVM(PACA_EXGEN, 0xd00) EXC_COMMON(single_step_common, 0xd00, single_step_exception) EXC_REAL_OOL_HV(h_data_storage, 0xe00, 0xe20) -EXC_VIRT_NONE(0x4e00, 0x4e20) +EXC_VIRT_OOL_HV(h_data_storage, 0x4e00, 0x4e20, 0xe00) TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0xe00) EXC_COMMON_BEGIN(h_data_storage_common) mfspr r10,SPRN_HDAR @@ -941,7 +946,7 @@ EXC_COMMON_BEGIN(h_data_storage_common) EXC_REAL_OOL_HV(h_instr_storage, 0xe20, 0xe40) -EXC_VIRT_NONE(0x4e20, 0x4e40) +EXC_VIRT_OOL_HV(h_instr_storage, 0x4e20, 0x4e40, 0xe20) TRAMP_KVM_HV(PACA_EXGEN, 0xe20) EXC_COMMON(h_instr_storage_common, 0xe20, unknown_exception) -- cgit v1.2.3 From c92701322711682de89b2bd0f32affad040b6e86 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 30 Jan 2017 21:21:41 +1100 Subject: KVM: PPC: Book3S HV: Add userspace interfaces for POWER9 MMU This adds two capabilities and two ioctls to allow userspace to find out about and configure the POWER9 MMU in a guest. The two capabilities tell userspace whether KVM can support a guest using the radix MMU, or using the hashed page table (HPT) MMU with a process table and segment tables. (Note that the MMUs in the POWER9 processor cores do not use the process and segment tables when in HPT mode, but the nest MMU does). The KVM_PPC_CONFIGURE_V3_MMU ioctl allows userspace to specify whether a guest will use the radix MMU or the HPT MMU, and to specify the size and location (in guest space) of the process table. The KVM_PPC_GET_RMMU_INFO ioctl gives userspace information about the radix MMU. It returns a list of supported radix tree geometries (base page size and number of bits indexed at each level of the radix tree) and the encoding used to specify the various page sizes for the TLB invalidate entry instruction. Initially, both capabilities return 0 and the ioctls return -EINVAL, until the necessary infrastructure for them to operate correctly is added. Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- Documentation/virtual/kvm/api.txt | 83 +++++++++++++++++++++++++++++++++++++ arch/powerpc/include/asm/kvm_ppc.h | 2 + arch/powerpc/include/uapi/asm/kvm.h | 20 +++++++++ arch/powerpc/kvm/book3s_hv.c | 13 ++++++ arch/powerpc/kvm/powerpc.c | 32 ++++++++++++++ include/uapi/linux/kvm.h | 6 +++ 6 files changed, 156 insertions(+) (limited to 'arch/powerpc/include') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 03145b7cafaa..4470671b0c26 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -3201,6 +3201,71 @@ struct kvm_reinject_control { pit_reinject = 0 (!reinject mode) is recommended, unless running an old operating system that uses the PIT for timing (e.g. Linux 2.4.x). +4.99 KVM_PPC_CONFIGURE_V3_MMU + +Capability: KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 +Architectures: ppc +Type: vm ioctl +Parameters: struct kvm_ppc_mmuv3_cfg (in) +Returns: 0 on success, + -EFAULT if struct kvm_ppc_mmuv3_cfg cannot be read, + -EINVAL if the configuration is invalid + +This ioctl controls whether the guest will use radix or HPT (hashed +page table) translation, and sets the pointer to the process table for +the guest. + +struct kvm_ppc_mmuv3_cfg { + __u64 flags; + __u64 process_table; +}; + +There are two bits that can be set in flags; KVM_PPC_MMUV3_RADIX and +KVM_PPC_MMUV3_GTSE. KVM_PPC_MMUV3_RADIX, if set, configures the guest +to use radix tree translation, and if clear, to use HPT translation. +KVM_PPC_MMUV3_GTSE, if set and if KVM permits it, configures the guest +to be able to use the global TLB and SLB invalidation instructions; +if clear, the guest may not use these instructions. + +The process_table field specifies the address and size of the guest +process table, which is in the guest's space. This field is formatted +as the second doubleword of the partition table entry, as defined in +the Power ISA V3.00, Book III section 5.7.6.1. + +4.100 KVM_PPC_GET_RMMU_INFO + +Capability: KVM_CAP_PPC_RADIX_MMU +Architectures: ppc +Type: vm ioctl +Parameters: struct kvm_ppc_rmmu_info (out) +Returns: 0 on success, + -EFAULT if struct kvm_ppc_rmmu_info cannot be written, + -EINVAL if no useful information can be returned + +This ioctl returns a structure containing two things: (a) a list +containing supported radix tree geometries, and (b) a list that maps +page sizes to put in the "AP" (actual page size) field for the tlbie +(TLB invalidate entry) instruction. + +struct kvm_ppc_rmmu_info { + struct kvm_ppc_radix_geom { + __u8 page_shift; + __u8 level_bits[4]; + __u8 pad[3]; + } geometries[8]; + __u32 ap_encodings[8]; +}; + +The geometries[] field gives up to 8 supported geometries for the +radix page table, in terms of the log base 2 of the smallest page +size, and the number of bits indexed at each level of the tree, from +the PTE level up to the PGD level in that order. Any unused entries +will have 0 in the page_shift field. + +The ap_encodings gives the supported page sizes and their AP field +encodings, encoded with the AP value in the top 3 bits and the log +base 2 of the page size in the bottom 6 bits. + 5. The kvm_run structure ------------------------ @@ -3942,3 +4007,21 @@ In order to use SynIC, it has to be activated by setting this capability via KVM_ENABLE_CAP ioctl on the vcpu fd. Note that this will disable the use of APIC hardware virtualization even if supported by the CPU, as it's incompatible with SynIC auto-EOI behavior. + +8.3 KVM_CAP_PPC_RADIX_MMU + +Architectures: ppc + +This capability, if KVM_CHECK_EXTENSION indicates that it is +available, means that that the kernel can support guests using the +radix MMU defined in Power ISA V3.00 (as implemented in the POWER9 +processor). + +8.4 KVM_CAP_PPC_HASH_MMU_V3 + +Architectures: ppc + +This capability, if KVM_CHECK_EXTENSION indicates that it is +available, means that that the kernel can support guests using the +hashed page table MMU defined in Power ISA V3.00 (as implemented in +the POWER9 processor), including in-memory segment tables. diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 2da67bf1f2ec..48c760f89590 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -291,6 +291,8 @@ struct kvmppc_ops { struct irq_bypass_producer *); void (*irq_bypass_del_producer)(struct irq_bypass_consumer *, struct irq_bypass_producer *); + int (*configure_mmu)(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg); + int (*get_rmmu_info)(struct kvm *kvm, struct kvm_ppc_rmmu_info *info); }; extern struct kvmppc_ops *kvmppc_hv_ops; diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index 3603b6f51b11..cc0908b6c2a0 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -413,6 +413,26 @@ struct kvm_get_htab_header { __u16 n_invalid; }; +/* For KVM_PPC_CONFIGURE_V3_MMU */ +struct kvm_ppc_mmuv3_cfg { + __u64 flags; + __u64 process_table; /* second doubleword of partition table entry */ +}; + +/* Flag values for KVM_PPC_CONFIGURE_V3_MMU */ +#define KVM_PPC_MMUV3_RADIX 1 /* 1 = radix mode, 0 = HPT */ +#define KVM_PPC_MMUV3_GTSE 2 /* global translation shootdown enb. */ + +/* For KVM_PPC_GET_RMMU_INFO */ +struct kvm_ppc_rmmu_info { + struct kvm_ppc_radix_geom { + __u8 page_shift; + __u8 level_bits[4]; + __u8 pad[3]; + } geometries[8]; + __u32 ap_encodings[8]; +}; + /* Per-vcpu XICS interrupt controller state */ #define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index ec34e39471a7..5f08ed070ae5 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3657,6 +3657,17 @@ static void init_default_hcalls(void) } } +/* dummy implementations for now */ +static int kvmhv_configure_mmu(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg) +{ + return -EINVAL; +} + +static int kvmhv_get_rmmu_info(struct kvm *kvm, struct kvm_ppc_rmmu_info *info) +{ + return -EINVAL; +} + static struct kvmppc_ops kvm_ops_hv = { .get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv, .set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv, @@ -3694,6 +3705,8 @@ static struct kvmppc_ops kvm_ops_hv = { .irq_bypass_add_producer = kvmppc_irq_bypass_add_producer_hv, .irq_bypass_del_producer = kvmppc_irq_bypass_del_producer_hv, #endif + .configure_mmu = kvmhv_configure_mmu, + .get_rmmu_info = kvmhv_get_rmmu_info, }; static int kvm_init_subcore_bitmap(void) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index cd892dec7cb6..38c0d154c01e 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -565,6 +565,13 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_PPC_HWRNG: r = kvmppc_hwrng_present(); break; + case KVM_CAP_PPC_MMU_RADIX: + r = !!(0 && hv_enabled && radix_enabled()); + break; + case KVM_CAP_PPC_MMU_HASH_V3: + r = !!(0 && hv_enabled && !radix_enabled() && + cpu_has_feature(CPU_FTR_ARCH_300)); + break; #endif case KVM_CAP_SYNC_MMU: #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE @@ -1468,6 +1475,31 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_rtas_define_token(kvm, argp); break; } + case KVM_PPC_CONFIGURE_V3_MMU: { + struct kvm *kvm = filp->private_data; + struct kvm_ppc_mmuv3_cfg cfg; + + r = -EINVAL; + if (!kvm->arch.kvm_ops->configure_mmu) + goto out; + r = -EFAULT; + if (copy_from_user(&cfg, argp, sizeof(cfg))) + goto out; + r = kvm->arch.kvm_ops->configure_mmu(kvm, &cfg); + break; + } + case KVM_PPC_GET_RMMU_INFO: { + struct kvm *kvm = filp->private_data; + struct kvm_ppc_rmmu_info info; + + r = -EINVAL; + if (!kvm->arch.kvm_ops->get_rmmu_info) + goto out; + r = kvm->arch.kvm_ops->get_rmmu_info(kvm, &info); + if (r >= 0 && copy_to_user(argp, &info, sizeof(info))) + r = -EFAULT; + break; + } default: { struct kvm *kvm = filp->private_data; r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg); diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index cac48eda1075..e0035808c814 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -871,6 +871,8 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_S390_USER_INSTR0 130 #define KVM_CAP_MSI_DEVID 131 #define KVM_CAP_PPC_HTM 132 +#define KVM_CAP_PPC_MMU_RADIX 134 +#define KVM_CAP_PPC_MMU_HASH_V3 135 #ifdef KVM_CAP_IRQ_ROUTING @@ -1187,6 +1189,10 @@ struct kvm_s390_ucas_mapping { #define KVM_ARM_SET_DEVICE_ADDR _IOW(KVMIO, 0xab, struct kvm_arm_device_addr) /* Available with KVM_CAP_PPC_RTAS */ #define KVM_PPC_RTAS_DEFINE_TOKEN _IOW(KVMIO, 0xac, struct kvm_rtas_token_args) +/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 */ +#define KVM_PPC_CONFIGURE_V3_MMU _IOW(KVMIO, 0xaf, struct kvm_ppc_mmuv3_cfg) +/* Available with KVM_CAP_PPC_RADIX_MMU */ +#define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) -- cgit v1.2.3 From 468808bd35c4aa3cf7d9fde0ebb010270038734b Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 30 Jan 2017 21:21:42 +1100 Subject: KVM: PPC: Book3S HV: Set process table for HPT guests on POWER9 This adds the implementation of the KVM_PPC_CONFIGURE_V3_MMU ioctl for HPT guests on POWER9. With this, we can return 1 for the KVM_CAP_PPC_MMU_HASH_V3 capability. Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/kvm_host.h | 1 + arch/powerpc/kvm/book3s_hv.c | 35 +++++++++++++++++++++++++++++++---- arch/powerpc/kvm/powerpc.c | 2 +- 3 files changed, 33 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index e59b172666cd..944532dc4a57 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -264,6 +264,7 @@ struct kvm_arch { atomic_t hpte_mod_interest; cpumask_t need_tlb_flush; int hpt_cma_alloc; + u64 process_table; struct dentry *debugfs_dir; struct dentry *htab_dentry; #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 5f08ed070ae5..bb2854314ba4 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3091,8 +3091,8 @@ static void kvmppc_setup_partition_table(struct kvm *kvm) /* HTABSIZE and HTABORG fields */ dw0 |= kvm->arch.sdr1; - /* Second dword has GR=0; other fields are unused since UPRT=0 */ - dw1 = 0; + /* Second dword as set by userspace */ + dw1 = kvm->arch.process_table; mmu_partition_table_set_entry(kvm->arch.lpid, dw0, dw1); } @@ -3657,10 +3657,37 @@ static void init_default_hcalls(void) } } -/* dummy implementations for now */ static int kvmhv_configure_mmu(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg) { - return -EINVAL; + unsigned long lpcr; + + /* If not on a POWER9, reject it */ + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + return -ENODEV; + + /* If any unknown flags set, reject it */ + if (cfg->flags & ~(KVM_PPC_MMUV3_RADIX | KVM_PPC_MMUV3_GTSE)) + return -EINVAL; + + /* We can't do radix yet */ + if (cfg->flags & KVM_PPC_MMUV3_RADIX) + return -EINVAL; + + /* GR (guest radix) bit in process_table field must match */ + if (cfg->process_table & PATB_GR) + return -EINVAL; + + /* Process table size field must be reasonable, i.e. <= 24 */ + if ((cfg->process_table & PRTS_MASK) > 24) + return -EINVAL; + + kvm->arch.process_table = cfg->process_table; + kvmppc_setup_partition_table(kvm); + + lpcr = (cfg->flags & KVM_PPC_MMUV3_GTSE) ? LPCR_GTSE : 0; + kvmppc_update_lpcr(kvm, lpcr, LPCR_GTSE); + + return 0; } static int kvmhv_get_rmmu_info(struct kvm *kvm, struct kvm_ppc_rmmu_info *info) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 38c0d154c01e..1476a480745e 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -569,7 +569,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = !!(0 && hv_enabled && radix_enabled()); break; case KVM_CAP_PPC_MMU_HASH_V3: - r = !!(0 && hv_enabled && !radix_enabled() && + r = !!(hv_enabled && !radix_enabled() && cpu_has_feature(CPU_FTR_ARCH_300)); break; #endif -- cgit v1.2.3 From 9e04ba69beec372ddf857c700ff922e95f50b0d0 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 30 Jan 2017 21:21:44 +1100 Subject: KVM: PPC: Book3S HV: Add basic infrastructure for radix guests This adds a field in struct kvm_arch and an inline helper to indicate whether a guest is a radix guest or not, plus a new file to contain the radix MMU code, which currently contains just a translate function which knows how to traverse the guest page tables to translate an address. Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/kvm_book3s.h | 3 + arch/powerpc/include/asm/kvm_book3s_64.h | 6 ++ arch/powerpc/include/asm/kvm_host.h | 2 + arch/powerpc/kvm/Makefile | 3 +- arch/powerpc/kvm/book3s_64_mmu_hv.c | 10 ++- arch/powerpc/kvm/book3s_64_mmu_radix.c | 139 +++++++++++++++++++++++++++++++ 6 files changed, 160 insertions(+), 3 deletions(-) create mode 100644 arch/powerpc/kvm/book3s_64_mmu_radix.c (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 5cf306ae0ac3..7adfcc03a35f 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -182,6 +182,9 @@ extern void kvmppc_mmu_hpte_sysexit(void); extern int kvmppc_mmu_hv_init(void); extern int kvmppc_book3s_hcall_implemented(struct kvm *kvm, unsigned long hc); +extern int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, + struct kvmppc_pte *gpte, bool data, bool iswrite); + /* XXX remove this export when load_last_inst() is generic */ extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data); extern void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec); diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 848292176908..0db010cc4e65 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -36,6 +36,12 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu) #endif #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + +static inline bool kvm_is_radix(struct kvm *kvm) +{ + return kvm->arch.radix; +} + #define KVM_DEFAULT_HPT_ORDER 24 /* 16MB HPT by default */ #endif diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 944532dc4a57..fb73518bd03b 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -264,6 +264,8 @@ struct kvm_arch { atomic_t hpte_mod_interest; cpumask_t need_tlb_flush; int hpt_cma_alloc; + u8 radix; + pgd_t *pgtable; u64 process_table; struct dentry *debugfs_dir; struct dentry *htab_dentry; diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 7dd89b79d038..b87ccde2137a 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -70,7 +70,8 @@ endif kvm-hv-y += \ book3s_hv.o \ book3s_hv_interrupts.o \ - book3s_64_mmu_hv.o + book3s_64_mmu_hv.o \ + book3s_64_mmu_radix.o kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \ book3s_hv_rm_xics.o diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index b795dd1ac2ef..c208bf3b252f 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -119,6 +119,9 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp) long err = -EBUSY; long order; + if (kvm_is_radix(kvm)) + return -EINVAL; + mutex_lock(&kvm->lock); if (kvm->arch.hpte_setup_done) { kvm->arch.hpte_setup_done = 0; @@ -157,7 +160,7 @@ void kvmppc_free_hpt(struct kvm *kvm) if (kvm->arch.hpt_cma_alloc) kvm_release_hpt(virt_to_page(kvm->arch.hpt_virt), 1 << (kvm->arch.hpt_order - PAGE_SHIFT)); - else + else if (kvm->arch.hpt_virt) free_pages(kvm->arch.hpt_virt, kvm->arch.hpt_order - PAGE_SHIFT); } @@ -1675,7 +1678,10 @@ void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu) vcpu->arch.slb_nr = 32; /* POWER7/POWER8 */ - mmu->xlate = kvmppc_mmu_book3s_64_hv_xlate; + if (kvm_is_radix(vcpu->kvm)) + mmu->xlate = kvmppc_mmu_radix_xlate; + else + mmu->xlate = kvmppc_mmu_book3s_64_hv_xlate; mmu->reset_msr = kvmppc_mmu_book3s_64_hv_reset_msr; vcpu->arch.hflags |= BOOK3S_HFLAG_SLB; diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c new file mode 100644 index 000000000000..9091407fbfd4 --- /dev/null +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -0,0 +1,139 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * Copyright 2016 Paul Mackerras, IBM Corp. + */ + +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +/* + * Supported radix tree geometry. + * Like p9, we support either 5 or 9 bits at the first (lowest) level, + * for a page size of 64k or 4k. + */ +static int p9_supported_radix_bits[4] = { 5, 9, 9, 13 }; + +int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, + struct kvmppc_pte *gpte, bool data, bool iswrite) +{ + struct kvm *kvm = vcpu->kvm; + u32 pid; + int ret, level, ps; + __be64 prte, rpte; + unsigned long root, pte, index; + unsigned long rts, bits, offset; + unsigned long gpa; + unsigned long proc_tbl_size; + + /* Work out effective PID */ + switch (eaddr >> 62) { + case 0: + pid = vcpu->arch.pid; + break; + case 3: + pid = 0; + break; + default: + return -EINVAL; + } + proc_tbl_size = 1 << ((kvm->arch.process_table & PRTS_MASK) + 12); + if (pid * 16 >= proc_tbl_size) + return -EINVAL; + + /* Read partition table to find root of tree for effective PID */ + ret = kvm_read_guest(kvm, kvm->arch.process_table + pid * 16, + &prte, sizeof(prte)); + if (ret) + return ret; + + root = be64_to_cpu(prte); + rts = ((root & RTS1_MASK) >> (RTS1_SHIFT - 3)) | + ((root & RTS2_MASK) >> RTS2_SHIFT); + bits = root & RPDS_MASK; + root = root & RPDB_MASK; + + /* P9 DD1 interprets RTS (radix tree size) differently */ + offset = rts + 31; + if (cpu_has_feature(CPU_FTR_POWER9_DD1)) + offset -= 3; + + /* current implementations only support 52-bit space */ + if (offset != 52) + return -EINVAL; + + for (level = 3; level >= 0; --level) { + if (level && bits != p9_supported_radix_bits[level]) + return -EINVAL; + if (level == 0 && !(bits == 5 || bits == 9)) + return -EINVAL; + offset -= bits; + index = (eaddr >> offset) & ((1UL << bits) - 1); + /* check that low bits of page table base are zero */ + if (root & ((1UL << (bits + 3)) - 1)) + return -EINVAL; + ret = kvm_read_guest(kvm, root + index * 8, + &rpte, sizeof(rpte)); + if (ret) + return ret; + pte = __be64_to_cpu(rpte); + if (!(pte & _PAGE_PRESENT)) + return -ENOENT; + if (pte & _PAGE_PTE) + break; + bits = pte & 0x1f; + root = pte & 0x0fffffffffffff00ul; + } + /* need a leaf at lowest level; 512GB pages not supported */ + if (level < 0 || level == 3) + return -EINVAL; + + /* offset is now log base 2 of the page size */ + gpa = pte & 0x01fffffffffff000ul; + if (gpa & ((1ul << offset) - 1)) + return -EINVAL; + gpa += eaddr & ((1ul << offset) - 1); + for (ps = MMU_PAGE_4K; ps < MMU_PAGE_COUNT; ++ps) + if (offset == mmu_psize_defs[ps].shift) + break; + gpte->page_size = ps; + + gpte->eaddr = eaddr; + gpte->raddr = gpa; + + /* Work out permissions */ + gpte->may_read = !!(pte & _PAGE_READ); + gpte->may_write = !!(pte & _PAGE_WRITE); + gpte->may_execute = !!(pte & _PAGE_EXEC); + if (kvmppc_get_msr(vcpu) & MSR_PR) { + if (pte & _PAGE_PRIVILEGED) { + gpte->may_read = 0; + gpte->may_write = 0; + gpte->may_execute = 0; + } + } else { + if (!(pte & _PAGE_PRIVILEGED)) { + /* Check AMR/IAMR to see if strict mode is in force */ + if (vcpu->arch.amr & (1ul << 62)) + gpte->may_read = 0; + if (vcpu->arch.amr & (1ul << 63)) + gpte->may_write = 0; + if (vcpu->arch.iamr & (1ul << 62)) + gpte->may_execute = 0; + } + } + + return 0; +} + -- cgit v1.2.3 From f4c51f841d2ac7d36cacb84efbc383190861f87c Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 30 Jan 2017 21:21:45 +1100 Subject: KVM: PPC: Book3S HV: Modify guest entry/exit paths to handle radix guests This adds code to branch around the parts that radix guests don't need - clearing and loading the SLB with the guest SLB contents, saving the guest SLB contents on exit, and restoring the host SLB contents. Since the host is now using radix, we need to save and restore the host value for the PID register. On hypervisor data/instruction storage interrupts, we don't do the guest HPT lookup on radix, but just save the guest physical address for the fault (from the ASDR register) in the vcpu struct. Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/kvm_host.h | 1 + arch/powerpc/kernel/asm-offsets.c | 2 ++ arch/powerpc/kvm/book3s_hv_rmhandlers.S | 57 ++++++++++++++++++++++++++------- 3 files changed, 49 insertions(+), 11 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index fb73518bd03b..da1421a4d6f2 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -606,6 +606,7 @@ struct kvm_vcpu_arch { ulong fault_dar; u32 fault_dsisr; unsigned long intr_msr; + ulong fault_gpa; /* guest real address of page fault (POWER9) */ #endif #ifdef CONFIG_BOOKE diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 0601e6a7297c..3afa0ad9837f 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -498,6 +498,7 @@ int main(void) DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits)); DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls)); DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v)); + DEFINE(KVM_RADIX, offsetof(struct kvm, arch.radix)); DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr)); DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar)); DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa.pinned_addr)); @@ -537,6 +538,7 @@ int main(void) DEFINE(VCPU_SLB_NR, offsetof(struct kvm_vcpu, arch.slb_nr)); DEFINE(VCPU_FAULT_DSISR, offsetof(struct kvm_vcpu, arch.fault_dsisr)); DEFINE(VCPU_FAULT_DAR, offsetof(struct kvm_vcpu, arch.fault_dar)); + DEFINE(VCPU_FAULT_GPA, offsetof(struct kvm_vcpu, arch.fault_gpa)); DEFINE(VCPU_INTR_MSR, offsetof(struct kvm_vcpu, arch.intr_msr)); DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst)); DEFINE(VCPU_TRAP, offsetof(struct kvm_vcpu, arch.trap)); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 01f4392a284d..7fc7a9221509 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -518,6 +518,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* Stack frame offsets */ #define STACK_SLOT_TID (112-16) #define STACK_SLOT_PSSCR (112-24) +#define STACK_SLOT_PID (112-32) .global kvmppc_hv_entry kvmppc_hv_entry: @@ -530,6 +531,7 @@ kvmppc_hv_entry: * R1 = host R1 * R2 = TOC * all other volatile GPRS = free + * Does not preserve non-volatile GPRs or CR fields */ mflr r0 std r0, PPC_LR_STKOFF(r1) @@ -549,32 +551,38 @@ kvmppc_hv_entry: bl kvmhv_start_timing 1: #endif - /* Clear out SLB */ + + /* Use cr7 as an indication of radix mode */ + ld r5, HSTATE_KVM_VCORE(r13) + ld r9, VCORE_KVM(r5) /* pointer to struct kvm */ + lbz r0, KVM_RADIX(r9) + cmpwi cr7, r0, 0 + + /* Clear out SLB if hash */ + bne cr7, 2f li r6,0 slbmte r6,r6 slbia ptesync - +2: /* * POWER7/POWER8 host -> guest partition switch code. * We don't have to lock against concurrent tlbies, * but we do have to coordinate across hardware threads. */ /* Set bit in entry map iff exit map is zero. */ - ld r5, HSTATE_KVM_VCORE(r13) li r7, 1 lbz r6, HSTATE_PTID(r13) sld r7, r7, r6 - addi r9, r5, VCORE_ENTRY_EXIT -21: lwarx r3, 0, r9 + addi r8, r5, VCORE_ENTRY_EXIT +21: lwarx r3, 0, r8 cmpwi r3, 0x100 /* any threads starting to exit? */ bge secondary_too_late /* if so we're too late to the party */ or r3, r3, r7 - stwcx. r3, 0, r9 + stwcx. r3, 0, r8 bne 21b /* Primary thread switches to guest partition. */ - ld r9,VCORE_KVM(r5) /* pointer to struct kvm */ cmpwi r6,0 bne 10f lwz r7,KVM_LPID(r9) @@ -658,7 +666,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) beq kvmppc_primary_no_guest kvmppc_got_guest: - /* Load up guest SLB entries */ + /* Load up guest SLB entries (N.B. slb_max will be 0 for radix) */ lwz r5,VCPU_SLB_MAX(r4) cmpwi r5,0 beq 9f @@ -696,8 +704,10 @@ kvmppc_got_guest: BEGIN_FTR_SECTION mfspr r5, SPRN_TIDR mfspr r6, SPRN_PSSCR + mfspr r7, SPRN_PID std r5, STACK_SLOT_TID(r1) std r6, STACK_SLOT_PSSCR(r1) + std r7, STACK_SLOT_PID(r1) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) BEGIN_FTR_SECTION @@ -1293,11 +1303,15 @@ mc_cont: mtspr SPRN_CTRLT,r6 4: /* Read the guest SLB and save it away */ + ld r5, VCPU_KVM(r9) + lbz r0, KVM_RADIX(r5) + cmpwi r0, 0 + li r5, 0 + bne 3f /* for radix, save 0 entries */ lwz r0,VCPU_SLB_NR(r9) /* number of entries in SLB */ mtctr r0 li r6,0 addi r7,r9,VCPU_SLB - li r5,0 1: slbmfee r8,r6 andis. r0,r8,SLB_ESID_V@h beq 2f @@ -1309,7 +1323,7 @@ mc_cont: addi r5,r5,1 2: addi r6,r6,1 bdnz 1b - stw r5,VCPU_SLB_MAX(r9) +3: stw r5,VCPU_SLB_MAX(r9) /* * Save the guest PURR/SPURR @@ -1558,8 +1572,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) BEGIN_FTR_SECTION ld r5, STACK_SLOT_TID(r1) ld r6, STACK_SLOT_PSSCR(r1) + ld r7, STACK_SLOT_PID(r1) mtspr SPRN_TIDR, r5 mtspr SPRN_PSSCR, r6 + mtspr SPRN_PID, r7 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) /* @@ -1671,6 +1687,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) isync /* load host SLB entries */ +BEGIN_MMU_FTR_SECTION + b 0f +END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) ld r8,PACA_SLBSHADOWPTR(r13) .rept SLB_NUM_BOLTED @@ -1683,7 +1702,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) slbmte r6,r5 1: addi r8,r8,16 .endr - +0: #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING /* Finish timing, if we have a vcpu */ ld r4, HSTATE_KVM_VCPU(r13) @@ -1710,8 +1729,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) * reflect the HDSI to the guest as a DSI. */ kvmppc_hdsi: + ld r3, VCPU_KVM(r9) + lbz r0, KVM_RADIX(r3) + cmpwi r0, 0 mfspr r4, SPRN_HDAR mfspr r6, SPRN_HDSISR + bne .Lradix_hdsi /* on radix, just save DAR/DSISR/ASDR */ /* HPTE not found fault or protection fault? */ andis. r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h beq 1f /* if not, send it to the guest */ @@ -1788,11 +1811,23 @@ fast_interrupt_c_return: stb r0, HSTATE_IN_GUEST(r13) b guest_exit_cont +.Lradix_hdsi: + std r4, VCPU_FAULT_DAR(r9) + stw r6, VCPU_FAULT_DSISR(r9) +.Lradix_hisi: + mfspr r5, SPRN_ASDR + std r5, VCPU_FAULT_GPA(r9) + b guest_exit_cont + /* * Similarly for an HISI, reflect it to the guest as an ISI unless * it is an HPTE not found fault for a page that we have paged out. */ kvmppc_hisi: + ld r3, VCPU_KVM(r9) + lbz r0, KVM_RADIX(r3) + cmpwi r0, 0 + bne .Lradix_hisi /* for radix, just save ASDR */ andis. r0, r11, SRR1_ISI_NOPT@h beq 1f BEGIN_FTR_SECTION -- cgit v1.2.3 From 5a319350a46572d073042a3194676099dd2c135d Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 30 Jan 2017 21:21:46 +1100 Subject: KVM: PPC: Book3S HV: Page table construction and page faults for radix guests This adds the code to construct the second-level ("partition-scoped" in architecturese) page tables for guests using the radix MMU. Apart from the PGD level, which is allocated when the guest is created, the rest of the tree is all constructed in response to hypervisor page faults. As well as hypervisor page faults for missing pages, we also get faults for reference/change (RC) bits needing to be set, as well as various other error conditions. For now, we only set the R or C bit in the guest page table if the same bit is set in the host PTE for the backing page. This code can take advantage of the guest being backed with either transparent or ordinary 2MB huge pages, and insert 2MB page entries into the guest page tables. There is no support for 1GB huge pages yet. Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/kvm_book3s.h | 8 + arch/powerpc/kvm/book3s.c | 1 + arch/powerpc/kvm/book3s_64_mmu_hv.c | 7 +- arch/powerpc/kvm/book3s_64_mmu_radix.c | 385 +++++++++++++++++++++++++++++++++ arch/powerpc/kvm/book3s_hv.c | 17 +- 5 files changed, 415 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 7adfcc03a35f..ff5cd5c5ce8d 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -170,6 +170,8 @@ extern int kvmppc_book3s_hv_page_fault(struct kvm_run *run, unsigned long status); extern long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, unsigned long valid); +extern int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned long gpa, gva_t ea, int is_store); extern void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte); extern struct hpte_cache *kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu); @@ -182,8 +184,14 @@ extern void kvmppc_mmu_hpte_sysexit(void); extern int kvmppc_mmu_hv_init(void); extern int kvmppc_book3s_hcall_implemented(struct kvm *kvm, unsigned long hc); +extern int kvmppc_book3s_radix_page_fault(struct kvm_run *run, + struct kvm_vcpu *vcpu, + unsigned long ea, unsigned long dsisr); extern int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *gpte, bool data, bool iswrite); +extern void kvmppc_free_radix(struct kvm *kvm); +extern int kvmppc_radix_init(void); +extern void kvmppc_radix_exit(void); /* XXX remove this export when load_last_inst() is generic */ extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data); diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 019f008775b9..b6b5c185bd92 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -239,6 +239,7 @@ void kvmppc_core_queue_data_storage(struct kvm_vcpu *vcpu, ulong dar, kvmppc_set_dsisr(vcpu, flags); kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE); } +EXPORT_SYMBOL_GPL(kvmppc_core_queue_data_storage); /* used by kvm_hv */ void kvmppc_core_queue_inst_storage(struct kvm_vcpu *vcpu, ulong flags) { diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index c208bf3b252f..57690c22716d 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -395,8 +395,8 @@ static int instruction_is_store(unsigned int instr) return (instr & mask) != 0; } -static int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu, - unsigned long gpa, gva_t ea, int is_store) +int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned long gpa, gva_t ea, int is_store) { u32 last_inst; @@ -461,6 +461,9 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned long rcbits; long mmio_update; + if (kvm_is_radix(kvm)) + return kvmppc_book3s_radix_page_fault(run, vcpu, ea, dsisr); + /* * Real-mode code has already searched the HPT and found the * entry we're interested in. Lock the entry and check that diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 9091407fbfd4..865ea9bca364 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -137,3 +137,388 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, return 0; } +#ifdef CONFIG_PPC_64K_PAGES +#define MMU_BASE_PSIZE MMU_PAGE_64K +#else +#define MMU_BASE_PSIZE MMU_PAGE_4K +#endif + +static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr, + unsigned int pshift) +{ + int psize = MMU_BASE_PSIZE; + + if (pshift >= PMD_SHIFT) + psize = MMU_PAGE_2M; + addr &= ~0xfffUL; + addr |= mmu_psize_defs[psize].ap << 5; + asm volatile("ptesync": : :"memory"); + asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1) + : : "r" (addr), "r" (kvm->arch.lpid) : "memory"); + asm volatile("ptesync": : :"memory"); +} + +void kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep, unsigned long clr, + unsigned long set, unsigned long addr, + unsigned int shift) +{ + if (!(clr & _PAGE_PRESENT) && cpu_has_feature(CPU_FTR_POWER9_DD1) && + pte_present(*ptep)) { + /* have to invalidate it first */ + __radix_pte_update(ptep, _PAGE_PRESENT, 0); + kvmppc_radix_tlbie_page(kvm, addr, shift); + set |= _PAGE_PRESENT; + } + __radix_pte_update(ptep, clr, set); +} + +void kvmppc_radix_set_pte_at(struct kvm *kvm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + radix__set_pte_at(kvm->mm, addr, ptep, pte, 0); +} + +static struct kmem_cache *kvm_pte_cache; + +static pte_t *kvmppc_pte_alloc(void) +{ + return kmem_cache_alloc(kvm_pte_cache, GFP_KERNEL); +} + +static void kvmppc_pte_free(pte_t *ptep) +{ + kmem_cache_free(kvm_pte_cache, ptep); +} + +static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, + unsigned int level, unsigned long mmu_seq) +{ + pgd_t *pgd; + pud_t *pud, *new_pud = NULL; + pmd_t *pmd, *new_pmd = NULL; + pte_t *ptep, *new_ptep = NULL; + int ret; + + /* Traverse the guest's 2nd-level tree, allocate new levels needed */ + pgd = kvm->arch.pgtable + pgd_index(gpa); + pud = NULL; + if (pgd_present(*pgd)) + pud = pud_offset(pgd, gpa); + else + new_pud = pud_alloc_one(kvm->mm, gpa); + + pmd = NULL; + if (pud && pud_present(*pud)) + pmd = pmd_offset(pud, gpa); + else + new_pmd = pmd_alloc_one(kvm->mm, gpa); + + if (level == 0 && !(pmd && pmd_present(*pmd))) + new_ptep = kvmppc_pte_alloc(); + + /* Check if we might have been invalidated; let the guest retry if so */ + spin_lock(&kvm->mmu_lock); + ret = -EAGAIN; + if (mmu_notifier_retry(kvm, mmu_seq)) + goto out_unlock; + + /* Now traverse again under the lock and change the tree */ + ret = -ENOMEM; + if (pgd_none(*pgd)) { + if (!new_pud) + goto out_unlock; + pgd_populate(kvm->mm, pgd, new_pud); + new_pud = NULL; + } + pud = pud_offset(pgd, gpa); + if (pud_none(*pud)) { + if (!new_pmd) + goto out_unlock; + pud_populate(kvm->mm, pud, new_pmd); + new_pmd = NULL; + } + pmd = pmd_offset(pud, gpa); + if (pmd_large(*pmd)) { + /* Someone else has instantiated a large page here; retry */ + ret = -EAGAIN; + goto out_unlock; + } + if (level == 1 && !pmd_none(*pmd)) { + /* + * There's a page table page here, but we wanted + * to install a large page. Tell the caller and let + * it try installing a normal page if it wants. + */ + ret = -EBUSY; + goto out_unlock; + } + if (level == 0) { + if (pmd_none(*pmd)) { + if (!new_ptep) + goto out_unlock; + pmd_populate(kvm->mm, pmd, new_ptep); + new_ptep = NULL; + } + ptep = pte_offset_kernel(pmd, gpa); + if (pte_present(*ptep)) { + /* PTE was previously valid, so invalidate it */ + kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT, + 0, gpa, 0); + kvmppc_radix_tlbie_page(kvm, gpa, 0); + } + kvmppc_radix_set_pte_at(kvm, gpa, ptep, pte); + } else { + kvmppc_radix_set_pte_at(kvm, gpa, pmdp_ptep(pmd), pte); + } + ret = 0; + + out_unlock: + spin_unlock(&kvm->mmu_lock); + if (new_pud) + pud_free(kvm->mm, new_pud); + if (new_pmd) + pmd_free(kvm->mm, new_pmd); + if (new_ptep) + kvmppc_pte_free(new_ptep); + return ret; +} + +int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned long ea, unsigned long dsisr) +{ + struct kvm *kvm = vcpu->kvm; + unsigned long mmu_seq, pte_size; + unsigned long gpa, gfn, hva, pfn; + struct kvm_memory_slot *memslot; + struct page *page = NULL, *pages[1]; + long ret, npages, ok; + unsigned int writing; + struct vm_area_struct *vma; + unsigned long flags; + pte_t pte, *ptep; + unsigned long pgflags; + unsigned int shift, level; + + /* Check for unusual errors */ + if (dsisr & DSISR_UNSUPP_MMU) { + pr_err("KVM: Got unsupported MMU fault\n"); + return -EFAULT; + } + if (dsisr & DSISR_BADACCESS) { + /* Reflect to the guest as DSI */ + pr_err("KVM: Got radix HV page fault with DSISR=%lx\n", dsisr); + kvmppc_core_queue_data_storage(vcpu, ea, dsisr); + return RESUME_GUEST; + } + + /* Translate the logical address and get the page */ + gpa = vcpu->arch.fault_gpa & ~0xfffUL; + gpa &= ~0xF000000000000000ul; + gfn = gpa >> PAGE_SHIFT; + if (!(dsisr & DSISR_PGDIRFAULT)) + gpa |= ea & 0xfff; + memslot = gfn_to_memslot(kvm, gfn); + + /* No memslot means it's an emulated MMIO region */ + if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) { + if (dsisr & (DSISR_PGDIRFAULT | DSISR_BADACCESS | + DSISR_SET_RC)) { + /* + * Bad address in guest page table tree, or other + * unusual error - reflect it to the guest as DSI. + */ + kvmppc_core_queue_data_storage(vcpu, ea, dsisr); + return RESUME_GUEST; + } + return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea, + dsisr & DSISR_ISSTORE); + } + + /* used to check for invalidations in progress */ + mmu_seq = kvm->mmu_notifier_seq; + smp_rmb(); + + writing = (dsisr & DSISR_ISSTORE) != 0; + hva = gfn_to_hva_memslot(memslot, gfn); + if (dsisr & DSISR_SET_RC) { + /* + * Need to set an R or C bit in the 2nd-level tables; + * if the relevant bits aren't already set in the linux + * page tables, fall through to do the gup_fast to + * set them in the linux page tables too. + */ + ok = 0; + pgflags = _PAGE_ACCESSED; + if (writing) + pgflags |= _PAGE_DIRTY; + local_irq_save(flags); + ptep = __find_linux_pte_or_hugepte(current->mm->pgd, hva, + NULL, NULL); + if (ptep) { + pte = READ_ONCE(*ptep); + if (pte_present(pte) && + (pte_val(pte) & pgflags) == pgflags) + ok = 1; + } + local_irq_restore(flags); + if (ok) { + spin_lock(&kvm->mmu_lock); + if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) { + spin_unlock(&kvm->mmu_lock); + return RESUME_GUEST; + } + ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, + gpa, NULL, &shift); + if (ptep && pte_present(*ptep)) { + kvmppc_radix_update_pte(kvm, ptep, 0, pgflags, + gpa, shift); + spin_unlock(&kvm->mmu_lock); + return RESUME_GUEST; + } + spin_unlock(&kvm->mmu_lock); + } + } + + ret = -EFAULT; + pfn = 0; + pte_size = PAGE_SIZE; + pgflags = _PAGE_READ | _PAGE_EXEC; + level = 0; + npages = get_user_pages_fast(hva, 1, writing, pages); + if (npages < 1) { + /* Check if it's an I/O mapping */ + down_read(¤t->mm->mmap_sem); + vma = find_vma(current->mm, hva); + if (vma && vma->vm_start <= hva && hva < vma->vm_end && + (vma->vm_flags & VM_PFNMAP)) { + pfn = vma->vm_pgoff + + ((hva - vma->vm_start) >> PAGE_SHIFT); + pgflags = pgprot_val(vma->vm_page_prot); + } + up_read(¤t->mm->mmap_sem); + if (!pfn) + return -EFAULT; + } else { + page = pages[0]; + pfn = page_to_pfn(page); + if (PageHuge(page)) { + page = compound_head(page); + pte_size <<= compound_order(page); + /* See if we can insert a 2MB large-page PTE here */ + if (pte_size >= PMD_SIZE && + (gpa & PMD_MASK & PAGE_MASK) == + (hva & PMD_MASK & PAGE_MASK)) { + level = 1; + pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1); + } + } + /* See if we can provide write access */ + if (writing) { + /* + * We assume gup_fast has set dirty on the host PTE. + */ + pgflags |= _PAGE_WRITE; + } else { + local_irq_save(flags); + ptep = __find_linux_pte_or_hugepte(current->mm->pgd, + hva, NULL, NULL); + if (ptep && pte_write(*ptep) && pte_dirty(*ptep)) + pgflags |= _PAGE_WRITE; + local_irq_restore(flags); + } + } + + /* + * Compute the PTE value that we need to insert. + */ + pgflags |= _PAGE_PRESENT | _PAGE_PTE | _PAGE_ACCESSED; + if (pgflags & _PAGE_WRITE) + pgflags |= _PAGE_DIRTY; + pte = pfn_pte(pfn, __pgprot(pgflags)); + + /* Allocate space in the tree and write the PTE */ + ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq); + if (ret == -EBUSY) { + /* + * There's already a PMD where wanted to install a large page; + * for now, fall back to installing a small page. + */ + level = 0; + pfn |= gfn & ((PMD_SIZE >> PAGE_SHIFT) - 1); + pte = pfn_pte(pfn, __pgprot(pgflags)); + ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq); + } + if (ret == 0 || ret == -EAGAIN) + ret = RESUME_GUEST; + + if (page) { + /* + * We drop pages[0] here, not page because page might + * have been set to the head page of a compound, but + * we have to drop the reference on the correct tail + * page to match the get inside gup() + */ + put_page(pages[0]); + } + return ret; +} + +void kvmppc_free_radix(struct kvm *kvm) +{ + unsigned long ig, iu, im; + pte_t *pte; + pmd_t *pmd; + pud_t *pud; + pgd_t *pgd; + + if (!kvm->arch.pgtable) + return; + pgd = kvm->arch.pgtable; + for (ig = 0; ig < PTRS_PER_PGD; ++ig, ++pgd) { + if (!pgd_present(*pgd)) + continue; + pud = pud_offset(pgd, 0); + for (iu = 0; iu < PTRS_PER_PUD; ++iu, ++pud) { + if (!pud_present(*pud)) + continue; + pmd = pmd_offset(pud, 0); + for (im = 0; im < PTRS_PER_PMD; ++im, ++pmd) { + if (pmd_huge(*pmd)) { + pmd_clear(pmd); + continue; + } + if (!pmd_present(*pmd)) + continue; + pte = pte_offset_map(pmd, 0); + memset(pte, 0, sizeof(long) << PTE_INDEX_SIZE); + kvmppc_pte_free(pte); + pmd_clear(pmd); + } + pmd_free(kvm->mm, pmd_offset(pud, 0)); + pud_clear(pud); + } + pud_free(kvm->mm, pud_offset(pgd, 0)); + pgd_clear(pgd); + } + pgd_free(kvm->mm, kvm->arch.pgtable); +} + +static void pte_ctor(void *addr) +{ + memset(addr, 0, PTE_TABLE_SIZE); +} + +int kvmppc_radix_init(void) +{ + unsigned long size = sizeof(void *) << PTE_INDEX_SIZE; + + kvm_pte_cache = kmem_cache_create("kvm-pte", size, size, 0, pte_ctor); + if (!kvm_pte_cache) + return -ENOMEM; + return 0; +} + +void kvmppc_radix_exit(void) +{ + kmem_cache_destroy(kvm_pte_cache); +} diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index bb2854314ba4..d50251f9a3c9 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3356,7 +3356,10 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) kvmppc_free_vcores(kvm); - kvmppc_free_hpt(kvm); + if (kvm_is_radix(kvm)) + kvmppc_free_radix(kvm); + else + kvmppc_free_hpt(kvm); kvmppc_free_pimap(kvm); } @@ -3768,6 +3771,11 @@ static int kvm_init_subcore_bitmap(void) return 0; } +static int kvmppc_radix_possible(void) +{ + return cpu_has_feature(CPU_FTR_ARCH_300) && radix_enabled(); +} + static int kvmppc_book3s_init_hv(void) { int r; @@ -3807,12 +3815,19 @@ static int kvmppc_book3s_init_hv(void) init_vcore_lists(); r = kvmppc_mmu_hv_init(); + if (r) + return r; + + if (kvmppc_radix_possible()) + r = kvmppc_radix_init(); return r; } static void kvmppc_book3s_exit_hv(void) { kvmppc_free_host_rm_ops(); + if (kvmppc_radix_possible()) + kvmppc_radix_exit(); kvmppc_hv_ops = NULL; } -- cgit v1.2.3 From 01756099e0a5f431bbada9693d566269acfb51f9 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 30 Jan 2017 21:21:47 +1100 Subject: KVM: PPC: Book3S HV: MMU notifier callbacks for radix guests This adapts our implementations of the MMU notifier callbacks (unmap_hva, unmap_hva_range, age_hva, test_age_hva, set_spte_hva) to call radix functions when the guest is using radix. These implementations are much simpler than for HPT guests because we have only one PTE to deal with, so we don't need to traverse rmap chains. Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/kvm_book3s.h | 6 ++++ arch/powerpc/kvm/book3s_64_mmu_hv.c | 64 +++++++++++++++++++++++----------- arch/powerpc/kvm/book3s_64_mmu_radix.c | 54 ++++++++++++++++++++++++++++ 3 files changed, 103 insertions(+), 21 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index ff5cd5c5ce8d..952cc4b954a1 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -192,6 +192,12 @@ extern int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, extern void kvmppc_free_radix(struct kvm *kvm); extern int kvmppc_radix_init(void); extern void kvmppc_radix_exit(void); +extern int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, + unsigned long gfn); +extern int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, + unsigned long gfn); +extern int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, + unsigned long gfn); /* XXX remove this export when load_last_inst() is generic */ extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data); diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 57690c22716d..088c82bb7ba4 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -701,12 +701,13 @@ static void kvmppc_rmap_reset(struct kvm *kvm) srcu_read_unlock(&kvm->srcu, srcu_idx); } +typedef int (*hva_handler_fn)(struct kvm *kvm, struct kvm_memory_slot *memslot, + unsigned long gfn); + static int kvm_handle_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, - int (*handler)(struct kvm *kvm, - unsigned long *rmapp, - unsigned long gfn)) + hva_handler_fn handler) { int ret; int retval = 0; @@ -731,9 +732,7 @@ static int kvm_handle_hva_range(struct kvm *kvm, gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot); for (; gfn < gfn_end; ++gfn) { - gfn_t gfn_offset = gfn - memslot->base_gfn; - - ret = handler(kvm, &memslot->arch.rmap[gfn_offset], gfn); + ret = handler(kvm, memslot, gfn); retval |= ret; } } @@ -742,20 +741,21 @@ static int kvm_handle_hva_range(struct kvm *kvm, } static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, - int (*handler)(struct kvm *kvm, unsigned long *rmapp, - unsigned long gfn)) + hva_handler_fn handler) { return kvm_handle_hva_range(kvm, hva, hva + 1, handler); } -static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, +static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn) { struct revmap_entry *rev = kvm->arch.revmap; unsigned long h, i, j; __be64 *hptep; unsigned long ptel, psize, rcbits; + unsigned long *rmapp; + rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn]; for (;;) { lock_rmap(rmapp); if (!(*rmapp & KVMPPC_RMAP_PRESENT)) { @@ -816,26 +816,36 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, int kvm_unmap_hva_hv(struct kvm *kvm, unsigned long hva) { - kvm_handle_hva(kvm, hva, kvm_unmap_rmapp); + hva_handler_fn handler; + + handler = kvm_is_radix(kvm) ? kvm_unmap_radix : kvm_unmap_rmapp; + kvm_handle_hva(kvm, hva, handler); return 0; } int kvm_unmap_hva_range_hv(struct kvm *kvm, unsigned long start, unsigned long end) { - kvm_handle_hva_range(kvm, start, end, kvm_unmap_rmapp); + hva_handler_fn handler; + + handler = kvm_is_radix(kvm) ? kvm_unmap_radix : kvm_unmap_rmapp; + kvm_handle_hva_range(kvm, start, end, handler); return 0; } void kvmppc_core_flush_memslot_hv(struct kvm *kvm, struct kvm_memory_slot *memslot) { - unsigned long *rmapp; unsigned long gfn; unsigned long n; + unsigned long *rmapp; - rmapp = memslot->arch.rmap; gfn = memslot->base_gfn; - for (n = memslot->npages; n; --n) { + rmapp = memslot->arch.rmap; + for (n = memslot->npages; n; --n, ++gfn) { + if (kvm_is_radix(kvm)) { + kvm_unmap_radix(kvm, memslot, gfn); + continue; + } /* * Testing the present bit without locking is OK because * the memslot has been marked invalid already, and hence @@ -843,20 +853,21 @@ void kvmppc_core_flush_memslot_hv(struct kvm *kvm, * thus the present bit can't go from 0 to 1. */ if (*rmapp & KVMPPC_RMAP_PRESENT) - kvm_unmap_rmapp(kvm, rmapp, gfn); + kvm_unmap_rmapp(kvm, memslot, gfn); ++rmapp; - ++gfn; } } -static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, +static int kvm_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn) { struct revmap_entry *rev = kvm->arch.revmap; unsigned long head, i, j; __be64 *hptep; int ret = 0; + unsigned long *rmapp; + rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn]; retry: lock_rmap(rmapp); if (*rmapp & KVMPPC_RMAP_REFERENCED) { @@ -904,17 +915,22 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, int kvm_age_hva_hv(struct kvm *kvm, unsigned long start, unsigned long end) { - return kvm_handle_hva_range(kvm, start, end, kvm_age_rmapp); + hva_handler_fn handler; + + handler = kvm_is_radix(kvm) ? kvm_age_radix : kvm_age_rmapp; + return kvm_handle_hva_range(kvm, start, end, handler); } -static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, +static int kvm_test_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn) { struct revmap_entry *rev = kvm->arch.revmap; unsigned long head, i, j; unsigned long *hp; int ret = 1; + unsigned long *rmapp; + rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn]; if (*rmapp & KVMPPC_RMAP_REFERENCED) return 1; @@ -940,12 +956,18 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, int kvm_test_age_hva_hv(struct kvm *kvm, unsigned long hva) { - return kvm_handle_hva(kvm, hva, kvm_test_age_rmapp); + hva_handler_fn handler; + + handler = kvm_is_radix(kvm) ? kvm_test_age_radix : kvm_test_age_rmapp; + return kvm_handle_hva(kvm, hva, handler); } void kvm_set_spte_hva_hv(struct kvm *kvm, unsigned long hva, pte_t pte) { - kvm_handle_hva(kvm, hva, kvm_unmap_rmapp); + hva_handler_fn handler; + + handler = kvm_is_radix(kvm) ? kvm_unmap_radix : kvm_unmap_rmapp; + kvm_handle_hva(kvm, hva, handler); } static int vcpus_running(struct kvm *kvm) diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 865ea9bca364..69cabadc121a 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -463,6 +463,60 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, return ret; } +/* Called with kvm->lock held */ +int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, + unsigned long gfn) +{ + pte_t *ptep; + unsigned long gpa = gfn << PAGE_SHIFT; + unsigned int shift; + + ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa, + NULL, &shift); + if (ptep && pte_present(*ptep)) { + kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT, 0, + gpa, shift); + kvmppc_radix_tlbie_page(kvm, gpa, shift); + } + return 0; +} + +/* Called with kvm->lock held */ +int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, + unsigned long gfn) +{ + pte_t *ptep; + unsigned long gpa = gfn << PAGE_SHIFT; + unsigned int shift; + int ref = 0; + + ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa, + NULL, &shift); + if (ptep && pte_present(*ptep) && pte_young(*ptep)) { + kvmppc_radix_update_pte(kvm, ptep, _PAGE_ACCESSED, 0, + gpa, shift); + /* XXX need to flush tlb here? */ + ref = 1; + } + return ref; +} + +/* Called with kvm->lock held */ +int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, + unsigned long gfn) +{ + pte_t *ptep; + unsigned long gpa = gfn << PAGE_SHIFT; + unsigned int shift; + int ref = 0; + + ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa, + NULL, &shift); + if (ptep && pte_present(*ptep) && pte_young(*ptep)) + ref = 1; + return ref; +} + void kvmppc_free_radix(struct kvm *kvm) { unsigned long ig, iu, im; -- cgit v1.2.3 From 8f7b79b8379a85fb8dd0c3f42d9f452ec5552161 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 30 Jan 2017 21:21:48 +1100 Subject: KVM: PPC: Book3S HV: Implement dirty page logging for radix guests This adds code to keep track of dirty pages when requested (that is, when memslot->dirty_bitmap is non-NULL) for radix guests. We use the dirty bits in the PTEs in the second-level (partition-scoped) page tables, together with a bitmap of pages that were dirty when their PTE was invalidated (e.g., when the page was paged out). This bitmap is stored in the first half of the memslot->dirty_bitmap area, and kvm_vm_ioctl_get_dirty_log_hv() now uses the second half for the bitmap that gets returned to userspace. Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/kvm_book3s.h | 7 ++- arch/powerpc/kvm/book3s_64_mmu_hv.c | 28 ++++----- arch/powerpc/kvm/book3s_64_mmu_radix.c | 111 ++++++++++++++++++++++++++++++--- arch/powerpc/kvm/book3s_hv.c | 31 +++++++-- 4 files changed, 144 insertions(+), 33 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 952cc4b954a1..57dc407cec4a 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -198,6 +198,8 @@ extern int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn); extern int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn); +extern long kvmppc_hv_get_dirty_log_radix(struct kvm *kvm, + struct kvm_memory_slot *memslot, unsigned long *map); /* XXX remove this export when load_last_inst() is generic */ extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data); @@ -228,8 +230,11 @@ extern long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, extern long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags, unsigned long pte_index, unsigned long avpn, unsigned long *hpret); -extern long kvmppc_hv_get_dirty_log(struct kvm *kvm, +extern long kvmppc_hv_get_dirty_log_hpt(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long *map); +extern void kvmppc_harvest_vpa_dirty(struct kvmppc_vpa *vpa, + struct kvm_memory_slot *memslot, + unsigned long *map); extern void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask); extern void kvmppc_set_fscr(struct kvm_vcpu *vcpu, u64 fscr); diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 088c82bb7ba4..c9e587a2849d 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -1068,7 +1068,7 @@ static int kvm_test_clear_dirty_npages(struct kvm *kvm, unsigned long *rmapp) return npages_dirty; } -static void harvest_vpa_dirty(struct kvmppc_vpa *vpa, +void kvmppc_harvest_vpa_dirty(struct kvmppc_vpa *vpa, struct kvm_memory_slot *memslot, unsigned long *map) { @@ -1086,12 +1086,11 @@ static void harvest_vpa_dirty(struct kvmppc_vpa *vpa, __set_bit_le(gfn - memslot->base_gfn, map); } -long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot, - unsigned long *map) +long kvmppc_hv_get_dirty_log_hpt(struct kvm *kvm, + struct kvm_memory_slot *memslot, unsigned long *map) { unsigned long i, j; unsigned long *rmapp; - struct kvm_vcpu *vcpu; preempt_disable(); rmapp = memslot->arch.rmap; @@ -1107,15 +1106,6 @@ long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot, __set_bit_le(j, map); ++rmapp; } - - /* Harvest dirty bits from VPA and DTL updates */ - /* Note: we never modify the SLB shadow buffer areas */ - kvm_for_each_vcpu(i, vcpu, kvm) { - spin_lock(&vcpu->arch.vpa_update_lock); - harvest_vpa_dirty(&vcpu->arch.vpa, memslot, map); - harvest_vpa_dirty(&vcpu->arch.dtl, memslot, map); - spin_unlock(&vcpu->arch.vpa_update_lock); - } preempt_enable(); return 0; } @@ -1170,10 +1160,14 @@ void kvmppc_unpin_guest_page(struct kvm *kvm, void *va, unsigned long gpa, srcu_idx = srcu_read_lock(&kvm->srcu); memslot = gfn_to_memslot(kvm, gfn); if (memslot) { - rmap = &memslot->arch.rmap[gfn - memslot->base_gfn]; - lock_rmap(rmap); - *rmap |= KVMPPC_RMAP_CHANGED; - unlock_rmap(rmap); + if (!kvm_is_radix(kvm)) { + rmap = &memslot->arch.rmap[gfn - memslot->base_gfn]; + lock_rmap(rmap); + *rmap |= KVMPPC_RMAP_CHANGED; + unlock_rmap(rmap); + } else if (memslot->dirty_bitmap) { + mark_page_dirty(kvm, gfn); + } } srcu_read_unlock(&kvm->srcu, srcu_idx); } diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 69cabadc121a..125cc7ce1525 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -158,18 +158,21 @@ static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr, asm volatile("ptesync": : :"memory"); } -void kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep, unsigned long clr, - unsigned long set, unsigned long addr, - unsigned int shift) +unsigned long kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep, + unsigned long clr, unsigned long set, + unsigned long addr, unsigned int shift) { + unsigned long old = 0; + if (!(clr & _PAGE_PRESENT) && cpu_has_feature(CPU_FTR_POWER9_DD1) && pte_present(*ptep)) { /* have to invalidate it first */ - __radix_pte_update(ptep, _PAGE_PRESENT, 0); + old = __radix_pte_update(ptep, _PAGE_PRESENT, 0); kvmppc_radix_tlbie_page(kvm, addr, shift); set |= _PAGE_PRESENT; + old &= _PAGE_PRESENT; } - __radix_pte_update(ptep, clr, set); + return __radix_pte_update(ptep, clr, set) | old; } void kvmppc_radix_set_pte_at(struct kvm *kvm, unsigned long addr, @@ -197,6 +200,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, pud_t *pud, *new_pud = NULL; pmd_t *pmd, *new_pmd = NULL; pte_t *ptep, *new_ptep = NULL; + unsigned long old; int ret; /* Traverse the guest's 2nd-level tree, allocate new levels needed */ @@ -262,9 +266,11 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, ptep = pte_offset_kernel(pmd, gpa); if (pte_present(*ptep)) { /* PTE was previously valid, so invalidate it */ - kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT, - 0, gpa, 0); + old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT, + 0, gpa, 0); kvmppc_radix_tlbie_page(kvm, gpa, 0); + if (old & _PAGE_DIRTY) + mark_page_dirty(kvm, gpa >> PAGE_SHIFT); } kvmppc_radix_set_pte_at(kvm, gpa, ptep, pte); } else { @@ -463,6 +469,26 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, return ret; } +static void mark_pages_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot, + unsigned long gfn, unsigned int order) +{ + unsigned long i, limit; + unsigned long *dp; + + if (!memslot->dirty_bitmap) + return; + limit = 1ul << order; + if (limit < BITS_PER_LONG) { + for (i = 0; i < limit; ++i) + mark_page_dirty(kvm, gfn + i); + return; + } + dp = memslot->dirty_bitmap + (gfn - memslot->base_gfn); + limit /= BITS_PER_LONG; + for (i = 0; i < limit; ++i) + *dp++ = ~0ul; +} + /* Called with kvm->lock held */ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn) @@ -470,13 +496,21 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, pte_t *ptep; unsigned long gpa = gfn << PAGE_SHIFT; unsigned int shift; + unsigned long old; ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa, NULL, &shift); if (ptep && pte_present(*ptep)) { - kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT, 0, - gpa, shift); + old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT, 0, + gpa, shift); kvmppc_radix_tlbie_page(kvm, gpa, shift); + if (old & _PAGE_DIRTY) { + if (!shift) + mark_page_dirty(kvm, gfn); + else + mark_pages_dirty(kvm, memslot, + gfn, shift - PAGE_SHIFT); + } } return 0; } @@ -517,6 +551,65 @@ int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, return ref; } +/* Returns the number of PAGE_SIZE pages that are dirty */ +static int kvm_radix_test_clear_dirty(struct kvm *kvm, + struct kvm_memory_slot *memslot, int pagenum) +{ + unsigned long gfn = memslot->base_gfn + pagenum; + unsigned long gpa = gfn << PAGE_SHIFT; + pte_t *ptep; + unsigned int shift; + int ret = 0; + + ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa, + NULL, &shift); + if (ptep && pte_present(*ptep) && pte_dirty(*ptep)) { + ret = 1; + if (shift) + ret = 1 << (shift - PAGE_SHIFT); + kvmppc_radix_update_pte(kvm, ptep, _PAGE_DIRTY, 0, + gpa, shift); + kvmppc_radix_tlbie_page(kvm, gpa, shift); + } + return ret; +} + +long kvmppc_hv_get_dirty_log_radix(struct kvm *kvm, + struct kvm_memory_slot *memslot, unsigned long *map) +{ + unsigned long i, j; + unsigned long n, *p; + int npages; + + /* + * Radix accumulates dirty bits in the first half of the + * memslot's dirty_bitmap area, for when pages are paged + * out or modified by the host directly. Pick up these + * bits and add them to the map. + */ + n = kvm_dirty_bitmap_bytes(memslot) / sizeof(long); + p = memslot->dirty_bitmap; + for (i = 0; i < n; ++i) + map[i] |= xchg(&p[i], 0); + + for (i = 0; i < memslot->npages; i = j) { + npages = kvm_radix_test_clear_dirty(kvm, memslot, i); + + /* + * Note that if npages > 0 then i must be a multiple of npages, + * since huge pages are only used to back the guest at guest + * real addresses that are a multiple of their size. + * Since we have at most one PTE covering any given guest + * real address, if npages > 1 we can skip to i + npages. + */ + j = i + 1; + if (npages) + for (j = i; npages; ++j, --npages) + __set_bit_le(j, map); + } + return 0; +} + void kvmppc_free_radix(struct kvm *kvm) { unsigned long ig, iu, im; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index d50251f9a3c9..401e4cc8a91f 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2961,8 +2961,10 @@ static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm, { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int r; + int i, r; unsigned long n; + unsigned long *buf; + struct kvm_vcpu *vcpu; mutex_lock(&kvm->slots_lock); @@ -2976,15 +2978,32 @@ static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm, if (!memslot->dirty_bitmap) goto out; + /* + * Use second half of bitmap area because radix accumulates + * bits in the first half. + */ n = kvm_dirty_bitmap_bytes(memslot); - memset(memslot->dirty_bitmap, 0, n); + buf = memslot->dirty_bitmap + n / sizeof(long); + memset(buf, 0, n); - r = kvmppc_hv_get_dirty_log(kvm, memslot, memslot->dirty_bitmap); + if (kvm_is_radix(kvm)) + r = kvmppc_hv_get_dirty_log_radix(kvm, memslot, buf); + else + r = kvmppc_hv_get_dirty_log_hpt(kvm, memslot, buf); if (r) goto out; + /* Harvest dirty bits from VPA and DTL updates */ + /* Note: we never modify the SLB shadow buffer areas */ + kvm_for_each_vcpu(i, vcpu, kvm) { + spin_lock(&vcpu->arch.vpa_update_lock); + kvmppc_harvest_vpa_dirty(&vcpu->arch.vpa, memslot, buf); + kvmppc_harvest_vpa_dirty(&vcpu->arch.dtl, memslot, buf); + spin_unlock(&vcpu->arch.vpa_update_lock); + } + r = -EFAULT; - if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n)) + if (copy_to_user(log->dirty_bitmap, buf, n)) goto out; r = 0; @@ -3037,7 +3056,7 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, if (npages) atomic64_inc(&kvm->arch.mmio_update); - if (npages && old->npages) { + if (npages && old->npages && !kvm_is_radix(kvm)) { /* * If modifying a memslot, reset all the rmap dirty bits. * If this is a new memslot, we don't need to do anything @@ -3046,7 +3065,7 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, */ slots = kvm_memslots(kvm); memslot = id_to_memslot(slots, mem->slot); - kvmppc_hv_get_dirty_log(kvm, memslot, NULL); + kvmppc_hv_get_dirty_log_hpt(kvm, memslot, NULL); } } -- cgit v1.2.3 From a29ebeaf5575d03eef178bb87c425a1e46cae1ca Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 30 Jan 2017 21:21:50 +1100 Subject: KVM: PPC: Book3S HV: Invalidate TLB on radix guest vcpu movement With radix, the guest can do TLB invalidations itself using the tlbie (global) and tlbiel (local) TLB invalidation instructions. Linux guests use local TLB invalidations for translations that have only ever been accessed on one vcpu. However, that doesn't mean that the translations have only been accessed on one physical cpu (pcpu) since vcpus can move around from one pcpu to another. Thus a tlbiel might leave behind stale TLB entries on a pcpu where the vcpu previously ran, and if that task then moves back to that previous pcpu, it could see those stale TLB entries and thus access memory incorrectly. The usual symptom of this is random segfaults in userspace programs in the guest. To cope with this, we detect when a vcpu is about to start executing on a thread in a core that is a different core from the last time it executed. If that is the case, then we mark the core as needing a TLB flush and then send an interrupt to any thread in the core that is currently running a vcpu from the same guest. This will get those vcpus out of the guest, and the first one to re-enter the guest will do the TLB flush. The reason for interrupting the vcpus executing on the old core is to cope with the following scenario: CPU 0 CPU 1 CPU 4 (core 0) (core 0) (core 1) VCPU 0 runs task X VCPU 1 runs core 0 TLB gets entries from task X VCPU 0 moves to CPU 4 VCPU 0 runs task X Unmap pages of task X tlbiel (still VCPU 1) task X moves to VCPU 1 task X runs task X sees stale TLB entries That is, as soon as the VCPU starts executing on the new core, it could unmap and tlbiel some page table entries, and then the task could migrate to one of the VCPUs running on the old core and potentially see stale TLB entries. Since the TLB is shared between all the threads in a core, we only use the bit of kvm->arch.need_tlb_flush corresponding to the first thread in the core. To ensure that we don't have a window where we can miss a flush, this moves the clearing of the bit from before the actual flush to after it. This way, two threads might both do the flush, but we prevent the situation where one thread can enter the guest before the flush is finished. Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/kvm_host.h | 2 ++ arch/powerpc/kvm/book3s_hv.c | 45 +++++++++++++++++++++++++++++++++ arch/powerpc/kvm/book3s_hv_rm_mmu.c | 11 ++++++-- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 38 +++++++++++++++++++--------- 4 files changed, 82 insertions(+), 14 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index da1421a4d6f2..b2dbeac3f450 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -263,6 +263,7 @@ struct kvm_arch { unsigned long hpt_mask; atomic_t hpte_mod_interest; cpumask_t need_tlb_flush; + cpumask_t cpu_in_guest; int hpt_cma_alloc; u8 radix; pgd_t *pgtable; @@ -661,6 +662,7 @@ struct kvm_vcpu_arch { int state; int ptid; int thread_cpu; + int prev_cpu; bool timer_running; wait_queue_head_t cpu_run; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 401e4cc8a91f..50c230e83f9b 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -1821,6 +1821,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, vcpu->arch.vcore = vcore; vcpu->arch.ptid = vcpu->vcpu_id - vcore->first_vcpuid; vcpu->arch.thread_cpu = -1; + vcpu->arch.prev_cpu = -1; vcpu->arch.cpu_type = KVM_CPU_3S_64; kvmppc_sanity_check(vcpu); @@ -1950,11 +1951,33 @@ static void kvmppc_release_hwthread(int cpu) tpaca->kvm_hstate.kvm_split_mode = NULL; } +static void do_nothing(void *x) +{ +} + +static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu) +{ + int i; + + cpu = cpu_first_thread_sibling(cpu); + cpumask_set_cpu(cpu, &kvm->arch.need_tlb_flush); + /* + * Make sure setting of bit in need_tlb_flush precedes + * testing of cpu_in_guest bits. The matching barrier on + * the other side is the first smp_mb() in kvmppc_run_core(). + */ + smp_mb(); + for (i = 0; i < threads_per_core; ++i) + if (cpumask_test_cpu(cpu + i, &kvm->arch.cpu_in_guest)) + smp_call_function_single(cpu + i, do_nothing, NULL, 1); +} + static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc) { int cpu; struct paca_struct *tpaca; struct kvmppc_vcore *mvc = vc->master_vcore; + struct kvm *kvm = vc->kvm; cpu = vc->pcpu; if (vcpu) { @@ -1965,6 +1988,27 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc) cpu += vcpu->arch.ptid; vcpu->cpu = mvc->pcpu; vcpu->arch.thread_cpu = cpu; + + /* + * With radix, the guest can do TLB invalidations itself, + * and it could choose to use the local form (tlbiel) if + * it is invalidating a translation that has only ever been + * used on one vcpu. However, that doesn't mean it has + * only ever been used on one physical cpu, since vcpus + * can move around between pcpus. To cope with this, when + * a vcpu moves from one pcpu to another, we need to tell + * any vcpus running on the same core as this vcpu previously + * ran to flush the TLB. The TLB is shared between threads, + * so we use a single bit in .need_tlb_flush for all 4 threads. + */ + if (kvm_is_radix(kvm) && vcpu->arch.prev_cpu != cpu) { + if (vcpu->arch.prev_cpu >= 0 && + cpu_first_thread_sibling(vcpu->arch.prev_cpu) != + cpu_first_thread_sibling(cpu)) + radix_flush_cpu(kvm, vcpu->arch.prev_cpu, vcpu); + vcpu->arch.prev_cpu = cpu; + } + cpumask_set_cpu(cpu, &kvm->arch.cpu_in_guest); } tpaca = &paca[cpu]; tpaca->kvm_hstate.kvm_vcpu = vcpu; @@ -2552,6 +2596,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) kvmppc_release_hwthread(pcpu + i); if (sip && sip->napped[i]) kvmppc_ipi_thread(pcpu + i); + cpumask_clear_cpu(pcpu + i, &vc->kvm->arch.cpu_in_guest); } kvmppc_set_host_core(pcpu); diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 6c1ac3d21b91..b095afcd4309 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -43,6 +43,7 @@ static void *real_vmalloc_addr(void *x) static int global_invalidates(struct kvm *kvm, unsigned long flags) { int global; + int cpu; /* * If there is only one vcore, and it's currently running, @@ -60,8 +61,14 @@ static int global_invalidates(struct kvm *kvm, unsigned long flags) /* any other core might now have stale TLB entries... */ smp_wmb(); cpumask_setall(&kvm->arch.need_tlb_flush); - cpumask_clear_cpu(local_paca->kvm_hstate.kvm_vcore->pcpu, - &kvm->arch.need_tlb_flush); + cpu = local_paca->kvm_hstate.kvm_vcore->pcpu; + /* + * On POWER9, threads are independent but the TLB is shared, + * so use the bit for the first thread to represent the core. + */ + if (cpu_has_feature(CPU_FTR_ARCH_300)) + cpu = cpu_first_thread_sibling(cpu); + cpumask_clear_cpu(cpu, &kvm->arch.need_tlb_flush); } return global; diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 7fc7a9221509..dcc67a87d688 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -598,30 +598,44 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) /* See if we need to flush the TLB */ lhz r6,PACAPACAINDEX(r13) /* test_bit(cpu, need_tlb_flush) */ +BEGIN_FTR_SECTION + /* + * On POWER9, individual threads can come in here, but the + * TLB is shared between the 4 threads in a core, hence + * invalidating on one thread invalidates for all. + * Thus we make all 4 threads use the same bit here. + */ + clrrdi r6,r6,2 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) clrldi r7,r6,64-6 /* extract bit number (6 bits) */ srdi r6,r6,6 /* doubleword number */ sldi r6,r6,3 /* address offset */ add r6,r6,r9 addi r6,r6,KVM_NEED_FLUSH /* dword in kvm->arch.need_tlb_flush */ - li r0,1 - sld r0,r0,r7 + li r8,1 + sld r8,r8,r7 ld r7,0(r6) - and. r7,r7,r0 + and. r7,r7,r8 beq 22f -23: ldarx r7,0,r6 /* if set, clear the bit */ - andc r7,r7,r0 - stdcx. r7,0,r6 - bne 23b /* Flush the TLB of any entries for this LPID */ - lwz r6,KVM_TLB_SETS(r9) - li r0,0 /* RS for P9 version of tlbiel */ - mtctr r6 + lwz r0,KVM_TLB_SETS(r9) + mtctr r0 li r7,0x800 /* IS field = 0b10 */ ptesync -28: tlbiel r7 + li r0,0 /* RS for P9 version of tlbiel */ + bne cr7, 29f +28: tlbiel r7 /* On P9, rs=0, RIC=0, PRS=0, R=0 */ addi r7,r7,0x1000 bdnz 28b - ptesync + b 30f +29: PPC_TLBIEL(7,0,2,1,1) /* for radix, RIC=2, PRS=1, R=1 */ + addi r7,r7,0x1000 + bdnz 29b +30: ptesync +23: ldarx r7,0,r6 /* clear the bit after TLB flushed */ + andc r7,r7,r8 + stdcx. r7,0,r6 + bne 23b /* Add timebase offset onto timebase */ 22: ld r8,VCORE_TB_OFFSET(r5) -- cgit v1.2.3 From 8cf4ecc0ca9bd9bdc9b4ca0a99f7445a1e74afed Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 30 Jan 2017 21:21:53 +1100 Subject: KVM: PPC: Book3S HV: Enable radix guest support This adds a few last pieces of the support for radix guests: * Implement the backends for the KVM_PPC_CONFIGURE_V3_MMU and KVM_PPC_GET_RMMU_INFO ioctls for radix guests * On POWER9, allow secondary threads to be on/off-lined while guests are running. * Set up LPCR and the partition table entry for radix guests. * Don't allocate the rmap array in the kvm_memory_slot structure on radix. * Don't try to initialize the HPT for radix guests, since they don't have an HPT. * Take out the code that prevents the HV KVM module from initializing on radix hosts. At this stage, we only support radix guests if the host is running in radix mode, and only support HPT guests if the host is running in HPT mode. Thus a guest cannot switch from one mode to the other, which enables some simplifications. Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/kvm_book3s.h | 2 + arch/powerpc/kvm/book3s_64_mmu_hv.c | 1 - arch/powerpc/kvm/book3s_64_mmu_radix.c | 45 +++++++++++++++++ arch/powerpc/kvm/book3s_hv.c | 88 ++++++++++++++++++++++++---------- arch/powerpc/kvm/powerpc.c | 2 +- 5 files changed, 111 insertions(+), 27 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 57dc407cec4a..2bf35017ffc0 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -189,6 +189,7 @@ extern int kvmppc_book3s_radix_page_fault(struct kvm_run *run, unsigned long ea, unsigned long dsisr); extern int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *gpte, bool data, bool iswrite); +extern int kvmppc_init_vm_radix(struct kvm *kvm); extern void kvmppc_free_radix(struct kvm *kvm); extern int kvmppc_radix_init(void); extern void kvmppc_radix_exit(void); @@ -200,6 +201,7 @@ extern int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn); extern long kvmppc_hv_get_dirty_log_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long *map); +extern int kvmhv_get_rmmu_info(struct kvm *kvm, struct kvm_ppc_rmmu_info *info); /* XXX remove this export when load_last_inst() is generic */ extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data); diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index c9e587a2849d..9df3d940acec 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -155,7 +155,6 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp) void kvmppc_free_hpt(struct kvm *kvm) { - kvmppc_free_lpid(kvm->arch.lpid); vfree(kvm->arch.revmap); if (kvm->arch.hpt_cma_alloc) kvm_release_hpt(virt_to_page(kvm->arch.hpt_virt), diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 125cc7ce1525..4344651f408c 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -610,6 +610,51 @@ long kvmppc_hv_get_dirty_log_radix(struct kvm *kvm, return 0; } +static void add_rmmu_ap_encoding(struct kvm_ppc_rmmu_info *info, + int psize, int *indexp) +{ + if (!mmu_psize_defs[psize].shift) + return; + info->ap_encodings[*indexp] = mmu_psize_defs[psize].shift | + (mmu_psize_defs[psize].ap << 29); + ++(*indexp); +} + +int kvmhv_get_rmmu_info(struct kvm *kvm, struct kvm_ppc_rmmu_info *info) +{ + int i; + + if (!radix_enabled()) + return -EINVAL; + memset(info, 0, sizeof(*info)); + + /* 4k page size */ + info->geometries[0].page_shift = 12; + info->geometries[0].level_bits[0] = 9; + for (i = 1; i < 4; ++i) + info->geometries[0].level_bits[i] = p9_supported_radix_bits[i]; + /* 64k page size */ + info->geometries[1].page_shift = 16; + for (i = 0; i < 4; ++i) + info->geometries[1].level_bits[i] = p9_supported_radix_bits[i]; + + i = 0; + add_rmmu_ap_encoding(info, MMU_PAGE_4K, &i); + add_rmmu_ap_encoding(info, MMU_PAGE_64K, &i); + add_rmmu_ap_encoding(info, MMU_PAGE_2M, &i); + add_rmmu_ap_encoding(info, MMU_PAGE_1G, &i); + + return 0; +} + +int kvmppc_init_vm_radix(struct kvm *kvm) +{ + kvm->arch.pgtable = pgd_alloc(kvm->mm); + if (!kvm->arch.pgtable) + return -ENOMEM; + return 0; +} + void kvmppc_free_radix(struct kvm *kvm) { unsigned long ig, iu, im; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 50c230e83f9b..e4a79679342e 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -1135,7 +1135,7 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, /* * Userspace can only modify DPFD (default prefetch depth), * ILE (interrupt little-endian) and TC (translation control). - * On POWER8 userspace can also modify AIL (alt. interrupt loc.) + * On POWER8 and POWER9 userspace can also modify AIL (alt. interrupt loc.). */ mask = LPCR_DPFD | LPCR_ILE | LPCR_TC; if (cpu_has_feature(CPU_FTR_ARCH_207S)) @@ -2922,7 +2922,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) smp_mb(); /* On the first time here, set up HTAB and VRMA */ - if (!vcpu->kvm->arch.hpte_setup_done) { + if (!kvm_is_radix(vcpu->kvm) && !vcpu->kvm->arch.hpte_setup_done) { r = kvmppc_hv_setup_htab_rma(vcpu); if (r) goto out; @@ -2984,6 +2984,13 @@ static int kvm_vm_ioctl_get_smmu_info_hv(struct kvm *kvm, { struct kvm_ppc_one_seg_page_size *sps; + /* + * Since we don't yet support HPT guests on a radix host, + * return an error if the host uses radix. + */ + if (radix_enabled()) + return -EINVAL; + info->flags = KVM_PPC_PAGE_SIZES_REAL; if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) info->flags |= KVM_PPC_1T_SEGMENTS; @@ -3069,6 +3076,15 @@ static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *free, static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot, unsigned long npages) { + /* + * For now, if radix_enabled() then we only support radix guests, + * and in that case we don't need the rmap array. + */ + if (radix_enabled()) { + slot->arch.rmap = NULL; + return 0; + } + slot->arch.rmap = vzalloc(npages * sizeof(*slot->arch.rmap)); if (!slot->arch.rmap) return -ENOMEM; @@ -3149,14 +3165,20 @@ static void kvmppc_setup_partition_table(struct kvm *kvm) { unsigned long dw0, dw1; - /* PS field - page size for VRMA */ - dw0 = ((kvm->arch.vrma_slb_v & SLB_VSID_L) >> 1) | - ((kvm->arch.vrma_slb_v & SLB_VSID_LP) << 1); - /* HTABSIZE and HTABORG fields */ - dw0 |= kvm->arch.sdr1; + if (!kvm_is_radix(kvm)) { + /* PS field - page size for VRMA */ + dw0 = ((kvm->arch.vrma_slb_v & SLB_VSID_L) >> 1) | + ((kvm->arch.vrma_slb_v & SLB_VSID_LP) << 1); + /* HTABSIZE and HTABORG fields */ + dw0 |= kvm->arch.sdr1; - /* Second dword as set by userspace */ - dw1 = kvm->arch.process_table; + /* Second dword as set by userspace */ + dw1 = kvm->arch.process_table; + } else { + dw0 = PATB_HR | radix__get_tree_size() | + __pa(kvm->arch.pgtable) | RADIX_PGD_INDEX_SIZE; + dw1 = PATB_GR | kvm->arch.process_table; + } mmu_partition_table_set_entry(kvm->arch.lpid, dw0, dw1); } @@ -3326,6 +3348,7 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) { unsigned long lpcr, lpid; char buf[32]; + int ret; /* Allocate the guest's logical partition ID */ @@ -3373,13 +3396,30 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) lpcr |= LPCR_HVICE; } + /* + * For now, if the host uses radix, the guest must be radix. + */ + if (radix_enabled()) { + kvm->arch.radix = 1; + lpcr &= ~LPCR_VPM1; + lpcr |= LPCR_UPRT | LPCR_GTSE | LPCR_HR; + ret = kvmppc_init_vm_radix(kvm); + if (ret) { + kvmppc_free_lpid(kvm->arch.lpid); + return ret; + } + kvmppc_setup_partition_table(kvm); + } + kvm->arch.lpcr = lpcr; /* * Work out how many sets the TLB has, for the use of * the TLB invalidation loop in book3s_hv_rmhandlers.S. */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) + if (kvm_is_radix(kvm)) + kvm->arch.tlb_sets = POWER9_TLB_SETS_RADIX; /* 128 */ + else if (cpu_has_feature(CPU_FTR_ARCH_300)) kvm->arch.tlb_sets = POWER9_TLB_SETS_HASH; /* 256 */ else if (cpu_has_feature(CPU_FTR_ARCH_207S)) kvm->arch.tlb_sets = POWER8_TLB_SETS; /* 512 */ @@ -3389,8 +3429,11 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) /* * Track that we now have a HV mode VM active. This blocks secondary * CPU threads from coming online. + * On POWER9, we only need to do this for HPT guests on a radix + * host, which is not yet supported. */ - kvm_hv_vm_activated(); + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + kvm_hv_vm_activated(); /* * Create a debugfs directory for the VM @@ -3416,10 +3459,13 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) { debugfs_remove_recursive(kvm->arch.debugfs_dir); - kvm_hv_vm_deactivated(); + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + kvm_hv_vm_deactivated(); kvmppc_free_vcores(kvm); + kvmppc_free_lpid(kvm->arch.lpid); + if (kvm_is_radix(kvm)) kvmppc_free_radix(kvm); else @@ -3452,11 +3498,6 @@ static int kvmppc_core_check_processor_compat_hv(void) if (!cpu_has_feature(CPU_FTR_HVMODE) || !cpu_has_feature(CPU_FTR_ARCH_206)) return -EIO; - /* - * Disable KVM for Power9 in radix mode. - */ - if (cpu_has_feature(CPU_FTR_ARCH_300) && radix_enabled()) - return -EIO; return 0; } @@ -3727,6 +3768,7 @@ static void init_default_hcalls(void) static int kvmhv_configure_mmu(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg) { unsigned long lpcr; + int radix; /* If not on a POWER9, reject it */ if (!cpu_has_feature(CPU_FTR_ARCH_300)) @@ -3736,12 +3778,13 @@ static int kvmhv_configure_mmu(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg) if (cfg->flags & ~(KVM_PPC_MMUV3_RADIX | KVM_PPC_MMUV3_GTSE)) return -EINVAL; - /* We can't do radix yet */ - if (cfg->flags & KVM_PPC_MMUV3_RADIX) + /* We can't change a guest to/from radix yet */ + radix = !!(cfg->flags & KVM_PPC_MMUV3_RADIX); + if (radix != kvm_is_radix(kvm)) return -EINVAL; /* GR (guest radix) bit in process_table field must match */ - if (cfg->process_table & PATB_GR) + if (!!(cfg->process_table & PATB_GR) != radix) return -EINVAL; /* Process table size field must be reasonable, i.e. <= 24 */ @@ -3757,11 +3800,6 @@ static int kvmhv_configure_mmu(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg) return 0; } -static int kvmhv_get_rmmu_info(struct kvm *kvm, struct kvm_ppc_rmmu_info *info) -{ - return -EINVAL; -} - static struct kvmppc_ops kvm_ops_hv = { .get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv, .set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv, diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 1476a480745e..40a5b2d75ed1 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -566,7 +566,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = kvmppc_hwrng_present(); break; case KVM_CAP_PPC_MMU_RADIX: - r = !!(0 && hv_enabled && radix_enabled()); + r = !!(hv_enabled && radix_enabled()); break; case KVM_CAP_PPC_MMU_HASH_V3: r = !!(hv_enabled && !radix_enabled() && -- cgit v1.2.3 From f84ed59a612d866cde0bd17ad2a52acb524d44c9 Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Mon, 30 Jan 2017 17:41:53 +1100 Subject: powerpc/sparse: Constify the address pointer in __get_user_check() In __get_user_check, we create an intermediate pointer for the user address we're about to fetch. We currently don't tag this pointer as const. Make it const, as we are simply dereferencing it, and it's scope is limited to the __get_user_check macro. Signed-off-by: Daniel Axtens Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index a15d84d59356..71d81cbe3781 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -274,7 +274,7 @@ do { \ ({ \ long __gu_err = -EFAULT; \ unsigned long __gu_val = 0; \ - __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ + const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ might_fault(); \ if (access_ok(VERIFY_READ, __gu_addr, (size))) \ __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ -- cgit v1.2.3 From d466f6c5cac17e0c9f22bd4250020bf885049db7 Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Mon, 30 Jan 2017 17:41:54 +1100 Subject: powerpc/sparse: Constify the address pointer in __get_user_nocheck() In __get_user_nocheck, we create an intermediate pointer for the user address we're about to fetch. We currently don't tag this pointer as const. Make it const, as we are simply dereferencing it, and it's scope is limited to the __get_user_nocheck macro. Signed-off-by: Daniel Axtens Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 71d81cbe3781..44ded4193001 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -261,7 +261,7 @@ do { \ ({ \ long __gu_err; \ unsigned long __gu_val; \ - __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ + const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ __chk_user_ptr(ptr); \ if (!is_kernel_addr((unsigned long)__gu_addr)) \ might_fault(); \ -- cgit v1.2.3 From f2ca809059294b27703d709a3c4218197c5f16dc Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Mon, 30 Jan 2017 17:41:55 +1100 Subject: powerpc/sparse: Constify the address pointer in __get_user_nosleep() In __get_user_nosleep, we create an intermediate pointer for the user address we're about to fetch. We currently don't tag this pointer as const. Make it const, as we are simply dereferencing it, and it's scope is limited to the __get_user_nosleep macro. Signed-off-by: Daniel Axtens Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 44ded4193001..0e6add3187bc 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -286,7 +286,7 @@ do { \ ({ \ long __gu_err; \ unsigned long __gu_val; \ - __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ + const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ __chk_user_ptr(ptr); \ __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ -- cgit v1.2.3 From e70d59700fc32c9249b26acd4120303c497e84f1 Mon Sep 17 00:00:00 2001 From: John Allen Date: Fri, 6 Jan 2017 13:27:26 -0600 Subject: powerpc/pseries: Introduce memory hotplug READD operation Currently, memory must be hot removed and subsequently re-added in order to dynamically update the affinity of LMBs specified by a PRRN event. Earlier implementations of the PRRN event handler ran into issues in which the hot remove would occur successfully, but a hotplug event would be initiated from another source and grab the hotplug lock preventing the hot add from occurring. To prevent this situation, this patch introduces the notion of a hot "readd" action for memory which atomizes a hot remove and a hot add into a single, serialized operation on the hotplug queue. Signed-off-by: John Allen Reviewed-by: Nathan Fontenot Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/rtas.h | 1 + arch/powerpc/platforms/pseries/hotplug-memory.c | 41 +++++++++++++++++++++++++ 2 files changed, 42 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 9c23baa10b81..076b89247ab5 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -318,6 +318,7 @@ struct pseries_hp_errorlog { #define PSERIES_HP_ELOG_ACTION_ADD 1 #define PSERIES_HP_ELOG_ACTION_REMOVE 2 +#define PSERIES_HP_ELOG_ACTION_READD 3 #define PSERIES_HP_ELOG_ID_DRC_NAME 1 #define PSERIES_HP_ELOG_ID_DRC_INDEX 2 diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index be11fc3cdeb0..3381c20edbc0 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -563,6 +563,44 @@ static int dlpar_memory_remove_by_index(u32 drc_index, struct property *prop) return rc; } +static int dlpar_memory_readd_by_index(u32 drc_index, struct property *prop) +{ + struct of_drconf_cell *lmbs; + u32 num_lmbs, *p; + int lmb_found; + int i, rc; + + pr_info("Attempting to update LMB, drc index %x\n", drc_index); + + p = prop->value; + num_lmbs = *p++; + lmbs = (struct of_drconf_cell *)p; + + lmb_found = 0; + for (i = 0; i < num_lmbs; i++) { + if (lmbs[i].drc_index == drc_index) { + lmb_found = 1; + rc = dlpar_remove_lmb(&lmbs[i]); + if (!rc) { + rc = dlpar_add_lmb(&lmbs[i]); + if (rc) + dlpar_release_drc(lmbs[i].drc_index); + } + break; + } + } + + if (!lmb_found) + rc = -EINVAL; + + if (rc) + pr_info("Failed to update memory at %llx\n", + lmbs[i].base_addr); + else + pr_info("Memory at %llx was updated\n", lmbs[i].base_addr); + + return rc; +} #else static inline int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) @@ -779,6 +817,9 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog) else rc = -EINVAL; break; + case PSERIES_HP_ELOG_ACTION_READD: + rc = dlpar_memory_readd_by_index(drc_index, prop); + break; default: pr_err("Invalid action (%d) specified\n", hp_elog->action); rc = -EINVAL; -- cgit v1.2.3 From 2a196e24b39aa85351ecd9eb7cf511914157f14b Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Sun, 8 Jan 2017 17:31:42 -0600 Subject: powerpc: Move ARCH_DLINFO out of uapi It's an kernel private macro, it doesn't belong there Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/elf.h | 22 ++++++++++++++++++++++ arch/powerpc/include/uapi/asm/elf.h | 23 ----------------------- 2 files changed, 22 insertions(+), 23 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index ee46ffef608e..730c27ed10e1 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -136,4 +136,26 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm, #endif /* CONFIG_SPU_BASE */ +/* + * The requirements here are: + * - keep the final alignment of sp (sp & 0xf) + * - make sure the 32-bit value at the first 16 byte aligned position of + * AUXV is greater than 16 for glibc compatibility. + * AT_IGNOREPPC is used for that. + * - for compatibility with glibc ARCH_DLINFO must always be defined on PPC, + * even if DLINFO_ARCH_ITEMS goes to zero or is undefined. + * update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes + */ +#define ARCH_DLINFO \ +do { \ + /* Handle glibc compatibility. */ \ + NEW_AUX_ENT(AT_IGNOREPPC, AT_IGNOREPPC); \ + NEW_AUX_ENT(AT_IGNOREPPC, AT_IGNOREPPC); \ + /* Cache size items */ \ + NEW_AUX_ENT(AT_DCACHEBSIZE, dcache_bsize); \ + NEW_AUX_ENT(AT_ICACHEBSIZE, icache_bsize); \ + NEW_AUX_ENT(AT_UCACHEBSIZE, ucache_bsize); \ + VDSO_AUX_ENT(AT_SYSINFO_EHDR, current->mm->context.vdso_base); \ +} while (0) + #endif /* _ASM_POWERPC_ELF_H */ diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h index 3a9e44c45c78..b2c6fdd5ac30 100644 --- a/arch/powerpc/include/uapi/asm/elf.h +++ b/arch/powerpc/include/uapi/asm/elf.h @@ -162,29 +162,6 @@ typedef elf_vrreg_t elf_vrregset_t32[ELF_NVRREG32]; typedef elf_fpreg_t elf_vsrreghalf_t32[ELF_NVSRHALFREG]; #endif - -/* - * The requirements here are: - * - keep the final alignment of sp (sp & 0xf) - * - make sure the 32-bit value at the first 16 byte aligned position of - * AUXV is greater than 16 for glibc compatibility. - * AT_IGNOREPPC is used for that. - * - for compatibility with glibc ARCH_DLINFO must always be defined on PPC, - * even if DLINFO_ARCH_ITEMS goes to zero or is undefined. - * update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes - */ -#define ARCH_DLINFO \ -do { \ - /* Handle glibc compatibility. */ \ - NEW_AUX_ENT(AT_IGNOREPPC, AT_IGNOREPPC); \ - NEW_AUX_ENT(AT_IGNOREPPC, AT_IGNOREPPC); \ - /* Cache size items */ \ - NEW_AUX_ENT(AT_DCACHEBSIZE, dcache_bsize); \ - NEW_AUX_ENT(AT_ICACHEBSIZE, icache_bsize); \ - NEW_AUX_ENT(AT_UCACHEBSIZE, ucache_bsize); \ - VDSO_AUX_ENT(AT_SYSINFO_EHDR, current->mm->context.vdso_base); \ -} while (0) - /* PowerPC64 relocations defined by the ABIs */ #define R_PPC64_NONE R_PPC_NONE #define R_PPC64_ADDR32 R_PPC_ADDR32 /* 32bit absolute address. */ -- cgit v1.2.3 From bd067f83b0840e798328d14133ce4542d3bf9e71 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Sun, 8 Jan 2017 17:31:45 -0600 Subject: powerpc/64: Fix naming of cache block vs. cache line In a number of places we called "cache line size" what is actually the cache block size, which in the powerpc architecture, means the effective size to use with cache management instructions (it can be different from the actual cache line size). We fix the naming across the board and properly retrieve both pieces of information when available in the device-tree. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/cache.h | 12 ++++--- arch/powerpc/include/asm/page_64.h | 4 +-- arch/powerpc/kernel/align.c | 2 +- arch/powerpc/kernel/asm-offsets.c | 12 +++---- arch/powerpc/kernel/misc_64.S | 28 ++++++++-------- arch/powerpc/kernel/setup_64.c | 65 +++++++++++++++++++++----------------- arch/powerpc/kernel/vdso.c | 10 +++--- arch/powerpc/lib/copypage_64.S | 4 +-- arch/powerpc/lib/string_64.S | 6 ++-- 9 files changed, 75 insertions(+), 68 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h index 7657aa897a38..25ee433a8261 100644 --- a/arch/powerpc/include/asm/cache.h +++ b/arch/powerpc/include/asm/cache.h @@ -33,12 +33,14 @@ struct ppc64_caches { u32 dsize; /* L1 d-cache size */ u32 dline_size; /* L1 d-cache line size */ - u32 log_dline_size; - u32 dlines_per_page; + u32 dblock_size; /* L1 d-cache block size */ + u32 log_dblock_size; + u32 dblocks_per_page; u32 isize; /* L1 i-cache size */ - u32 iline_size; /* L1 i-cache line size */ - u32 log_iline_size; - u32 ilines_per_page; + u32 iline_size; /* L1 d-cache line size */ + u32 iblock_size; /* L1 i-cache block size */ + u32 log_iblock_size; + u32 iblocks_per_page; }; extern struct ppc64_caches ppc64_caches; diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h index dd5f0712afa2..c50a666308dd 100644 --- a/arch/powerpc/include/asm/page_64.h +++ b/arch/powerpc/include/asm/page_64.h @@ -47,14 +47,14 @@ static inline void clear_page(void *addr) unsigned long iterations; unsigned long onex, twox, fourx, eightx; - iterations = ppc64_caches.dlines_per_page / 8; + iterations = ppc64_caches.dblocks_per_page / 8; /* * Some verisions of gcc use multiply instructions to * calculate the offsets so lets give it a hand to * do better. */ - onex = ppc64_caches.dline_size; + onex = ppc64_caches.dblock_size; twox = onex << 1; fourx = onex << 2; eightx = onex << 3; diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index 8d58c61908f7..30ff6590a2dd 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -204,7 +204,7 @@ static int emulate_dcbz(struct pt_regs *regs, unsigned char __user *addr) int i, size; #ifdef __powerpc64__ - size = ppc64_caches.dline_size; + size = ppc64_caches.dblock_size; #else size = L1_CACHE_BYTES; #endif diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 0601e6a7297c..125442107b40 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -163,12 +163,12 @@ int main(void) DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); #ifdef CONFIG_PPC64 - DEFINE(DCACHEL1LINESIZE, offsetof(struct ppc64_caches, dline_size)); - DEFINE(DCACHEL1LOGLINESIZE, offsetof(struct ppc64_caches, log_dline_size)); - DEFINE(DCACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, dlines_per_page)); - DEFINE(ICACHEL1LINESIZE, offsetof(struct ppc64_caches, iline_size)); - DEFINE(ICACHEL1LOGLINESIZE, offsetof(struct ppc64_caches, log_iline_size)); - DEFINE(ICACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, ilines_per_page)); + DEFINE(DCACHEL1BLOCKSIZE, offsetof(struct ppc64_caches, dblock_size)); + DEFINE(DCACHEL1LOGBLOCKSIZE, offsetof(struct ppc64_caches, log_dblock_size)); + DEFINE(DCACHEL1BLOCKSPERPAGE, offsetof(struct ppc64_caches, dblocks_per_page)); + DEFINE(ICACHEL1BLOCKSIZE, offsetof(struct ppc64_caches, iblock_size)); + DEFINE(ICACHEL1LOGBLOCKSIZE, offsetof(struct ppc64_caches, log_iblock_size)); + DEFINE(ICACHEL1BLOCKSPERPAGE, offsetof(struct ppc64_caches, iblocks_per_page)); /* paca */ DEFINE(PACA_SIZE, sizeof(struct paca_struct)); DEFINE(PACAPACAINDEX, offsetof(struct paca_struct, paca_index)); diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 32be2a844947..ae179cb1bb3c 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -80,12 +80,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) * each other. */ ld r10,PPC64_CACHES@toc(r2) - lwz r7,DCACHEL1LINESIZE(r10)/* Get cache line size */ + lwz r7,DCACHEL1BLOCKSIZE(r10)/* Get cache block size */ addi r5,r7,-1 andc r6,r3,r5 /* round low to line bdy */ subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ - lwz r9,DCACHEL1LOGLINESIZE(r10) /* Get log-2 of cache line size */ + lwz r9,DCACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of cache block size */ srw. r8,r8,r9 /* compute line count */ beqlr /* nothing to do? */ mtctr r8 @@ -96,12 +96,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) /* Now invalidate the instruction cache */ - lwz r7,ICACHEL1LINESIZE(r10) /* Get Icache line size */ + lwz r7,ICACHEL1BLOCKSIZE(r10) /* Get Icache block size */ addi r5,r7,-1 andc r6,r3,r5 /* round low to line bdy */ subf r8,r6,r4 /* compute length */ add r8,r8,r5 - lwz r9,ICACHEL1LOGLINESIZE(r10) /* Get log-2 of Icache line size */ + lwz r9,ICACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of Icache block size */ srw. r8,r8,r9 /* compute line count */ beqlr /* nothing to do? */ mtctr r8 @@ -128,12 +128,12 @@ _GLOBAL(flush_dcache_range) * Different systems have different cache line sizes */ ld r10,PPC64_CACHES@toc(r2) - lwz r7,DCACHEL1LINESIZE(r10) /* Get dcache line size */ + lwz r7,DCACHEL1BLOCKSIZE(r10) /* Get dcache block size */ addi r5,r7,-1 andc r6,r3,r5 /* round low to line bdy */ subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ - lwz r9,DCACHEL1LOGLINESIZE(r10) /* Get log-2 of dcache line size */ + lwz r9,DCACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of dcache block size */ srw. r8,r8,r9 /* compute line count */ beqlr /* nothing to do? */ mtctr r8 @@ -156,12 +156,12 @@ EXPORT_SYMBOL(flush_dcache_range) */ _GLOBAL(flush_dcache_phys_range) ld r10,PPC64_CACHES@toc(r2) - lwz r7,DCACHEL1LINESIZE(r10) /* Get dcache line size */ + lwz r7,DCACHEL1BLOCKSIZE(r10) /* Get dcache block size */ addi r5,r7,-1 andc r6,r3,r5 /* round low to line bdy */ subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ - lwz r9,DCACHEL1LOGLINESIZE(r10) /* Get log-2 of dcache line size */ + lwz r9,DCACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of dcache block size */ srw. r8,r8,r9 /* compute line count */ beqlr /* nothing to do? */ mfmsr r5 /* Disable MMU Data Relocation */ @@ -184,12 +184,12 @@ _GLOBAL(flush_dcache_phys_range) _GLOBAL(flush_inval_dcache_range) ld r10,PPC64_CACHES@toc(r2) - lwz r7,DCACHEL1LINESIZE(r10) /* Get dcache line size */ + lwz r7,DCACHEL1BLOCKSIZE(r10) /* Get dcache block size */ addi r5,r7,-1 andc r6,r3,r5 /* round low to line bdy */ subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ - lwz r9,DCACHEL1LOGLINESIZE(r10)/* Get log-2 of dcache line size */ + lwz r9,DCACHEL1LOGBLOCKSIZE(r10)/* Get log-2 of dcache block size */ srw. r8,r8,r9 /* compute line count */ beqlr /* nothing to do? */ sync @@ -225,8 +225,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) /* Flush the dcache */ ld r7,PPC64_CACHES@toc(r2) clrrdi r3,r3,PAGE_SHIFT /* Page align */ - lwz r4,DCACHEL1LINESPERPAGE(r7) /* Get # dcache lines per page */ - lwz r5,DCACHEL1LINESIZE(r7) /* Get dcache line size */ + lwz r4,DCACHEL1BLOCKSPERPAGE(r7) /* Get # dcache blocks per page */ + lwz r5,DCACHEL1BLOCKSIZE(r7) /* Get dcache block size */ mr r6,r3 mtctr r4 0: dcbst 0,r6 @@ -236,8 +236,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) /* Now invalidate the icache */ - lwz r4,ICACHEL1LINESPERPAGE(r7) /* Get # icache lines per page */ - lwz r5,ICACHEL1LINESIZE(r7) /* Get icache line size */ + lwz r4,ICACHEL1BLOCKSPERPAGE(r7) /* Get # icache blocks per page */ + lwz r5,ICACHEL1BLOCKSIZE(r7) /* Get icache block size */ mtctr r4 1: icbi 0,r3 add r3,r3,r5 diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index ae84d345c13c..08cccb2501e7 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -78,10 +78,10 @@ int spinning_secondaries; u64 ppc64_pft_size; struct ppc64_caches ppc64_caches = { - .dline_size = 0x40, - .log_dline_size = 6, - .iline_size = 0x40, - .log_iline_size = 6 + .dblock_size = 0x40, + .log_dblock_size = 6, + .iblock_size = 0x40, + .log_iblock_size = 6 }; EXPORT_SYMBOL_GPL(ppc64_caches); @@ -412,59 +412,66 @@ void __init initialize_cache_info(void) * d-cache and i-cache sizes... -Peter */ if (num_cpus == 1) { - const __be32 *sizep, *lsizep; - u32 size, lsize; + const __be32 *sizep, *lsizep, *bsizep; + u32 size, lsize, bsize; size = 0; - lsize = cur_cpu_spec->dcache_bsize; + lsize = bsize = cur_cpu_spec->dcache_bsize; sizep = of_get_property(np, "d-cache-size", NULL); if (sizep != NULL) size = be32_to_cpu(*sizep); - lsizep = of_get_property(np, "d-cache-block-size", + bsizep = of_get_property(np, "d-cache-block-size", NULL); - /* fallback if block size missing */ - if (lsizep == NULL) - lsizep = of_get_property(np, - "d-cache-line-size", - NULL); + lsizep = of_get_property(np, "d-cache-line-size", + NULL); + if (bsizep == NULL) + bsizep = lsizep; if (lsizep != NULL) lsize = be32_to_cpu(*lsizep); - if (sizep == NULL || lsizep == NULL) + if (bsizep != NULL) + bsize = be32_to_cpu(*bsizep); + if (sizep == NULL || bsizep == NULL || lsizep == NULL) DBG("Argh, can't find dcache properties ! " - "sizep: %p, lsizep: %p\n", sizep, lsizep); + "sizep: %p, bsizep: %p, lsizep: %p\n", + sizep, bsizep, lsizep); ppc64_caches.dsize = size; ppc64_caches.dline_size = lsize; - ppc64_caches.log_dline_size = __ilog2(lsize); - ppc64_caches.dlines_per_page = PAGE_SIZE / lsize; + ppc64_caches.dblock_size = bsize; + ppc64_caches.log_dblock_size = __ilog2(bsize); + ppc64_caches.dblocks_per_page = PAGE_SIZE / bsize; size = 0; - lsize = cur_cpu_spec->icache_bsize; + lsize = bsize = cur_cpu_spec->icache_bsize; sizep = of_get_property(np, "i-cache-size", NULL); if (sizep != NULL) size = be32_to_cpu(*sizep); - lsizep = of_get_property(np, "i-cache-block-size", + bsizep = of_get_property(np, "i-cache-block-size", + NULL); + lsizep = of_get_property(np, "i-cache-line-size", NULL); - if (lsizep == NULL) - lsizep = of_get_property(np, - "i-cache-line-size", - NULL); + if (bsizep == NULL) + bsizep = lsizep; if (lsizep != NULL) lsize = be32_to_cpu(*lsizep); - if (sizep == NULL || lsizep == NULL) + if (bsizep != NULL) + bsize = be32_to_cpu(*bsizep); + if (sizep == NULL || bsizep == NULL || lsizep == NULL) DBG("Argh, can't find icache properties ! " - "sizep: %p, lsizep: %p\n", sizep, lsizep); + "sizep: %p, bsizep: %p, lsizep: %p\n", + sizep, bsizep, lsizep); ppc64_caches.isize = size; ppc64_caches.iline_size = lsize; - ppc64_caches.log_iline_size = __ilog2(lsize); - ppc64_caches.ilines_per_page = PAGE_SIZE / lsize; + ppc64_caches.iblock_size = bsize; + ppc64_caches.log_iblock_size = __ilog2(bsize); + ppc64_caches.iblocks_per_page = PAGE_SIZE / bsize; } } /* For use by binfmt_elf */ - dcache_bsize = ppc64_caches.dline_size; - icache_bsize = ppc64_caches.iline_size; + dcache_bsize = ppc64_caches.dblock_size; + icache_bsize = ppc64_caches.iblock_size; DBG(" <- initialize_cache_info()\n"); } diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 4111d30badfa..9c0a85776c6c 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -740,12 +740,10 @@ static int __init vdso_init(void) vdso_data->dcache_line_size = ppc64_caches.dline_size; vdso_data->icache_size = ppc64_caches.isize; vdso_data->icache_line_size = ppc64_caches.iline_size; - - /* XXXOJN: Blocks should be added to ppc64_caches and used instead */ - vdso_data->dcache_block_size = ppc64_caches.dline_size; - vdso_data->icache_block_size = ppc64_caches.iline_size; - vdso_data->dcache_log_block_size = ppc64_caches.log_dline_size; - vdso_data->icache_log_block_size = ppc64_caches.log_iline_size; + vdso_data->dcache_block_size = ppc64_caches.dblock_size; + vdso_data->icache_block_size = ppc64_caches.iblock_size; + vdso_data->dcache_log_block_size = ppc64_caches.log_dblock_size; + vdso_data->icache_log_block_size = ppc64_caches.log_iblock_size; /* * Calculate the size of the 64 bits vDSO diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S index 21367b3a8146..4bcc9e76fb55 100644 --- a/arch/powerpc/lib/copypage_64.S +++ b/arch/powerpc/lib/copypage_64.S @@ -26,8 +26,8 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY) ori r5,r5,PAGE_SIZE@l BEGIN_FTR_SECTION ld r10,PPC64_CACHES@toc(r2) - lwz r11,DCACHEL1LOGLINESIZE(r10) /* log2 of cache line size */ - lwz r12,DCACHEL1LINESIZE(r10) /* get cache line size */ + lwz r11,DCACHEL1LOGBLOCKSIZE(r10) /* log2 of cache block size */ + lwz r12,DCACHEL1BLOCKSIZE(r10) /* get cache block size */ li r9,0 srd r8,r5,r11 diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S index c100f4d5d5d0..d5b4d9498c54 100644 --- a/arch/powerpc/lib/string_64.S +++ b/arch/powerpc/lib/string_64.S @@ -152,9 +152,9 @@ err2; std r0,0(r3) addi r3,r3,8 addi r4,r4,-8 - /* Destination is 16 byte aligned, need to get it cacheline aligned */ -11: lwz r7,DCACHEL1LOGLINESIZE(r5) - lwz r9,DCACHEL1LINESIZE(r5) + /* Destination is 16 byte aligned, need to get it cache block aligned */ +11: lwz r7,DCACHEL1LOGBLOCKSIZE(r5) + lwz r9,DCACHEL1BLOCKSIZE(r5) /* * With worst case alignment the long clear loop takes a minimum -- cgit v1.2.3 From 5d451a87e5ebbde18c2b48284778f29d308816c2 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Sun, 8 Jan 2017 17:31:46 -0600 Subject: powerpc/64: Retrieve number of L1 cache sets from device-tree It will be used to calculate the associativity Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/cache.h | 2 ++ arch/powerpc/kernel/setup_64.c | 28 ++++++++++++++++++++++++++-- 2 files changed, 28 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h index 25ee433a8261..1fa364340146 100644 --- a/arch/powerpc/include/asm/cache.h +++ b/arch/powerpc/include/asm/cache.h @@ -36,11 +36,13 @@ struct ppc64_caches { u32 dblock_size; /* L1 d-cache block size */ u32 log_dblock_size; u32 dblocks_per_page; + u32 dsets; u32 isize; /* L1 i-cache size */ u32 iline_size; /* L1 d-cache line size */ u32 iblock_size; /* L1 i-cache block size */ u32 log_iblock_size; u32 iblocks_per_page; + u32 isets; }; extern struct ppc64_caches ppc64_caches; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 08cccb2501e7..75c9a8641ba1 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -412,14 +412,18 @@ void __init initialize_cache_info(void) * d-cache and i-cache sizes... -Peter */ if (num_cpus == 1) { - const __be32 *sizep, *lsizep, *bsizep; - u32 size, lsize, bsize; + const __be32 *sizep, *lsizep, *bsizep, *setsp; + u32 size, lsize, bsize, sets; size = 0; + sets = -1u; lsize = bsize = cur_cpu_spec->dcache_bsize; sizep = of_get_property(np, "d-cache-size", NULL); if (sizep != NULL) size = be32_to_cpu(*sizep); + setsp = of_get_property(np, "d-cache-sets", NULL); + if (setsp != NULL) + sets = be32_to_cpu(*setsp); bsizep = of_get_property(np, "d-cache-block-size", NULL); lsizep = of_get_property(np, "d-cache-line-size", @@ -435,17 +439,32 @@ void __init initialize_cache_info(void) "sizep: %p, bsizep: %p, lsizep: %p\n", sizep, bsizep, lsizep); + /* + * OF is weird .. it represents fully associative caches + * as "1 way" which doesn't make much sense and doesn't + * leave room for direct mapped. We'll assume that 0 + * in OF means direct mapped for that reason. + */ + if (sets == 1) + sets = 0; + else if (sets == 0) + sets = 1; ppc64_caches.dsize = size; + ppc64_caches.dsets = sets; ppc64_caches.dline_size = lsize; ppc64_caches.dblock_size = bsize; ppc64_caches.log_dblock_size = __ilog2(bsize); ppc64_caches.dblocks_per_page = PAGE_SIZE / bsize; size = 0; + sets = -1u; lsize = bsize = cur_cpu_spec->icache_bsize; sizep = of_get_property(np, "i-cache-size", NULL); if (sizep != NULL) size = be32_to_cpu(*sizep); + setsp = of_get_property(np, "i-cache-sets", NULL); + if (setsp != NULL) + sets = be32_to_cpu(*setsp); bsizep = of_get_property(np, "i-cache-block-size", NULL); lsizep = of_get_property(np, "i-cache-line-size", @@ -461,7 +480,12 @@ void __init initialize_cache_info(void) "sizep: %p, bsizep: %p, lsizep: %p\n", sizep, bsizep, lsizep); + if (sets == 1) + sets = 0; + else if (sets == 0) + sets = 1; ppc64_caches.isize = size; + ppc64_caches.isets = sets; ppc64_caches.iline_size = lsize; ppc64_caches.iblock_size = bsize; ppc64_caches.log_iblock_size = __ilog2(bsize); -- cgit v1.2.3 From e2827fe5c1566f66a922dd7493cbe4522c50580a Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Sun, 8 Jan 2017 17:31:47 -0600 Subject: powerpc/64: Clean up ppc64_caches using a struct per cache We have two set of identical struct members for the I and D sides and mostly identical bunches of code to parse the device-tree to populate them. Instead make a ppc_cache_info structure with one copy for I and one for D Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/cache.h | 24 ++--- arch/powerpc/include/asm/page_64.h | 4 +- arch/powerpc/kernel/align.c | 2 +- arch/powerpc/kernel/asm-offsets.c | 12 +-- arch/powerpc/kernel/setup_64.c | 183 ++++++++++++++++++------------------- arch/powerpc/kernel/vdso.c | 16 ++-- 6 files changed, 119 insertions(+), 122 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h index 1fa364340146..823750fa6e66 100644 --- a/arch/powerpc/include/asm/cache.h +++ b/arch/powerpc/include/asm/cache.h @@ -30,19 +30,19 @@ #define IFETCH_ALIGN_BYTES (1 << IFETCH_ALIGN_SHIFT) #if defined(__powerpc64__) && !defined(__ASSEMBLY__) + +struct ppc_cache_info { + u32 size; + u32 line_size; + u32 block_size; /* L1 only */ + u32 log_block_size; + u32 blocks_per_page; + u32 sets; +}; + struct ppc64_caches { - u32 dsize; /* L1 d-cache size */ - u32 dline_size; /* L1 d-cache line size */ - u32 dblock_size; /* L1 d-cache block size */ - u32 log_dblock_size; - u32 dblocks_per_page; - u32 dsets; - u32 isize; /* L1 i-cache size */ - u32 iline_size; /* L1 d-cache line size */ - u32 iblock_size; /* L1 i-cache block size */ - u32 log_iblock_size; - u32 iblocks_per_page; - u32 isets; + struct ppc_cache_info l1d; + struct ppc_cache_info l1i; }; extern struct ppc64_caches ppc64_caches; diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h index c50a666308dd..3e83d2a20b6f 100644 --- a/arch/powerpc/include/asm/page_64.h +++ b/arch/powerpc/include/asm/page_64.h @@ -47,14 +47,14 @@ static inline void clear_page(void *addr) unsigned long iterations; unsigned long onex, twox, fourx, eightx; - iterations = ppc64_caches.dblocks_per_page / 8; + iterations = ppc64_caches.l1d.blocks_per_page / 8; /* * Some verisions of gcc use multiply instructions to * calculate the offsets so lets give it a hand to * do better. */ - onex = ppc64_caches.dblock_size; + onex = ppc64_caches.l1d.block_size; twox = onex << 1; fourx = onex << 2; eightx = onex << 3; diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index 30ff6590a2dd..cbc7c42cdb74 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -204,7 +204,7 @@ static int emulate_dcbz(struct pt_regs *regs, unsigned char __user *addr) int i, size; #ifdef __powerpc64__ - size = ppc64_caches.dblock_size; + size = ppc64_caches.l1d.block_size; #else size = L1_CACHE_BYTES; #endif diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 125442107b40..b4324db94741 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -163,12 +163,12 @@ int main(void) DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); #ifdef CONFIG_PPC64 - DEFINE(DCACHEL1BLOCKSIZE, offsetof(struct ppc64_caches, dblock_size)); - DEFINE(DCACHEL1LOGBLOCKSIZE, offsetof(struct ppc64_caches, log_dblock_size)); - DEFINE(DCACHEL1BLOCKSPERPAGE, offsetof(struct ppc64_caches, dblocks_per_page)); - DEFINE(ICACHEL1BLOCKSIZE, offsetof(struct ppc64_caches, iblock_size)); - DEFINE(ICACHEL1LOGBLOCKSIZE, offsetof(struct ppc64_caches, log_iblock_size)); - DEFINE(ICACHEL1BLOCKSPERPAGE, offsetof(struct ppc64_caches, iblocks_per_page)); + DEFINE(DCACHEL1BLOCKSIZE, offsetof(struct ppc64_caches, l1d.block_size)); + DEFINE(DCACHEL1LOGBLOCKSIZE, offsetof(struct ppc64_caches, l1d.log_block_size)); + DEFINE(DCACHEL1BLOCKSPERPAGE, offsetof(struct ppc64_caches, l1d.blocks_per_page)); + DEFINE(ICACHEL1BLOCKSIZE, offsetof(struct ppc64_caches, l1i.block_size)); + DEFINE(ICACHEL1LOGBLOCKSIZE, offsetof(struct ppc64_caches, l1i.log_block_size)); + DEFINE(ICACHEL1BLOCKSPERPAGE, offsetof(struct ppc64_caches, l1i.blocks_per_page)); /* paca */ DEFINE(PACA_SIZE, sizeof(struct paca_struct)); DEFINE(PACAPACAINDEX, offsetof(struct paca_struct, paca_index)); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 75c9a8641ba1..b87dcb2968d9 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -78,10 +78,14 @@ int spinning_secondaries; u64 ppc64_pft_size; struct ppc64_caches ppc64_caches = { - .dblock_size = 0x40, - .log_dblock_size = 6, - .iblock_size = 0x40, - .log_iblock_size = 6 + .l1d = { + .block_size = 0x40, + .log_block_size = 6, + }, + .l1i = { + .block_size = 0x40, + .log_block_size = 6 + }, }; EXPORT_SYMBOL_GPL(ppc64_caches); @@ -397,105 +401,98 @@ void smp_release_cpus(void) * cache informations about the CPU that will be used by cache flush * routines and/or provided to userland */ + +static void init_cache_info(struct ppc_cache_info *info, u32 size, u32 lsize, + u32 bsize, u32 sets) +{ + info->size = size; + info->sets = sets; + info->line_size = lsize; + info->block_size = bsize; + info->log_block_size = __ilog2(bsize); + info->blocks_per_page = PAGE_SIZE / bsize; +} + +static bool __init parse_cache_info(struct device_node *np, + bool icache, + struct ppc_cache_info *info) +{ + static const char *ipropnames[] __initdata = { + "i-cache-size", + "i-cache-sets", + "i-cache-block-size", + "i-cache-line-size", + }; + static const char *dpropnames[] __initdata = { + "d-cache-size", + "d-cache-sets", + "d-cache-block-size", + "d-cache-line-size", + }; + const char **propnames = icache ? ipropnames : dpropnames; + const __be32 *sizep, *lsizep, *bsizep, *setsp; + u32 size, lsize, bsize, sets; + bool success = true; + + size = 0; + sets = -1u; + lsize = bsize = cur_cpu_spec->dcache_bsize; + sizep = of_get_property(np, propnames[0], NULL); + if (sizep != NULL) + size = be32_to_cpu(*sizep); + setsp = of_get_property(np, propnames[1], NULL); + if (setsp != NULL) + sets = be32_to_cpu(*setsp); + bsizep = of_get_property(np, propnames[2], NULL); + lsizep = of_get_property(np, propnames[3], NULL); + if (bsizep == NULL) + bsizep = lsizep; + if (lsizep != NULL) + lsize = be32_to_cpu(*lsizep); + if (bsizep != NULL) + bsize = be32_to_cpu(*bsizep); + if (sizep == NULL || bsizep == NULL || lsizep == NULL) + success = false; + + /* + * OF is weird .. it represents fully associative caches + * as "1 way" which doesn't make much sense and doesn't + * leave room for direct mapped. We'll assume that 0 + * in OF means direct mapped for that reason. + */ + if (sets == 1) + sets = 0; + else if (sets == 0) + sets = 1; + + init_cache_info(info, size, lsize, bsize, sets); + + return success; +} + void __init initialize_cache_info(void) { struct device_node *np; - unsigned long num_cpus = 0; DBG(" -> initialize_cache_info()\n"); - for_each_node_by_type(np, "cpu") { - num_cpus += 1; + np = of_find_node_by_type(NULL, "cpu"); - /* - * We're assuming *all* of the CPUs have the same - * d-cache and i-cache sizes... -Peter - */ - if (num_cpus == 1) { - const __be32 *sizep, *lsizep, *bsizep, *setsp; - u32 size, lsize, bsize, sets; - - size = 0; - sets = -1u; - lsize = bsize = cur_cpu_spec->dcache_bsize; - sizep = of_get_property(np, "d-cache-size", NULL); - if (sizep != NULL) - size = be32_to_cpu(*sizep); - setsp = of_get_property(np, "d-cache-sets", NULL); - if (setsp != NULL) - sets = be32_to_cpu(*setsp); - bsizep = of_get_property(np, "d-cache-block-size", - NULL); - lsizep = of_get_property(np, "d-cache-line-size", - NULL); - if (bsizep == NULL) - bsizep = lsizep; - if (lsizep != NULL) - lsize = be32_to_cpu(*lsizep); - if (bsizep != NULL) - bsize = be32_to_cpu(*bsizep); - if (sizep == NULL || bsizep == NULL || lsizep == NULL) - DBG("Argh, can't find dcache properties ! " - "sizep: %p, bsizep: %p, lsizep: %p\n", - sizep, bsizep, lsizep); - - /* - * OF is weird .. it represents fully associative caches - * as "1 way" which doesn't make much sense and doesn't - * leave room for direct mapped. We'll assume that 0 - * in OF means direct mapped for that reason. - */ - if (sets == 1) - sets = 0; - else if (sets == 0) - sets = 1; - ppc64_caches.dsize = size; - ppc64_caches.dsets = sets; - ppc64_caches.dline_size = lsize; - ppc64_caches.dblock_size = bsize; - ppc64_caches.log_dblock_size = __ilog2(bsize); - ppc64_caches.dblocks_per_page = PAGE_SIZE / bsize; - - size = 0; - sets = -1u; - lsize = bsize = cur_cpu_spec->icache_bsize; - sizep = of_get_property(np, "i-cache-size", NULL); - if (sizep != NULL) - size = be32_to_cpu(*sizep); - setsp = of_get_property(np, "i-cache-sets", NULL); - if (setsp != NULL) - sets = be32_to_cpu(*setsp); - bsizep = of_get_property(np, "i-cache-block-size", - NULL); - lsizep = of_get_property(np, "i-cache-line-size", - NULL); - if (bsizep == NULL) - bsizep = lsizep; - if (lsizep != NULL) - lsize = be32_to_cpu(*lsizep); - if (bsizep != NULL) - bsize = be32_to_cpu(*bsizep); - if (sizep == NULL || bsizep == NULL || lsizep == NULL) - DBG("Argh, can't find icache properties ! " - "sizep: %p, bsizep: %p, lsizep: %p\n", - sizep, bsizep, lsizep); - - if (sets == 1) - sets = 0; - else if (sets == 0) - sets = 1; - ppc64_caches.isize = size; - ppc64_caches.isets = sets; - ppc64_caches.iline_size = lsize; - ppc64_caches.iblock_size = bsize; - ppc64_caches.log_iblock_size = __ilog2(bsize); - ppc64_caches.iblocks_per_page = PAGE_SIZE / bsize; - } + /* + * We're assuming *all* of the CPUs have the same + * d-cache and i-cache sizes... -Peter + */ + if (np) { + if (!parse_cache_info(np, false, &ppc64_caches.l1d)) + DBG("Argh, can't find dcache properties !\n"); + + if (!parse_cache_info(np, true, &ppc64_caches.l1i)) + DBG("Argh, can't find icache properties !\n"); } /* For use by binfmt_elf */ - dcache_bsize = ppc64_caches.dblock_size; - icache_bsize = ppc64_caches.iblock_size; + dcache_bsize = ppc64_caches.l1d.block_size; + icache_bsize = ppc64_caches.l1i.block_size; DBG(" <- initialize_cache_info()\n"); } diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 9c0a85776c6c..22b01a3962f0 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -736,14 +736,14 @@ static int __init vdso_init(void) if (firmware_has_feature(FW_FEATURE_LPAR)) vdso_data->platform |= 1; vdso_data->physicalMemorySize = memblock_phys_mem_size(); - vdso_data->dcache_size = ppc64_caches.dsize; - vdso_data->dcache_line_size = ppc64_caches.dline_size; - vdso_data->icache_size = ppc64_caches.isize; - vdso_data->icache_line_size = ppc64_caches.iline_size; - vdso_data->dcache_block_size = ppc64_caches.dblock_size; - vdso_data->icache_block_size = ppc64_caches.iblock_size; - vdso_data->dcache_log_block_size = ppc64_caches.log_dblock_size; - vdso_data->icache_log_block_size = ppc64_caches.log_iblock_size; + vdso_data->dcache_size = ppc64_caches.l1d.size; + vdso_data->dcache_line_size = ppc64_caches.l1d.line_size; + vdso_data->icache_size = ppc64_caches.l1i.size; + vdso_data->icache_line_size = ppc64_caches.l1i.line_size; + vdso_data->dcache_block_size = ppc64_caches.l1d.block_size; + vdso_data->icache_block_size = ppc64_caches.l1i.block_size; + vdso_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size; + vdso_data->icache_log_block_size = ppc64_caches.l1i.log_block_size; /* * Calculate the size of the 64 bits vDSO -- cgit v1.2.3 From 65e01f386fcddb3460be78fc886856889f80ecc7 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Sun, 8 Jan 2017 17:31:48 -0600 Subject: powerpc/64: Add L2 and L3 cache shape info Retrieved from device-tree when available Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/cache.h | 2 ++ arch/powerpc/kernel/setup_64.c | 26 +++++++++++++++++++++----- 2 files changed, 23 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h index 823750fa6e66..d7cf60f87604 100644 --- a/arch/powerpc/include/asm/cache.h +++ b/arch/powerpc/include/asm/cache.h @@ -43,6 +43,8 @@ struct ppc_cache_info { struct ppc64_caches { struct ppc_cache_info l1d; struct ppc_cache_info l1i; + struct ppc_cache_info l2; + struct ppc_cache_info l3; }; extern struct ppc64_caches ppc64_caches; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index b87dcb2968d9..db18f7b68a1d 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -472,22 +472,38 @@ static bool __init parse_cache_info(struct device_node *np, void __init initialize_cache_info(void) { - struct device_node *np; + struct device_node *cpu, *l2, *l3 = NULL; DBG(" -> initialize_cache_info()\n"); - np = of_find_node_by_type(NULL, "cpu"); + cpu = of_find_node_by_type(NULL, "cpu"); /* * We're assuming *all* of the CPUs have the same * d-cache and i-cache sizes... -Peter */ - if (np) { - if (!parse_cache_info(np, false, &ppc64_caches.l1d)) + if (cpu) { + if (!parse_cache_info(cpu, false, &ppc64_caches.l1d)) DBG("Argh, can't find dcache properties !\n"); - if (!parse_cache_info(np, true, &ppc64_caches.l1i)) + if (!parse_cache_info(cpu, true, &ppc64_caches.l1i)) DBG("Argh, can't find icache properties !\n"); + + /* + * Try to find the L2 and L3 if any. Assume they are + * unified and use the D-side properties. + */ + l2 = of_find_next_cache_node(cpu); + of_node_put(cpu); + if (l2) { + parse_cache_info(l2, false, &ppc64_caches.l2); + l3 = of_find_next_cache_node(l2); + of_node_put(l2); + } + if (l3) { + parse_cache_info(l3, false, &ppc64_caches.l3); + of_node_put(l3); + } } /* For use by binfmt_elf */ -- cgit v1.2.3 From 98a5f361b8625c6f4841d6ba013bbf0e80d08147 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 3 Feb 2017 17:20:07 +1100 Subject: powerpc: Add new cache geometry aux vectors This adds AUX vectors for the L1I,D, L2 and L3 cache levels providing for each cache level the size of the cache in bytes and the geometry (line size and number of ways). We chose to not use the existing alpha/sh definition which packs all the information in a single entry per cache level as it is too restricted to represent some of the geometries used on POWER. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/cache.h | 1 + arch/powerpc/include/asm/elf.h | 20 ++++++++++++++++++++ arch/powerpc/include/uapi/asm/auxvec.h | 33 ++++++++++++++++++++++++++++++++- arch/powerpc/kernel/setup_64.c | 5 +++++ 4 files changed, 58 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h index d7cf60f87604..5a90292afbad 100644 --- a/arch/powerpc/include/asm/cache.h +++ b/arch/powerpc/include/asm/cache.h @@ -38,6 +38,7 @@ struct ppc_cache_info { u32 log_block_size; u32 blocks_per_page; u32 sets; + u32 assoc; }; struct ppc64_caches { diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index 730c27ed10e1..93b9b84568e8 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -136,6 +136,25 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm, #endif /* CONFIG_SPU_BASE */ +#ifdef CONFIG_PPC64 + +#define get_cache_geometry(level) \ + (ppc64_caches.level.assoc << 16 | ppc64_caches.level.line_size) + +#define ARCH_DLINFO_CACHE_GEOMETRY \ + NEW_AUX_ENT(AT_L1I_CACHESIZE, ppc64_caches.l1i.size); \ + NEW_AUX_ENT(AT_L1I_CACHEGEOMETRY, get_cache_geometry(l1i)); \ + NEW_AUX_ENT(AT_L1D_CACHESIZE, ppc64_caches.l1i.size); \ + NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, get_cache_geometry(l1i)); \ + NEW_AUX_ENT(AT_L2_CACHESIZE, ppc64_caches.l2.size); \ + NEW_AUX_ENT(AT_L2_CACHEGEOMETRY, get_cache_geometry(l2)); \ + NEW_AUX_ENT(AT_L3_CACHESIZE, ppc64_caches.l3.size); \ + NEW_AUX_ENT(AT_L3_CACHEGEOMETRY, get_cache_geometry(l3)) + +#else +#define ARCH_DLINFO_CACHE_GEOMETRY +#endif + /* * The requirements here are: * - keep the final alignment of sp (sp & 0xf) @@ -156,6 +175,7 @@ do { \ NEW_AUX_ENT(AT_ICACHEBSIZE, icache_bsize); \ NEW_AUX_ENT(AT_UCACHEBSIZE, ucache_bsize); \ VDSO_AUX_ENT(AT_SYSINFO_EHDR, current->mm->context.vdso_base); \ + ARCH_DLINFO_CACHE_GEOMETRY; \ } while (0) #endif /* _ASM_POWERPC_ELF_H */ diff --git a/arch/powerpc/include/uapi/asm/auxvec.h b/arch/powerpc/include/uapi/asm/auxvec.h index ce17d2c9eb4e..be6e94ecec42 100644 --- a/arch/powerpc/include/uapi/asm/auxvec.h +++ b/arch/powerpc/include/uapi/asm/auxvec.h @@ -16,6 +16,37 @@ */ #define AT_SYSINFO_EHDR 33 -#define AT_VECTOR_SIZE_ARCH 6 /* entries in ARCH_DLINFO */ +/* + * AT_*CACHEBSIZE above represent the cache *block* size which is + * the size that is affected by the cache management instructions. + * + * It doesn't nececssarily matches the cache *line* size which is + * more of a performance tuning hint. Additionally the latter can + * be different for the different cache levels. + * + * The set of entries below represent more extensive information + * about the caches, in the form of two entry per cache type, + * one entry containing the cache size in bytes, and the other + * containing the cache line size in bytes in the bottom 16 bits + * and the cache associativity in the next 16 bits. + * + * The associativity is such that if N is the 16-bit value, the + * cache is N way set associative. A value if 0xffff means fully + * associative, a value of 1 means directly mapped. + * + * For all these fields, a value of 0 means that the information + * is not known. + */ + +#define AT_L1I_CACHESIZE 40 +#define AT_L1I_CACHEGEOMETRY 41 +#define AT_L1D_CACHESIZE 42 +#define AT_L1D_CACHEGEOMETRY 43 +#define AT_L2_CACHESIZE 44 +#define AT_L2_CACHEGEOMETRY 45 +#define AT_L3_CACHESIZE 46 +#define AT_L3_CACHEGEOMETRY 47 + +#define AT_VECTOR_SIZE_ARCH 14 /* entries in ARCH_DLINFO */ #endif diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 364fbffd7e83..b9855f1b290a 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -411,6 +411,11 @@ static void init_cache_info(struct ppc_cache_info *info, u32 size, u32 lsize, info->block_size = bsize; info->log_block_size = __ilog2(bsize); info->blocks_per_page = PAGE_SIZE / bsize; + + if (sets == 0) + info->assoc = 0xffff; + else + info->assoc = size / (sets * lsize); } static bool __init parse_cache_info(struct device_node *np, -- cgit v1.2.3 From 852e5da99d15d0631c09e718abaa4b2fccda1185 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 6 Dec 2016 11:40:15 +1000 Subject: powerpc/64s: Tidy up after exception handler rework Somewhere along the line, search/replace left some naming garbled, and untidy alignment (aka. mpe stuffed it up). Might as well fix them all up now while git blame history doesn't extend too far. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/head-64.h | 160 +++++++++++++++++------------------ arch/powerpc/kernel/exceptions-64s.S | 2 +- 2 files changed, 81 insertions(+), 81 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h index fca7033839a9..c691fc2f5dae 100644 --- a/arch/powerpc/include/asm/head-64.h +++ b/arch/powerpc/include/asm/head-64.h @@ -102,7 +102,7 @@ name: #define FIXED_SECTION_ENTRY_BEGIN(sname, name) \ __FIXED_SECTION_ENTRY_BEGIN(sname, name, IFETCH_ALIGN_BYTES) -#define FIXED_SECTION_ENTRY_BEGIN_LOCATION(sname, name, start) \ +#define FIXED_SECTION_ENTRY_BEGIN_LOCATION(sname, name, start) \ USE_FIXED_SECTION(sname); \ name##_start = (start); \ .if (start) < sname##_start; \ @@ -113,7 +113,7 @@ name: .global name; \ name: -#define FIXED_SECTION_ENTRY_END_LOCATION(sname, name, end) \ +#define FIXED_SECTION_ENTRY_END_LOCATION(sname, name, end) \ .if (end) > sname##_end; \ .error "Fixed section overflow"; \ .abort; \ @@ -147,12 +147,12 @@ name: * Following are the BOOK3S exception handler helper macros. * Handlers come in a number of types, and each type has a number of varieties. * - * EXC_REAL_* - real, unrelocated exception vectors - * EXC_VIRT_* - virt (AIL), unrelocated exception vectors + * EXC_REAL_* - real, unrelocated exception vectors + * EXC_VIRT_* - virt (AIL), unrelocated exception vectors * TRAMP_REAL_* - real, unrelocated helpers (virt can call these) - * TRAMP_VIRT_* - virt, unreloc helpers (in practice, real can use) - * TRAMP_KVM - KVM handlers that get put into real, unrelocated - * EXC_COMMON_* - virt, relocated common handlers + * TRAMP_VIRT_* - virt, unreloc helpers (in practice, real can use) + * TRAMP_KVM - KVM handlers that get put into real, unrelocated + * EXC_COMMON_* - virt, relocated common handlers * * The EXC handlers are given a name, and branch to name_common, or the * appropriate KVM or masking function. Vector handler verieties are as @@ -194,20 +194,20 @@ name: #define EXC_REAL_BEGIN(name, start, end) \ FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##name, start) -#define EXC_REAL_END(name, start, end) \ +#define EXC_REAL_END(name, start, end) \ FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##name, end) #define EXC_VIRT_BEGIN(name, start, end) \ FIXED_SECTION_ENTRY_BEGIN_LOCATION(virt_vectors, exc_virt_##start##_##name, start) -#define EXC_VIRT_END(name, start, end) \ +#define EXC_VIRT_END(name, start, end) \ FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##name, end) -#define EXC_COMMON_BEGIN(name) \ - USE_TEXT_SECTION(); \ - .balign IFETCH_ALIGN_BYTES; \ - .global name; \ - DEFINE_FIXED_SYMBOL(name); \ +#define EXC_COMMON_BEGIN(name) \ + USE_TEXT_SECTION(); \ + .balign IFETCH_ALIGN_BYTES; \ + .global name; \ + DEFINE_FIXED_SYMBOL(name); \ name: #define TRAMP_REAL_BEGIN(name) \ @@ -217,7 +217,7 @@ name: FIXED_SECTION_ENTRY_BEGIN(virt_trampolines, name) #ifdef CONFIG_KVM_BOOK3S_64_HANDLER -#define TRAMP_KVM_BEGIN(name) \ +#define TRAMP_KVM_BEGIN(name) \ TRAMP_REAL_BEGIN(name) #else #define TRAMP_KVM_BEGIN(name) @@ -232,132 +232,132 @@ name: FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##unused, end); -#define EXC_REAL(name, start, end) \ - EXC_REAL_BEGIN(name, start, end); \ +#define EXC_REAL(name, start, end) \ + EXC_REAL_BEGIN(name, start, end); \ STD_EXCEPTION_PSERIES(start, name##_common); \ EXC_REAL_END(name, start, end); -#define EXC_VIRT(name, start, end, realvec) \ - EXC_VIRT_BEGIN(name, start, end); \ +#define EXC_VIRT(name, start, end, realvec) \ + EXC_VIRT_BEGIN(name, start, end); \ STD_RELON_EXCEPTION_PSERIES(start, realvec, name##_common); \ EXC_VIRT_END(name, start, end); -#define EXC_REAL_MASKABLE(name, start, end) \ - EXC_REAL_BEGIN(name, start, end); \ +#define EXC_REAL_MASKABLE(name, start, end) \ + EXC_REAL_BEGIN(name, start, end); \ MASKABLE_EXCEPTION_PSERIES(start, start, name##_common); \ EXC_REAL_END(name, start, end); -#define EXC_VIRT_MASKABLE(name, start, end, realvec) \ - EXC_VIRT_BEGIN(name, start, end); \ +#define EXC_VIRT_MASKABLE(name, start, end, realvec) \ + EXC_VIRT_BEGIN(name, start, end); \ MASKABLE_RELON_EXCEPTION_PSERIES(start, realvec, name##_common); \ EXC_VIRT_END(name, start, end); -#define EXC_REAL_HV(name, start, end) \ - EXC_REAL_BEGIN(name, start, end); \ +#define EXC_REAL_HV(name, start, end) \ + EXC_REAL_BEGIN(name, start, end); \ STD_EXCEPTION_HV(start, start, name##_common); \ EXC_REAL_END(name, start, end); -#define EXC_VIRT_HV(name, start, end, realvec) \ - EXC_VIRT_BEGIN(name, start, end); \ +#define EXC_VIRT_HV(name, start, end, realvec) \ + EXC_VIRT_BEGIN(name, start, end); \ STD_RELON_EXCEPTION_HV(start, realvec, name##_common); \ EXC_VIRT_END(name, start, end); -#define __EXC_REAL_OOL(name, start, end) \ - EXC_REAL_BEGIN(name, start, end); \ +#define __EXC_REAL_OOL(name, start, end) \ + EXC_REAL_BEGIN(name, start, end); \ __OOL_EXCEPTION(start, label, tramp_real_##name); \ EXC_REAL_END(name, start, end); -#define __TRAMP_REAL_REAL_OOL(name, vec) \ +#define __TRAMP_REAL_OOL(name, vec) \ TRAMP_REAL_BEGIN(tramp_real_##name); \ STD_EXCEPTION_PSERIES_OOL(vec, name##_common); \ -#define EXC_REAL_OOL(name, start, end) \ - __EXC_REAL_OOL(name, start, end); \ - __TRAMP_REAL_REAL_OOL(name, start); +#define EXC_REAL_OOL(name, start, end) \ + __EXC_REAL_OOL(name, start, end); \ + __TRAMP_REAL_OOL(name, start); -#define __EXC_REAL_OOL_MASKABLE(name, start, end) \ +#define __EXC_REAL_OOL_MASKABLE(name, start, end) \ __EXC_REAL_OOL(name, start, end); -#define __TRAMP_REAL_REAL_OOL_MASKABLE(name, vec) \ +#define __TRAMP_REAL_OOL_MASKABLE(name, vec) \ TRAMP_REAL_BEGIN(tramp_real_##name); \ MASKABLE_EXCEPTION_PSERIES_OOL(vec, name##_common); \ -#define EXC_REAL_OOL_MASKABLE(name, start, end) \ - __EXC_REAL_OOL_MASKABLE(name, start, end); \ - __TRAMP_REAL_REAL_OOL_MASKABLE(name, start); +#define EXC_REAL_OOL_MASKABLE(name, start, end) \ + __EXC_REAL_OOL_MASKABLE(name, start, end); \ + __TRAMP_REAL_OOL_MASKABLE(name, start); -#define __EXC_REAL_OOL_HV_DIRECT(name, start, end, handler) \ - EXC_REAL_BEGIN(name, start, end); \ +#define __EXC_REAL_OOL_HV_DIRECT(name, start, end, handler) \ + EXC_REAL_BEGIN(name, start, end); \ __OOL_EXCEPTION(start, label, handler); \ EXC_REAL_END(name, start, end); -#define __EXC_REAL_OOL_HV(name, start, end) \ +#define __EXC_REAL_OOL_HV(name, start, end) \ __EXC_REAL_OOL(name, start, end); -#define __TRAMP_REAL_REAL_OOL_HV(name, vec) \ +#define __TRAMP_REAL_OOL_HV(name, vec) \ TRAMP_REAL_BEGIN(tramp_real_##name); \ STD_EXCEPTION_HV_OOL(vec, name##_common); \ -#define EXC_REAL_OOL_HV(name, start, end) \ - __EXC_REAL_OOL_HV(name, start, end); \ - __TRAMP_REAL_REAL_OOL_HV(name, start); +#define EXC_REAL_OOL_HV(name, start, end) \ + __EXC_REAL_OOL_HV(name, start, end); \ + __TRAMP_REAL_OOL_HV(name, start); -#define __EXC_REAL_OOL_MASKABLE_HV(name, start, end) \ +#define __EXC_REAL_OOL_MASKABLE_HV(name, start, end) \ __EXC_REAL_OOL(name, start, end); -#define __TRAMP_REAL_REAL_OOL_MASKABLE_HV(name, vec) \ +#define __TRAMP_REAL_OOL_MASKABLE_HV(name, vec) \ TRAMP_REAL_BEGIN(tramp_real_##name); \ MASKABLE_EXCEPTION_HV_OOL(vec, name##_common); \ -#define EXC_REAL_OOL_MASKABLE_HV(name, start, end) \ - __EXC_REAL_OOL_MASKABLE_HV(name, start, end); \ - __TRAMP_REAL_REAL_OOL_MASKABLE_HV(name, start); +#define EXC_REAL_OOL_MASKABLE_HV(name, start, end) \ + __EXC_REAL_OOL_MASKABLE_HV(name, start, end); \ + __TRAMP_REAL_OOL_MASKABLE_HV(name, start); -#define __EXC_VIRT_OOL(name, start, end) \ - EXC_VIRT_BEGIN(name, start, end); \ +#define __EXC_VIRT_OOL(name, start, end) \ + EXC_VIRT_BEGIN(name, start, end); \ __OOL_EXCEPTION(start, label, tramp_virt_##name); \ EXC_VIRT_END(name, start, end); -#define __TRAMP_REAL_VIRT_OOL(name, realvec) \ - TRAMP_VIRT_BEGIN(tramp_virt_##name); \ +#define __TRAMP_VIRT_OOL(name, realvec) \ + TRAMP_VIRT_BEGIN(tramp_virt_##name); \ STD_RELON_EXCEPTION_PSERIES_OOL(realvec, name##_common); \ -#define EXC_VIRT_OOL(name, start, end, realvec) \ - __EXC_VIRT_OOL(name, start, end); \ - __TRAMP_REAL_VIRT_OOL(name, realvec); +#define EXC_VIRT_OOL(name, start, end, realvec) \ + __EXC_VIRT_OOL(name, start, end); \ + __TRAMP_VIRT_OOL(name, realvec); -#define __EXC_VIRT_OOL_MASKABLE(name, start, end) \ +#define __EXC_VIRT_OOL_MASKABLE(name, start, end) \ __EXC_VIRT_OOL(name, start, end); -#define __TRAMP_REAL_VIRT_OOL_MASKABLE(name, realvec) \ - TRAMP_VIRT_BEGIN(tramp_virt_##name); \ +#define __TRAMP_VIRT_OOL_MASKABLE(name, realvec) \ + TRAMP_VIRT_BEGIN(tramp_virt_##name); \ MASKABLE_RELON_EXCEPTION_PSERIES_OOL(realvec, name##_common); \ -#define EXC_VIRT_OOL_MASKABLE(name, start, end, realvec) \ - __EXC_VIRT_OOL_MASKABLE(name, start, end); \ - __TRAMP_REAL_VIRT_OOL_MASKABLE(name, realvec); +#define EXC_VIRT_OOL_MASKABLE(name, start, end, realvec) \ + __EXC_VIRT_OOL_MASKABLE(name, start, end); \ + __TRAMP_VIRT_OOL_MASKABLE(name, realvec); -#define __EXC_VIRT_OOL_HV(name, start, end) \ +#define __EXC_VIRT_OOL_HV(name, start, end) \ __EXC_VIRT_OOL(name, start, end); -#define __TRAMP_REAL_VIRT_OOL_HV(name, realvec) \ - TRAMP_VIRT_BEGIN(tramp_virt_##name); \ +#define __TRAMP_VIRT_OOL_HV(name, realvec) \ + TRAMP_VIRT_BEGIN(tramp_virt_##name); \ STD_RELON_EXCEPTION_HV_OOL(realvec, name##_common); \ -#define EXC_VIRT_OOL_HV(name, start, end, realvec) \ - __EXC_VIRT_OOL_HV(name, start, end); \ - __TRAMP_REAL_VIRT_OOL_HV(name, realvec); +#define EXC_VIRT_OOL_HV(name, start, end, realvec) \ + __EXC_VIRT_OOL_HV(name, start, end); \ + __TRAMP_VIRT_OOL_HV(name, realvec); -#define __EXC_VIRT_OOL_MASKABLE_HV(name, start, end) \ +#define __EXC_VIRT_OOL_MASKABLE_HV(name, start, end) \ __EXC_VIRT_OOL(name, start, end); -#define __TRAMP_REAL_VIRT_OOL_MASKABLE_HV(name, realvec) \ - TRAMP_VIRT_BEGIN(tramp_virt_##name); \ +#define __TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec) \ + TRAMP_VIRT_BEGIN(tramp_virt_##name); \ MASKABLE_RELON_EXCEPTION_HV_OOL(realvec, name##_common); \ -#define EXC_VIRT_OOL_MASKABLE_HV(name, start, end, realvec) \ - __EXC_VIRT_OOL_MASKABLE_HV(name, start, end); \ - __TRAMP_REAL_VIRT_OOL_MASKABLE_HV(name, realvec); +#define EXC_VIRT_OOL_MASKABLE_HV(name, start, end, realvec) \ + __EXC_VIRT_OOL_MASKABLE_HV(name, start, end); \ + __TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec); #define TRAMP_KVM(area, n) \ TRAMP_KVM_BEGIN(do_kvm_##n); \ @@ -378,16 +378,16 @@ name: TRAMP_KVM_BEGIN(do_kvm_H##n); \ KVM_HANDLER_SKIP(area, EXC_HV, n + 0x2); \ -#define EXC_COMMON(name, realvec, hdlr) \ - EXC_COMMON_BEGIN(name); \ +#define EXC_COMMON(name, realvec, hdlr) \ + EXC_COMMON_BEGIN(name); \ STD_EXCEPTION_COMMON(realvec, name, hdlr); \ -#define EXC_COMMON_ASYNC(name, realvec, hdlr) \ - EXC_COMMON_BEGIN(name); \ +#define EXC_COMMON_ASYNC(name, realvec, hdlr) \ + EXC_COMMON_BEGIN(name); \ STD_EXCEPTION_COMMON_ASYNC(realvec, name, hdlr); \ #define EXC_COMMON_HV(name, realvec, hdlr) \ - EXC_COMMON_BEGIN(name); \ + EXC_COMMON_BEGIN(name); \ STD_EXCEPTION_COMMON(realvec + 0x2, name, hdlr); \ #endif /* _ASM_POWERPC_HEAD_64_H */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 069aac8af909..bc1c2479a04c 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -960,7 +960,7 @@ EXC_COMMON(emulation_assist_common, 0xe40, emulation_assist_interrupt) * mode. */ __EXC_REAL_OOL_HV_DIRECT(hmi_exception, 0xe60, 0xe80, hmi_exception_early) -__TRAMP_REAL_REAL_OOL_MASKABLE_HV(hmi_exception, 0xe60) +__TRAMP_REAL_OOL_MASKABLE_HV(hmi_exception, 0xe60) EXC_VIRT_NONE(0x4e60, 0x4e80) TRAMP_KVM_HV(PACA_EXGEN, 0xe60) TRAMP_REAL_BEGIN(hmi_exception_early) -- cgit v1.2.3 From 1a6822d194c3f627eeb6aaca6688a5d0a444663e Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 6 Dec 2016 11:41:12 +1000 Subject: powerpc/64s: Use (start, size) rather than (start, end) for exception handlers start,size has the benefit of being easier to search for (start,end usually gives you the preceeding vector from the one you want, as first result). Suggested-by: Benjamin Herrenschmidt Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/head-64.h | 158 ++++++++++++++-------------- arch/powerpc/kernel/exceptions-64s.S | 195 ++++++++++++++++++----------------- 2 files changed, 185 insertions(+), 168 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h index c691fc2f5dae..a475711cd9c3 100644 --- a/arch/powerpc/include/asm/head-64.h +++ b/arch/powerpc/include/asm/head-64.h @@ -38,8 +38,8 @@ * li r10,128 * mv r11,r10 - * FIXED_SECTION_ENTRY_BEGIN_LOCATION(section_name, label2, start_address) - * FIXED_SECTION_ENTRY_END_LOCATION(section_name, label2, end_address) + * FIXED_SECTION_ENTRY_BEGIN_LOCATION(section_name, label2, start_address, size) + * FIXED_SECTION_ENTRY_END_LOCATION(section_name, label2, start_address, size) * CLOSE_FIXED_SECTION(section_name) * * ZERO_FIXED_SECTION can be used to emit zeroed data. @@ -102,9 +102,15 @@ name: #define FIXED_SECTION_ENTRY_BEGIN(sname, name) \ __FIXED_SECTION_ENTRY_BEGIN(sname, name, IFETCH_ALIGN_BYTES) -#define FIXED_SECTION_ENTRY_BEGIN_LOCATION(sname, name, start) \ +#define FIXED_SECTION_ENTRY_BEGIN_LOCATION(sname, name, start, size) \ USE_FIXED_SECTION(sname); \ name##_start = (start); \ + .if ((start) % (size) != 0); \ + .error "Fixed section exception vector misalignment"; \ + .endif; \ + .if ((size) != 0x20) && ((size) != 0x80) && ((size) != 0x100); \ + .error "Fixed section exception vector bad size"; \ + .endif; \ .if (start) < sname##_start; \ .error "Fixed section underflow"; \ .abort; \ @@ -113,16 +119,16 @@ name: .global name; \ name: -#define FIXED_SECTION_ENTRY_END_LOCATION(sname, name, end) \ - .if (end) > sname##_end; \ +#define FIXED_SECTION_ENTRY_END_LOCATION(sname, name, start, size) \ + .if (start) + (size) > sname##_end; \ .error "Fixed section overflow"; \ .abort; \ .endif; \ - .if (. - name > end - name##_start); \ + .if (. - name > (start) + (size) - name##_start); \ .error "Fixed entry overflow"; \ .abort; \ .endif; \ - . = ((end) - sname##_start); \ + . = ((start) + (size) - sname##_start); \ /* @@ -191,17 +197,17 @@ name: * and OOL handlers are implemented as types of TRAMP and TRAMP_VIRT handlers. */ -#define EXC_REAL_BEGIN(name, start, end) \ - FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##name, start) +#define EXC_REAL_BEGIN(name, start, size) \ + FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##name, start, size) -#define EXC_REAL_END(name, start, end) \ - FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##name, end) +#define EXC_REAL_END(name, start, size) \ + FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##name, start, size) -#define EXC_VIRT_BEGIN(name, start, end) \ - FIXED_SECTION_ENTRY_BEGIN_LOCATION(virt_vectors, exc_virt_##start##_##name, start) +#define EXC_VIRT_BEGIN(name, start, size) \ + FIXED_SECTION_ENTRY_BEGIN_LOCATION(virt_vectors, exc_virt_##start##_##name, start, size) -#define EXC_VIRT_END(name, start, end) \ - FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##name, end) +#define EXC_VIRT_END(name, start, size) \ + FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##name, start, size) #define EXC_COMMON_BEGIN(name) \ USE_TEXT_SECTION(); \ @@ -223,140 +229,140 @@ name: #define TRAMP_KVM_BEGIN(name) #endif -#define EXC_REAL_NONE(start, end) \ - FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##unused, start); \ - FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##unused, end) +#define EXC_REAL_NONE(start, size) \ + FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##unused, start, size); \ + FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##unused, start, size) -#define EXC_VIRT_NONE(start, end) \ - FIXED_SECTION_ENTRY_BEGIN_LOCATION(virt_vectors, exc_virt_##start##_##unused, start); \ - FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##unused, end); +#define EXC_VIRT_NONE(start, size) \ + FIXED_SECTION_ENTRY_BEGIN_LOCATION(virt_vectors, exc_virt_##start##_##unused, start, size); \ + FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##unused, start, size); -#define EXC_REAL(name, start, end) \ - EXC_REAL_BEGIN(name, start, end); \ +#define EXC_REAL(name, start, size) \ + EXC_REAL_BEGIN(name, start, size); \ STD_EXCEPTION_PSERIES(start, name##_common); \ - EXC_REAL_END(name, start, end); + EXC_REAL_END(name, start, size); -#define EXC_VIRT(name, start, end, realvec) \ - EXC_VIRT_BEGIN(name, start, end); \ +#define EXC_VIRT(name, start, size, realvec) \ + EXC_VIRT_BEGIN(name, start, size); \ STD_RELON_EXCEPTION_PSERIES(start, realvec, name##_common); \ - EXC_VIRT_END(name, start, end); + EXC_VIRT_END(name, start, size); -#define EXC_REAL_MASKABLE(name, start, end) \ - EXC_REAL_BEGIN(name, start, end); \ +#define EXC_REAL_MASKABLE(name, start, size) \ + EXC_REAL_BEGIN(name, start, size); \ MASKABLE_EXCEPTION_PSERIES(start, start, name##_common); \ - EXC_REAL_END(name, start, end); + EXC_REAL_END(name, start, size); -#define EXC_VIRT_MASKABLE(name, start, end, realvec) \ - EXC_VIRT_BEGIN(name, start, end); \ +#define EXC_VIRT_MASKABLE(name, start, size, realvec) \ + EXC_VIRT_BEGIN(name, start, size); \ MASKABLE_RELON_EXCEPTION_PSERIES(start, realvec, name##_common); \ - EXC_VIRT_END(name, start, end); + EXC_VIRT_END(name, start, size); -#define EXC_REAL_HV(name, start, end) \ - EXC_REAL_BEGIN(name, start, end); \ +#define EXC_REAL_HV(name, start, size) \ + EXC_REAL_BEGIN(name, start, size); \ STD_EXCEPTION_HV(start, start, name##_common); \ - EXC_REAL_END(name, start, end); + EXC_REAL_END(name, start, size); -#define EXC_VIRT_HV(name, start, end, realvec) \ - EXC_VIRT_BEGIN(name, start, end); \ +#define EXC_VIRT_HV(name, start, size, realvec) \ + EXC_VIRT_BEGIN(name, start, size); \ STD_RELON_EXCEPTION_HV(start, realvec, name##_common); \ - EXC_VIRT_END(name, start, end); + EXC_VIRT_END(name, start, size); -#define __EXC_REAL_OOL(name, start, end) \ - EXC_REAL_BEGIN(name, start, end); \ +#define __EXC_REAL_OOL(name, start, size) \ + EXC_REAL_BEGIN(name, start, size); \ __OOL_EXCEPTION(start, label, tramp_real_##name); \ - EXC_REAL_END(name, start, end); + EXC_REAL_END(name, start, size); #define __TRAMP_REAL_OOL(name, vec) \ TRAMP_REAL_BEGIN(tramp_real_##name); \ STD_EXCEPTION_PSERIES_OOL(vec, name##_common); \ -#define EXC_REAL_OOL(name, start, end) \ - __EXC_REAL_OOL(name, start, end); \ +#define EXC_REAL_OOL(name, start, size) \ + __EXC_REAL_OOL(name, start, size); \ __TRAMP_REAL_OOL(name, start); -#define __EXC_REAL_OOL_MASKABLE(name, start, end) \ - __EXC_REAL_OOL(name, start, end); +#define __EXC_REAL_OOL_MASKABLE(name, start, size) \ + __EXC_REAL_OOL(name, start, size); #define __TRAMP_REAL_OOL_MASKABLE(name, vec) \ TRAMP_REAL_BEGIN(tramp_real_##name); \ MASKABLE_EXCEPTION_PSERIES_OOL(vec, name##_common); \ -#define EXC_REAL_OOL_MASKABLE(name, start, end) \ - __EXC_REAL_OOL_MASKABLE(name, start, end); \ +#define EXC_REAL_OOL_MASKABLE(name, start, size) \ + __EXC_REAL_OOL_MASKABLE(name, start, size); \ __TRAMP_REAL_OOL_MASKABLE(name, start); -#define __EXC_REAL_OOL_HV_DIRECT(name, start, end, handler) \ - EXC_REAL_BEGIN(name, start, end); \ +#define __EXC_REAL_OOL_HV_DIRECT(name, start, size, handler) \ + EXC_REAL_BEGIN(name, start, size); \ __OOL_EXCEPTION(start, label, handler); \ - EXC_REAL_END(name, start, end); + EXC_REAL_END(name, start, size); -#define __EXC_REAL_OOL_HV(name, start, end) \ - __EXC_REAL_OOL(name, start, end); +#define __EXC_REAL_OOL_HV(name, start, size) \ + __EXC_REAL_OOL(name, start, size); #define __TRAMP_REAL_OOL_HV(name, vec) \ TRAMP_REAL_BEGIN(tramp_real_##name); \ STD_EXCEPTION_HV_OOL(vec, name##_common); \ -#define EXC_REAL_OOL_HV(name, start, end) \ - __EXC_REAL_OOL_HV(name, start, end); \ +#define EXC_REAL_OOL_HV(name, start, size) \ + __EXC_REAL_OOL_HV(name, start, size); \ __TRAMP_REAL_OOL_HV(name, start); -#define __EXC_REAL_OOL_MASKABLE_HV(name, start, end) \ - __EXC_REAL_OOL(name, start, end); +#define __EXC_REAL_OOL_MASKABLE_HV(name, start, size) \ + __EXC_REAL_OOL(name, start, size); #define __TRAMP_REAL_OOL_MASKABLE_HV(name, vec) \ TRAMP_REAL_BEGIN(tramp_real_##name); \ MASKABLE_EXCEPTION_HV_OOL(vec, name##_common); \ -#define EXC_REAL_OOL_MASKABLE_HV(name, start, end) \ - __EXC_REAL_OOL_MASKABLE_HV(name, start, end); \ +#define EXC_REAL_OOL_MASKABLE_HV(name, start, size) \ + __EXC_REAL_OOL_MASKABLE_HV(name, start, size); \ __TRAMP_REAL_OOL_MASKABLE_HV(name, start); -#define __EXC_VIRT_OOL(name, start, end) \ - EXC_VIRT_BEGIN(name, start, end); \ +#define __EXC_VIRT_OOL(name, start, size) \ + EXC_VIRT_BEGIN(name, start, size); \ __OOL_EXCEPTION(start, label, tramp_virt_##name); \ - EXC_VIRT_END(name, start, end); + EXC_VIRT_END(name, start, size); #define __TRAMP_VIRT_OOL(name, realvec) \ TRAMP_VIRT_BEGIN(tramp_virt_##name); \ STD_RELON_EXCEPTION_PSERIES_OOL(realvec, name##_common); \ -#define EXC_VIRT_OOL(name, start, end, realvec) \ - __EXC_VIRT_OOL(name, start, end); \ +#define EXC_VIRT_OOL(name, start, size, realvec) \ + __EXC_VIRT_OOL(name, start, size); \ __TRAMP_VIRT_OOL(name, realvec); -#define __EXC_VIRT_OOL_MASKABLE(name, start, end) \ - __EXC_VIRT_OOL(name, start, end); +#define __EXC_VIRT_OOL_MASKABLE(name, start, size) \ + __EXC_VIRT_OOL(name, start, size); #define __TRAMP_VIRT_OOL_MASKABLE(name, realvec) \ TRAMP_VIRT_BEGIN(tramp_virt_##name); \ MASKABLE_RELON_EXCEPTION_PSERIES_OOL(realvec, name##_common); \ -#define EXC_VIRT_OOL_MASKABLE(name, start, end, realvec) \ - __EXC_VIRT_OOL_MASKABLE(name, start, end); \ +#define EXC_VIRT_OOL_MASKABLE(name, start, size, realvec) \ + __EXC_VIRT_OOL_MASKABLE(name, start, size); \ __TRAMP_VIRT_OOL_MASKABLE(name, realvec); -#define __EXC_VIRT_OOL_HV(name, start, end) \ - __EXC_VIRT_OOL(name, start, end); +#define __EXC_VIRT_OOL_HV(name, start, size) \ + __EXC_VIRT_OOL(name, start, size); #define __TRAMP_VIRT_OOL_HV(name, realvec) \ TRAMP_VIRT_BEGIN(tramp_virt_##name); \ STD_RELON_EXCEPTION_HV_OOL(realvec, name##_common); \ -#define EXC_VIRT_OOL_HV(name, start, end, realvec) \ - __EXC_VIRT_OOL_HV(name, start, end); \ +#define EXC_VIRT_OOL_HV(name, start, size, realvec) \ + __EXC_VIRT_OOL_HV(name, start, size); \ __TRAMP_VIRT_OOL_HV(name, realvec); -#define __EXC_VIRT_OOL_MASKABLE_HV(name, start, end) \ - __EXC_VIRT_OOL(name, start, end); +#define __EXC_VIRT_OOL_MASKABLE_HV(name, start, size) \ + __EXC_VIRT_OOL(name, start, size); #define __TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec) \ TRAMP_VIRT_BEGIN(tramp_virt_##name); \ MASKABLE_RELON_EXCEPTION_HV_OOL(realvec, name##_common); \ -#define EXC_VIRT_OOL_MASKABLE_HV(name, start, end, realvec) \ - __EXC_VIRT_OOL_MASKABLE_HV(name, start, end); \ +#define EXC_VIRT_OOL_MASKABLE_HV(name, start, size, realvec) \ + __EXC_VIRT_OOL_MASKABLE_HV(name, start, size); \ __TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec); #define TRAMP_KVM(area, n) \ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index bc1c2479a04c..a6205a4a3574 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -93,7 +93,7 @@ USE_FIXED_SECTION(real_vectors) __start_interrupts: /* No virt vectors corresponding with 0x0..0x100 */ -EXC_VIRT_NONE(0x4000, 0x4100) +EXC_VIRT_NONE(0x4000, 0x100) #ifdef CONFIG_PPC_P7_NAP @@ -114,15 +114,15 @@ EXC_VIRT_NONE(0x4000, 0x4100) #define IDLETEST NOTEST #endif -EXC_REAL_BEGIN(system_reset, 0x100, 0x200) +EXC_REAL_BEGIN(system_reset, 0x100, 0x100) SET_SCRATCH0(r13) GET_PACA(r13) clrrdi r13,r13,1 /* Last bit of HSPRG0 is set if waking from winkle */ EXCEPTION_PROLOG_PSERIES_PACA(PACA_EXGEN, system_reset_common, EXC_STD, IDLETEST, 0x100) -EXC_REAL_END(system_reset, 0x100, 0x200) -EXC_VIRT_NONE(0x4100, 0x4200) +EXC_REAL_END(system_reset, 0x100, 0x100) +EXC_VIRT_NONE(0x4100, 0x100) #ifdef CONFIG_PPC_P7_NAP EXC_COMMON_BEGIN(system_reset_idle_common) @@ -166,7 +166,7 @@ TRAMP_REAL_BEGIN(system_reset_fwnmi) #endif /* CONFIG_PPC_PSERIES */ -EXC_REAL_BEGIN(machine_check, 0x200, 0x300) +EXC_REAL_BEGIN(machine_check, 0x200, 0x100) /* This is moved out of line as it can be patched by FW, but * some code path might still want to branch into the original * vector @@ -186,8 +186,8 @@ BEGIN_FTR_SECTION FTR_SECTION_ELSE b machine_check_pSeries_0 ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) -EXC_REAL_END(machine_check, 0x200, 0x300) -EXC_VIRT_NONE(0x4200, 0x4300) +EXC_REAL_END(machine_check, 0x200, 0x100) +EXC_VIRT_NONE(0x4200, 0x100) TRAMP_REAL_BEGIN(machine_check_powernv_early) BEGIN_FTR_SECTION EXCEPTION_PROLOG_1(PACA_EXMC, NOTEST, 0x200) @@ -483,8 +483,8 @@ EXC_COMMON_BEGIN(unrecover_mce) b 1b -EXC_REAL(data_access, 0x300, 0x380) -EXC_VIRT(data_access, 0x4300, 0x4380, 0x300) +EXC_REAL(data_access, 0x300, 0x80) +EXC_VIRT(data_access, 0x4300, 0x80, 0x300) TRAMP_KVM_SKIP(PACA_EXGEN, 0x300) EXC_COMMON_BEGIN(data_access_common) @@ -512,7 +512,7 @@ MMU_FTR_SECTION_ELSE ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) -EXC_REAL_BEGIN(data_access_slb, 0x380, 0x400) +EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80) SET_SCRATCH0(r13) EXCEPTION_PROLOG_0(PACA_EXSLB) EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x380) @@ -533,9 +533,9 @@ EXC_REAL_BEGIN(data_access_slb, 0x380, 0x400) mtctr r10 bctr #endif -EXC_REAL_END(data_access_slb, 0x380, 0x400) +EXC_REAL_END(data_access_slb, 0x380, 0x80) -EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x4400) +EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x80) SET_SCRATCH0(r13) EXCEPTION_PROLOG_0(PACA_EXSLB) EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x380) @@ -556,12 +556,12 @@ EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x4400) mtctr r10 bctr #endif -EXC_VIRT_END(data_access_slb, 0x4380, 0x4400) +EXC_VIRT_END(data_access_slb, 0x4380, 0x80) TRAMP_KVM_SKIP(PACA_EXSLB, 0x380) -EXC_REAL(instruction_access, 0x400, 0x480) -EXC_VIRT(instruction_access, 0x4400, 0x4480, 0x400) +EXC_REAL(instruction_access, 0x400, 0x80) +EXC_VIRT(instruction_access, 0x4400, 0x80, 0x400) TRAMP_KVM(PACA_EXGEN, 0x400) EXC_COMMON_BEGIN(instruction_access_common) @@ -580,7 +580,7 @@ MMU_FTR_SECTION_ELSE ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) -EXC_REAL_BEGIN(instruction_access_slb, 0x480, 0x500) +EXC_REAL_BEGIN(instruction_access_slb, 0x480, 0x80) SET_SCRATCH0(r13) EXCEPTION_PROLOG_0(PACA_EXSLB) EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480) @@ -596,9 +596,9 @@ EXC_REAL_BEGIN(instruction_access_slb, 0x480, 0x500) mtctr r10 bctr #endif -EXC_REAL_END(instruction_access_slb, 0x480, 0x500) +EXC_REAL_END(instruction_access_slb, 0x480, 0x80) -EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x4500) +EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x80) SET_SCRATCH0(r13) EXCEPTION_PROLOG_0(PACA_EXSLB) EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x480) @@ -614,7 +614,7 @@ EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x4500) mtctr r10 bctr #endif -EXC_VIRT_END(instruction_access_slb, 0x4480, 0x4500) +EXC_VIRT_END(instruction_access_slb, 0x4480, 0x80) TRAMP_KVM(PACA_EXSLB, 0x480) @@ -711,7 +711,7 @@ EXC_COMMON_BEGIN(bad_addr_slb) bl slb_miss_bad_addr b ret_from_except -EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x600) +EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x100) .globl hardware_interrupt_hv; hardware_interrupt_hv: BEGIN_FTR_SECTION @@ -725,9 +725,9 @@ do_kvm_H0x500: do_kvm_0x500: KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500) ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) -EXC_REAL_END(hardware_interrupt, 0x500, 0x600) +EXC_REAL_END(hardware_interrupt, 0x500, 0x100) -EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x4600) +EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x100) .globl hardware_interrupt_relon_hv; hardware_interrupt_relon_hv: BEGIN_FTR_SECTION @@ -735,13 +735,13 @@ hardware_interrupt_relon_hv: FTR_SECTION_ELSE _MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, EXC_STD, SOFTEN_TEST_PR) ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) -EXC_VIRT_END(hardware_interrupt, 0x4500, 0x4600) +EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100) EXC_COMMON_ASYNC(hardware_interrupt_common, 0x500, do_IRQ) -EXC_REAL(alignment, 0x600, 0x700) -EXC_VIRT(alignment, 0x4600, 0x4700, 0x600) +EXC_REAL(alignment, 0x600, 0x100) +EXC_VIRT(alignment, 0x4600, 0x100, 0x600) TRAMP_KVM(PACA_EXGEN, 0x600) EXC_COMMON_BEGIN(alignment_common) mfspr r10,SPRN_DAR @@ -760,8 +760,8 @@ EXC_COMMON_BEGIN(alignment_common) b ret_from_except -EXC_REAL(program_check, 0x700, 0x800) -EXC_VIRT(program_check, 0x4700, 0x4800, 0x700) +EXC_REAL(program_check, 0x700, 0x100) +EXC_VIRT(program_check, 0x4700, 0x100, 0x700) TRAMP_KVM(PACA_EXGEN, 0x700) EXC_COMMON_BEGIN(program_check_common) EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) @@ -772,8 +772,8 @@ EXC_COMMON_BEGIN(program_check_common) b ret_from_except -EXC_REAL(fp_unavailable, 0x800, 0x900) -EXC_VIRT(fp_unavailable, 0x4800, 0x4900, 0x800) +EXC_REAL(fp_unavailable, 0x800, 0x100) +EXC_VIRT(fp_unavailable, 0x4800, 0x100, 0x800) TRAMP_KVM(PACA_EXGEN, 0x800) EXC_COMMON_BEGIN(fp_unavailable_common) EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN) @@ -805,20 +805,20 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif -EXC_REAL_MASKABLE(decrementer, 0x900, 0x980) -EXC_VIRT_MASKABLE(decrementer, 0x4900, 0x4980, 0x900) +EXC_REAL_MASKABLE(decrementer, 0x900, 0x80) +EXC_VIRT_MASKABLE(decrementer, 0x4900, 0x80, 0x900) TRAMP_KVM(PACA_EXGEN, 0x900) EXC_COMMON_ASYNC(decrementer_common, 0x900, timer_interrupt) -EXC_REAL_HV(hdecrementer, 0x980, 0xa00) -EXC_VIRT_HV(hdecrementer, 0x4980, 0x4a00, 0x980) +EXC_REAL_HV(hdecrementer, 0x980, 0x80) +EXC_VIRT_HV(hdecrementer, 0x4980, 0x80, 0x980) TRAMP_KVM_HV(PACA_EXGEN, 0x980) EXC_COMMON(hdecrementer_common, 0x980, hdec_interrupt) -EXC_REAL_MASKABLE(doorbell_super, 0xa00, 0xb00) -EXC_VIRT_MASKABLE(doorbell_super, 0x4a00, 0x4b00, 0xa00) +EXC_REAL_MASKABLE(doorbell_super, 0xa00, 0x100) +EXC_VIRT_MASKABLE(doorbell_super, 0x4a00, 0x100, 0xa00) TRAMP_KVM(PACA_EXGEN, 0xa00) #ifdef CONFIG_PPC_DOORBELL EXC_COMMON_ASYNC(doorbell_super_common, 0xa00, doorbell_exception) @@ -827,8 +827,8 @@ EXC_COMMON_ASYNC(doorbell_super_common, 0xa00, unknown_exception) #endif -EXC_REAL(trap_0b, 0xb00, 0xc00) -EXC_VIRT(trap_0b, 0x4b00, 0x4c00, 0xb00) +EXC_REAL(trap_0b, 0xb00, 0x100) +EXC_VIRT(trap_0b, 0x4b00, 0x100, 0xb00) TRAMP_KVM(PACA_EXGEN, 0xb00) EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) @@ -884,7 +884,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \ b system_call_common ; #endif -EXC_REAL_BEGIN(system_call, 0xc00, 0xd00) +EXC_REAL_BEGIN(system_call, 0xc00, 0x100) /* * If CONFIG_KVM_BOOK3S_64_HANDLER is set, save the PPR (on systems * that support it) before changing to HMT_MEDIUM. That allows the KVM @@ -909,25 +909,25 @@ EXC_REAL_BEGIN(system_call, 0xc00, 0xd00) SYSCALL_PSERIES_1 SYSCALL_PSERIES_2_RFID SYSCALL_PSERIES_3 -EXC_REAL_END(system_call, 0xc00, 0xd00) +EXC_REAL_END(system_call, 0xc00, 0x100) -EXC_VIRT_BEGIN(system_call, 0x4c00, 0x4d00) +EXC_VIRT_BEGIN(system_call, 0x4c00, 0x100) HMT_MEDIUM SYSCALL_PSERIES_1 SYSCALL_PSERIES_2_DIRECT SYSCALL_PSERIES_3 -EXC_VIRT_END(system_call, 0x4c00, 0x4d00) +EXC_VIRT_END(system_call, 0x4c00, 0x100) TRAMP_KVM(PACA_EXGEN, 0xc00) -EXC_REAL(single_step, 0xd00, 0xe00) -EXC_VIRT(single_step, 0x4d00, 0x4e00, 0xd00) +EXC_REAL(single_step, 0xd00, 0x100) +EXC_VIRT(single_step, 0x4d00, 0x100, 0xd00) TRAMP_KVM(PACA_EXGEN, 0xd00) EXC_COMMON(single_step_common, 0xd00, single_step_exception) -EXC_REAL_OOL_HV(h_data_storage, 0xe00, 0xe20) -EXC_VIRT_NONE(0x4e00, 0x4e20) +EXC_REAL_OOL_HV(h_data_storage, 0xe00, 0x20) +EXC_VIRT_NONE(0x4e00, 0x20) TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0xe00) EXC_COMMON_BEGIN(h_data_storage_common) mfspr r10,SPRN_HDAR @@ -942,14 +942,14 @@ EXC_COMMON_BEGIN(h_data_storage_common) b ret_from_except -EXC_REAL_OOL_HV(h_instr_storage, 0xe20, 0xe40) -EXC_VIRT_NONE(0x4e20, 0x4e40) +EXC_REAL_OOL_HV(h_instr_storage, 0xe20, 0x20) +EXC_VIRT_NONE(0x4e20, 0x20) TRAMP_KVM_HV(PACA_EXGEN, 0xe20) EXC_COMMON(h_instr_storage_common, 0xe20, unknown_exception) -EXC_REAL_OOL_HV(emulation_assist, 0xe40, 0xe60) -EXC_VIRT_OOL_HV(emulation_assist, 0x4e40, 0x4e60, 0xe40) +EXC_REAL_OOL_HV(emulation_assist, 0xe40, 0x20) +EXC_VIRT_OOL_HV(emulation_assist, 0x4e40, 0x20, 0xe40) TRAMP_KVM_HV(PACA_EXGEN, 0xe40) EXC_COMMON(emulation_assist_common, 0xe40, emulation_assist_interrupt) @@ -959,9 +959,9 @@ EXC_COMMON(emulation_assist_common, 0xe40, emulation_assist_interrupt) * first, and then eventaully from there to the trampoline to get into virtual * mode. */ -__EXC_REAL_OOL_HV_DIRECT(hmi_exception, 0xe60, 0xe80, hmi_exception_early) +__EXC_REAL_OOL_HV_DIRECT(hmi_exception, 0xe60, 0x20, hmi_exception_early) __TRAMP_REAL_OOL_MASKABLE_HV(hmi_exception, 0xe60) -EXC_VIRT_NONE(0x4e60, 0x4e80) +EXC_VIRT_NONE(0x4e60, 0x20) TRAMP_KVM_HV(PACA_EXGEN, 0xe60) TRAMP_REAL_BEGIN(hmi_exception_early) EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_HV, 0xe60) @@ -1015,8 +1015,8 @@ hmi_exception_after_realmode: EXC_COMMON_ASYNC(hmi_exception_common, 0xe60, handle_hmi_exception) -EXC_REAL_OOL_MASKABLE_HV(h_doorbell, 0xe80, 0xea0) -EXC_VIRT_OOL_MASKABLE_HV(h_doorbell, 0x4e80, 0x4ea0, 0xe80) +EXC_REAL_OOL_MASKABLE_HV(h_doorbell, 0xe80, 0x20) +EXC_VIRT_OOL_MASKABLE_HV(h_doorbell, 0x4e80, 0x20, 0xe80) TRAMP_KVM_HV(PACA_EXGEN, 0xe80) #ifdef CONFIG_PPC_DOORBELL EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, doorbell_exception) @@ -1025,24 +1025,26 @@ EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, unknown_exception) #endif -EXC_REAL_OOL_MASKABLE_HV(h_virt_irq, 0xea0, 0xec0) -EXC_VIRT_OOL_MASKABLE_HV(h_virt_irq, 0x4ea0, 0x4ec0, 0xea0) +EXC_REAL_OOL_MASKABLE_HV(h_virt_irq, 0xea0, 0x20) +EXC_VIRT_OOL_MASKABLE_HV(h_virt_irq, 0x4ea0, 0x20, 0xea0) TRAMP_KVM_HV(PACA_EXGEN, 0xea0) EXC_COMMON_ASYNC(h_virt_irq_common, 0xea0, do_IRQ) -EXC_REAL_NONE(0xec0, 0xf00) -EXC_VIRT_NONE(0x4ec0, 0x4f00) +EXC_REAL_NONE(0xec0, 0x20) +EXC_VIRT_NONE(0x4ec0, 0x20) +EXC_REAL_NONE(0xee0, 0x20) +EXC_VIRT_NONE(0x4ee0, 0x20) -EXC_REAL_OOL(performance_monitor, 0xf00, 0xf20) -EXC_VIRT_OOL(performance_monitor, 0x4f00, 0x4f20, 0xf00) +EXC_REAL_OOL(performance_monitor, 0xf00, 0x20) +EXC_VIRT_OOL(performance_monitor, 0x4f00, 0x20, 0xf00) TRAMP_KVM(PACA_EXGEN, 0xf00) EXC_COMMON_ASYNC(performance_monitor_common, 0xf00, performance_monitor_exception) -EXC_REAL_OOL(altivec_unavailable, 0xf20, 0xf40) -EXC_VIRT_OOL(altivec_unavailable, 0x4f20, 0x4f40, 0xf20) +EXC_REAL_OOL(altivec_unavailable, 0xf20, 0x20) +EXC_VIRT_OOL(altivec_unavailable, 0x4f20, 0x20, 0xf20) TRAMP_KVM(PACA_EXGEN, 0xf20) EXC_COMMON_BEGIN(altivec_unavailable_common) EXCEPTION_PROLOG_COMMON(0xf20, PACA_EXGEN) @@ -1078,8 +1080,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) b ret_from_except -EXC_REAL_OOL(vsx_unavailable, 0xf40, 0xf60) -EXC_VIRT_OOL(vsx_unavailable, 0x4f40, 0x4f60, 0xf40) +EXC_REAL_OOL(vsx_unavailable, 0xf40, 0x20) +EXC_VIRT_OOL(vsx_unavailable, 0x4f40, 0x20, 0xf40) TRAMP_KVM(PACA_EXGEN, 0xf40) EXC_COMMON_BEGIN(vsx_unavailable_common) EXCEPTION_PROLOG_COMMON(0xf40, PACA_EXGEN) @@ -1114,41 +1116,50 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) b ret_from_except -EXC_REAL_OOL(facility_unavailable, 0xf60, 0xf80) -EXC_VIRT_OOL(facility_unavailable, 0x4f60, 0x4f80, 0xf60) +EXC_REAL_OOL(facility_unavailable, 0xf60, 0x20) +EXC_VIRT_OOL(facility_unavailable, 0x4f60, 0x20, 0xf60) TRAMP_KVM(PACA_EXGEN, 0xf60) EXC_COMMON(facility_unavailable_common, 0xf60, facility_unavailable_exception) -EXC_REAL_OOL_HV(h_facility_unavailable, 0xf80, 0xfa0) -EXC_VIRT_OOL_HV(h_facility_unavailable, 0x4f80, 0x4fa0, 0xf80) +EXC_REAL_OOL_HV(h_facility_unavailable, 0xf80, 0x20) +EXC_VIRT_OOL_HV(h_facility_unavailable, 0x4f80, 0x20, 0xf80) TRAMP_KVM_HV(PACA_EXGEN, 0xf80) EXC_COMMON(h_facility_unavailable_common, 0xf80, facility_unavailable_exception) -EXC_REAL_NONE(0xfa0, 0x1200) -EXC_VIRT_NONE(0x4fa0, 0x5200) +EXC_REAL_NONE(0xfa0, 0x20) +EXC_VIRT_NONE(0x4fa0, 0x20) +EXC_REAL_NONE(0xfc0, 0x20) +EXC_VIRT_NONE(0x4fc0, 0x20) +EXC_REAL_NONE(0xfe0, 0x20) +EXC_VIRT_NONE(0x4fe0, 0x20) + +EXC_REAL_NONE(0x1000, 0x100) +EXC_VIRT_NONE(0x5000, 0x100) +EXC_REAL_NONE(0x1100, 0x100) +EXC_VIRT_NONE(0x5100, 0x100) #ifdef CONFIG_CBE_RAS -EXC_REAL_HV(cbe_system_error, 0x1200, 0x1300) -EXC_VIRT_NONE(0x5200, 0x5300) +EXC_REAL_HV(cbe_system_error, 0x1200, 0x100) +EXC_VIRT_NONE(0x5200, 0x100) TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0x1200) EXC_COMMON(cbe_system_error_common, 0x1200, cbe_system_error_exception) #else /* CONFIG_CBE_RAS */ -EXC_REAL_NONE(0x1200, 0x1300) -EXC_VIRT_NONE(0x5200, 0x5300) +EXC_REAL_NONE(0x1200, 0x100) +EXC_VIRT_NONE(0x5200, 0x100) #endif -EXC_REAL(instruction_breakpoint, 0x1300, 0x1400) -EXC_VIRT(instruction_breakpoint, 0x5300, 0x5400, 0x1300) +EXC_REAL(instruction_breakpoint, 0x1300, 0x100) +EXC_VIRT(instruction_breakpoint, 0x5300, 0x100, 0x1300) TRAMP_KVM_SKIP(PACA_EXGEN, 0x1300) EXC_COMMON(instruction_breakpoint_common, 0x1300, instruction_breakpoint_exception) -EXC_REAL_NONE(0x1400, 0x1500) -EXC_VIRT_NONE(0x5400, 0x5500) +EXC_REAL_NONE(0x1400, 0x100) +EXC_VIRT_NONE(0x5400, 0x100) -EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x1600) +EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x100) mtspr SPRN_SPRG_HSCRATCH0,r13 EXCEPTION_PROLOG_0(PACA_EXGEN) EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x1500) @@ -1163,14 +1174,14 @@ EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x1600) KVMTEST_PR(0x1500) EXCEPTION_PROLOG_PSERIES_1(denorm_common, EXC_HV) -EXC_REAL_END(denorm_exception_hv, 0x1500, 0x1600) +EXC_REAL_END(denorm_exception_hv, 0x1500, 0x100) #ifdef CONFIG_PPC_DENORMALISATION -EXC_VIRT_BEGIN(denorm_exception, 0x5500, 0x5600) +EXC_VIRT_BEGIN(denorm_exception, 0x5500, 0x100) b exc_real_0x1500_denorm_exception_hv -EXC_VIRT_END(denorm_exception, 0x5500, 0x5600) +EXC_VIRT_END(denorm_exception, 0x5500, 0x100) #else -EXC_VIRT_NONE(0x5500, 0x5600) +EXC_VIRT_NONE(0x5500, 0x100) #endif TRAMP_KVM_SKIP(PACA_EXGEN, 0x1500) @@ -1243,18 +1254,18 @@ EXC_COMMON_HV(denorm_common, 0x1500, unknown_exception) #ifdef CONFIG_CBE_RAS -EXC_REAL_HV(cbe_maintenance, 0x1600, 0x1700) -EXC_VIRT_NONE(0x5600, 0x5700) +EXC_REAL_HV(cbe_maintenance, 0x1600, 0x100) +EXC_VIRT_NONE(0x5600, 0x100) TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0x1600) EXC_COMMON(cbe_maintenance_common, 0x1600, cbe_maintenance_exception) #else /* CONFIG_CBE_RAS */ -EXC_REAL_NONE(0x1600, 0x1700) -EXC_VIRT_NONE(0x5600, 0x5700) +EXC_REAL_NONE(0x1600, 0x100) +EXC_VIRT_NONE(0x5600, 0x100) #endif -EXC_REAL(altivec_assist, 0x1700, 0x1800) -EXC_VIRT(altivec_assist, 0x5700, 0x5800, 0x1700) +EXC_REAL(altivec_assist, 0x1700, 0x100) +EXC_VIRT(altivec_assist, 0x5700, 0x100, 0x1700) TRAMP_KVM(PACA_EXGEN, 0x1700) #ifdef CONFIG_ALTIVEC EXC_COMMON(altivec_assist_common, 0x1700, altivec_assist_exception) @@ -1264,13 +1275,13 @@ EXC_COMMON(altivec_assist_common, 0x1700, unknown_exception) #ifdef CONFIG_CBE_RAS -EXC_REAL_HV(cbe_thermal, 0x1800, 0x1900) -EXC_VIRT_NONE(0x5800, 0x5900) +EXC_REAL_HV(cbe_thermal, 0x1800, 0x100) +EXC_VIRT_NONE(0x5800, 0x100) TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0x1800) EXC_COMMON(cbe_thermal_common, 0x1800, cbe_thermal_exception) #else /* CONFIG_CBE_RAS */ -EXC_REAL_NONE(0x1800, 0x1900) -EXC_VIRT_NONE(0x5800, 0x5900) +EXC_REAL_NONE(0x1800, 0x100) +EXC_VIRT_NONE(0x5800, 0x100) #endif -- cgit v1.2.3 From a5ecdad4847897007399d7a14c9109b65ce4c9b7 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 7 Feb 2017 00:09:27 +0530 Subject: powerpc/mm: Add MMU_FTR_KERNEL_RO to possible feature mask Without this we will always find the feature disabled. Fixes: 984d7a1ec6 ("powerpc/mm: Fixup kernel read only mapping") Cc: stable@vger.kernel.org # v4.7+ Signed-off-by: Aneesh Kumar K.V Acked-by: Balbir Singh Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/mmu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index a34c764ca8dd..e5616bf83623 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -136,6 +136,7 @@ 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 | #ifdef CONFIG_PPC_RADIX_MMU MMU_FTR_TYPE_RADIX | #endif -- cgit v1.2.3 From 2337d207288f163e10bd8d4d7eeb0c1c75046a0c Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 27 Jan 2017 14:24:33 +1000 Subject: powerpc/64: CONFIG_RELOCATABLE support for hmi interrupts The branch from hmi_exception_early to hmi_exception_realmode must use a "relocatable-style" branch, because it is branching from unrelocated exception code to beyond __end_interrupts. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/exception-64s.h | 8 ++++++++ arch/powerpc/kernel/exceptions-64s.S | 2 +- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 8fa09fa500f0..14752eee3d0c 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -236,6 +236,11 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) mtctr reg; \ bctr +#define BRANCH_LINK_TO_FAR(reg, label) \ + __LOAD_FAR_HANDLER(reg, label); \ + mtctr reg; \ + bctrl + /* * KVM requires __LOAD_FAR_HANDLER. * @@ -260,6 +265,9 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) #define BRANCH_TO_COMMON(reg, label) \ b label +#define BRANCH_LINK_TO_FAR(reg, label) \ + bl label + #define BRANCH_TO_KVM(reg, label) \ b label diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 34a04a5fa468..76dd7738c122 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -982,7 +982,7 @@ TRAMP_REAL_BEGIN(hmi_exception_early) EXCEPTION_PROLOG_COMMON_2(PACA_EXGEN) EXCEPTION_PROLOG_COMMON_3(0xe60) addi r3,r1,STACK_FRAME_OVERHEAD - bl hmi_exception_realmode + BRANCH_LINK_TO_FAR(r4, hmi_exception_realmode) /* Windup the stack. */ /* Move original HSRR0 and HSRR1 into the respective regs */ ld r9,_MSR(r1) -- cgit v1.2.3 From ab9bad0ead9ab179ace09988a3f1cfca122eb7c2 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Tue, 7 Feb 2017 16:03:17 +1100 Subject: powerpc/powernv: Remove separate entry for OPAL real mode calls All entry points already read the MSR so they can easily do the right thing. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/opal.h | 7 --- arch/powerpc/kernel/idle_book3s.S | 6 +-- arch/powerpc/kvm/book3s_hv_builtin.c | 34 ++++--------- arch/powerpc/kvm/book3s_hv_rm_xics.c | 10 ++-- arch/powerpc/platforms/powernv/opal-wrappers.S | 70 +++++++++++--------------- arch/powerpc/platforms/powernv/pci-ioda.c | 5 -- 6 files changed, 46 insertions(+), 86 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 5c7db0f1a708..16efe7406776 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -67,7 +67,6 @@ int64_t opal_pci_config_write_half_word(uint64_t phb_id, uint64_t bus_dev_func, int64_t opal_pci_config_write_word(uint64_t phb_id, uint64_t bus_dev_func, uint64_t offset, uint32_t data); int64_t opal_set_xive(uint32_t isn, uint16_t server, uint8_t priority); -int64_t opal_rm_set_xive(uint32_t isn, uint16_t server, uint8_t priority); int64_t opal_get_xive(uint32_t isn, __be16 *server, uint8_t *priority); int64_t opal_register_exception_handler(uint64_t opal_exception, uint64_t handler_address, @@ -220,18 +219,12 @@ int64_t opal_pci_set_power_state(uint64_t async_token, uint64_t id, int64_t opal_pci_poll2(uint64_t id, uint64_t data); int64_t opal_int_get_xirr(uint32_t *out_xirr, bool just_poll); -int64_t opal_rm_int_get_xirr(__be32 *out_xirr, bool just_poll); int64_t opal_int_set_cppr(uint8_t cppr); int64_t opal_int_eoi(uint32_t xirr); -int64_t opal_rm_int_eoi(uint32_t xirr); int64_t opal_int_set_mfrr(uint32_t cpu, uint8_t mfrr); -int64_t opal_rm_int_set_mfrr(uint32_t cpu, uint8_t mfrr); 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_rm_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); /* Internal functions */ extern int early_init_dt_scan_opal(unsigned long node, const char *uname, diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 72dac0b58061..5302e1ad82c2 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -250,7 +250,7 @@ fastsleep_workaround_at_entry: /* Fast sleep workaround */ li r3,1 li r4,1 - bl opal_rm_config_cpu_idle_state + bl opal_config_cpu_idle_state /* Clear Lock bit */ li r0,0 @@ -544,7 +544,7 @@ timebase_resync: */ ble cr3,clear_lock /* Time base re-sync */ - bl opal_rm_resync_timebase; + bl opal_resync_timebase; /* * If waking up from sleep, per core state is not lost, skip to * clear_lock. @@ -633,7 +633,7 @@ hypervisor_state_restored: fastsleep_workaround_at_exit: li r3,1 li r4,0 - bl opal_rm_config_cpu_idle_state + bl opal_config_cpu_idle_state b timebase_resync /* diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index fe08fea54b70..2f69fbc19bb0 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -29,11 +29,6 @@ #include #include -static bool in_realmode(void) -{ - return !(mfmsr() & MSR_IR); -} - #define KVM_CMA_CHUNK_ORDER 18 /* @@ -230,13 +225,10 @@ void kvmhv_rm_send_ipi(int cpu) /* Else poke the target with an IPI */ xics_phys = paca[cpu].kvm_hstate.xics_phys; - if (!in_realmode()) - opal_int_set_mfrr(get_hard_smp_processor_id(cpu), IPI_PRIORITY); - else if (xics_phys) + if (xics_phys) rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY); else - opal_rm_int_set_mfrr(get_hard_smp_processor_id(cpu), - IPI_PRIORITY); + opal_int_set_mfrr(get_hard_smp_processor_id(cpu), IPI_PRIORITY); } /* @@ -419,10 +411,8 @@ static long kvmppc_read_one_intr(bool *again) /* Now read the interrupt from the ICP */ xics_phys = local_paca->kvm_hstate.xics_phys; rc = 0; - if (!in_realmode()) + if (!xics_phys) rc = opal_int_get_xirr(&xirr, false); - else if (!xics_phys) - rc = opal_rm_int_get_xirr(&xirr, false); else xirr = _lwzcix(xics_phys + XICS_XIRR); if (rc < 0) @@ -453,15 +443,12 @@ static long kvmppc_read_one_intr(bool *again) */ if (xisr == XICS_IPI) { rc = 0; - if (!in_realmode()) { - opal_int_set_mfrr(hard_smp_processor_id(), 0xff); - rc = opal_int_eoi(h_xirr); - } else if (xics_phys) { + if (xics_phys) { _stbcix(xics_phys + XICS_MFRR, 0xff); _stwcix(xics_phys + XICS_XIRR, xirr); } else { - opal_rm_int_set_mfrr(hard_smp_processor_id(), 0xff); - rc = opal_rm_int_eoi(h_xirr); + opal_int_set_mfrr(hard_smp_processor_id(), 0xff); + rc = opal_int_eoi(h_xirr); } /* If rc > 0, there is another interrupt pending */ *again = rc > 0; @@ -482,14 +469,11 @@ static long kvmppc_read_one_intr(bool *again) /* We raced with the host, * we need to resend that IPI, bummer */ - if (!in_realmode()) - opal_int_set_mfrr(hard_smp_processor_id(), - IPI_PRIORITY); - else if (xics_phys) + if (xics_phys) _stbcix(xics_phys + XICS_MFRR, IPI_PRIORITY); else - opal_rm_int_set_mfrr(hard_smp_processor_id(), - IPI_PRIORITY); + opal_int_set_mfrr(hard_smp_processor_id(), + IPI_PRIORITY); /* Let side effects complete */ smp_mb(); return 1; diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c index 7e2eb3e865b3..29f43ed6d5eb 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_xics.c +++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c @@ -36,7 +36,7 @@ EXPORT_SYMBOL(kvm_irq_bypass); static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, u32 new_irq); -static int xics_opal_rm_set_server(unsigned int hw_irq, int server_cpu); +static int xics_opal_set_server(unsigned int hw_irq, int server_cpu); /* -- ICS routines -- */ static void ics_rm_check_resend(struct kvmppc_xics *xics, @@ -728,7 +728,7 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) ++vcpu->stat.pthru_host; if (state->intr_cpu != pcpu) { ++vcpu->stat.pthru_bad_aff; - xics_opal_rm_set_server(state->host_irq, pcpu); + xics_opal_set_server(state->host_irq, pcpu); } state->intr_cpu = -1; } @@ -756,16 +756,16 @@ static void icp_eoi(struct irq_chip *c, u32 hwirq, __be32 xirr, bool *again) if (xics_phys) { _stwcix(xics_phys + XICS_XIRR, xirr); } else { - rc = opal_rm_int_eoi(be32_to_cpu(xirr)); + rc = opal_int_eoi(be32_to_cpu(xirr)); *again = rc > 0; } } -static int xics_opal_rm_set_server(unsigned int hw_irq, int server_cpu) +static int xics_opal_set_server(unsigned int hw_irq, int server_cpu) { unsigned int mangle_cpu = get_hard_smp_processor_id(server_cpu) << 2; - return opal_rm_set_xive(hw_irq, mangle_cpu, DEFAULT_PRIORITY); + return opal_set_xive(hw_irq, mangle_cpu, DEFAULT_PRIORITY); } /* diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 3aa40f1b20f5..28799e557348 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -58,14 +58,16 @@ END_FTR_SECTION(0, 1); \ #define OPAL_CALL(name, token) \ _GLOBAL_TOC(name); \ + mfmsr r12; \ mflr r0; \ + andi. r11,r12,MSR_IR|MSR_DR; \ std r0,PPC_LR_STKOFF(r1); \ li r0,token; \ + beq opal_real_call; \ OPAL_BRANCH(opal_tracepoint_entry) \ - mfcr r12; \ - stw r12,8(r1); \ + mfcr r11; \ + stw r11,8(r1); \ li r11,0; \ - mfmsr r12; \ ori r11,r11,MSR_EE; \ std r12,PACASAVEDMSR(r13); \ andc r12,r12,r11; \ @@ -98,6 +100,30 @@ opal_return: mtcr r4; rfid +opal_real_call: + mfcr r11 + stw r11,8(r1) + /* Set opal return address */ + LOAD_REG_ADDR(r11, opal_return_realmode) + mtlr r11 + li r11,MSR_LE + andc r12,r12,r11 + mtspr SPRN_HSRR1,r12 + LOAD_REG_ADDR(r11,opal) + ld r12,8(r11) + ld r2,0(r11) + mtspr SPRN_HSRR0,r12 + hrfid + +opal_return_realmode: + FIXUP_ENDIAN + ld r2,PACATOC(r13); + lwz r11,8(r1); + ld r12,PPC_LR_STKOFF(r1) + mtcr r11; + mtlr r12 + blr + #ifdef CONFIG_TRACEPOINTS opal_tracepoint_entry: stdu r1,-STACKFRAMESIZE(r1) @@ -155,36 +181,6 @@ opal_tracepoint_return: blr #endif -#define OPAL_CALL_REAL(name, token) \ - _GLOBAL_TOC(name); \ - mflr r0; \ - std r0,PPC_LR_STKOFF(r1); \ - li r0,token; \ - mfcr r12; \ - stw r12,8(r1); \ - \ - /* Set opal return address */ \ - LOAD_REG_ADDR(r11, opal_return_realmode); \ - mtlr r11; \ - mfmsr r12; \ - li r11,MSR_LE; \ - andc r12,r12,r11; \ - mtspr SPRN_HSRR1,r12; \ - LOAD_REG_ADDR(r11,opal); \ - ld r12,8(r11); \ - ld r2,0(r11); \ - mtspr SPRN_HSRR0,r12; \ - hrfid - -opal_return_realmode: - FIXUP_ENDIAN - ld r2,PACATOC(r13); - lwz r11,8(r1); - ld r12,PPC_LR_STKOFF(r1) - mtcr r11; - mtlr r12 - blr - OPAL_CALL(opal_invalid_call, OPAL_INVALID_CALL); OPAL_CALL(opal_console_write, OPAL_CONSOLE_WRITE); @@ -208,7 +204,6 @@ OPAL_CALL(opal_pci_config_write_byte, OPAL_PCI_CONFIG_WRITE_BYTE); OPAL_CALL(opal_pci_config_write_half_word, OPAL_PCI_CONFIG_WRITE_HALF_WORD); OPAL_CALL(opal_pci_config_write_word, OPAL_PCI_CONFIG_WRITE_WORD); OPAL_CALL(opal_set_xive, OPAL_SET_XIVE); -OPAL_CALL_REAL(opal_rm_set_xive, OPAL_SET_XIVE); OPAL_CALL(opal_get_xive, OPAL_GET_XIVE); OPAL_CALL(opal_register_exception_handler, OPAL_REGISTER_OPAL_EXCEPTION_HANDLER); OPAL_CALL(opal_pci_eeh_freeze_status, OPAL_PCI_EEH_FREEZE_STATUS); @@ -264,7 +259,6 @@ OPAL_CALL(opal_validate_flash, OPAL_FLASH_VALIDATE); OPAL_CALL(opal_manage_flash, OPAL_FLASH_MANAGE); OPAL_CALL(opal_update_flash, OPAL_FLASH_UPDATE); OPAL_CALL(opal_resync_timebase, OPAL_RESYNC_TIMEBASE); -OPAL_CALL_REAL(opal_rm_resync_timebase, OPAL_RESYNC_TIMEBASE); OPAL_CALL(opal_check_token, OPAL_CHECK_TOKEN); OPAL_CALL(opal_dump_init, OPAL_DUMP_INIT); OPAL_CALL(opal_dump_info, OPAL_DUMP_INFO); @@ -280,9 +274,7 @@ OPAL_CALL(opal_sensor_read, OPAL_SENSOR_READ); OPAL_CALL(opal_get_param, OPAL_GET_PARAM); OPAL_CALL(opal_set_param, OPAL_SET_PARAM); OPAL_CALL(opal_handle_hmi, OPAL_HANDLE_HMI); -OPAL_CALL_REAL(opal_rm_handle_hmi, OPAL_HANDLE_HMI); OPAL_CALL(opal_config_cpu_idle_state, OPAL_CONFIG_CPU_IDLE_STATE); -OPAL_CALL_REAL(opal_rm_config_cpu_idle_state, OPAL_CONFIG_CPU_IDLE_STATE); OPAL_CALL(opal_slw_set_reg, OPAL_SLW_SET_REG); OPAL_CALL(opal_register_dump_region, OPAL_REGISTER_DUMP_REGION); OPAL_CALL(opal_unregister_dump_region, OPAL_UNREGISTER_DUMP_REGION); @@ -304,11 +296,7 @@ OPAL_CALL(opal_pci_get_presence_state, OPAL_PCI_GET_PRESENCE_STATE); OPAL_CALL(opal_pci_get_power_state, OPAL_PCI_GET_POWER_STATE); OPAL_CALL(opal_pci_set_power_state, OPAL_PCI_SET_POWER_STATE); OPAL_CALL(opal_int_get_xirr, OPAL_INT_GET_XIRR); -OPAL_CALL_REAL(opal_rm_int_get_xirr, OPAL_INT_GET_XIRR); OPAL_CALL(opal_int_set_cppr, OPAL_INT_SET_CPPR); OPAL_CALL(opal_int_eoi, OPAL_INT_EOI); -OPAL_CALL_REAL(opal_rm_int_eoi, OPAL_INT_EOI); OPAL_CALL(opal_int_set_mfrr, OPAL_INT_SET_MFRR); -OPAL_CALL_REAL(opal_rm_int_set_mfrr, OPAL_INT_SET_MFRR); OPAL_CALL(opal_pci_tce_kill, OPAL_PCI_TCE_KILL); -OPAL_CALL_REAL(opal_rm_pci_tce_kill, OPAL_PCI_TCE_KILL); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index b07680cd2518..a897958edb88 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1962,11 +1962,6 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl, if (phb->model == PNV_PHB_MODEL_PHB3 && phb->regs) pnv_pci_phb3_tce_invalidate(pe, rm, shift, index, npages); - else if (rm) - opal_rm_pci_tce_kill(phb->opal_id, - OPAL_PCI_TCE_KILL_PAGES, - pe->pe_number, 1u << shift, - index << shift, npages); else opal_pci_tce_kill(phb->opal_id, OPAL_PCI_TCE_KILL_PAGES, -- cgit v1.2.3 From 64b40ffbc83029f035571cad9727e34e69dbf6d0 Mon Sep 17 00:00:00 2001 From: David Gibson Date: Fri, 9 Dec 2016 11:07:35 +1100 Subject: powerpc/pseries: Add hypercall wrappers for hash page table resizing This adds the hypercall numbers and wrapper functions for the hash page table resizing hypercalls. These hypercall numbers are defined in the PAPR ACR "HPT resizing option". It also adds a new firmware feature flag to track the presence of the HPT resizing calls. Signed-off-by: David Gibson Reviewed-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/firmware.h | 5 +++-- arch/powerpc/include/asm/hvcall.h | 2 ++ arch/powerpc/include/asm/plpar_wrappers.h | 12 ++++++++++++ arch/powerpc/platforms/pseries/firmware.c | 1 + 4 files changed, 18 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index 1e0b5a5d660a..8645897472b1 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -42,7 +42,7 @@ #define FW_FEATURE_SPLPAR ASM_CONST(0x0000000000100000) #define FW_FEATURE_LPAR ASM_CONST(0x0000000000400000) #define FW_FEATURE_PS3_LV1 ASM_CONST(0x0000000000800000) -/* Free ASM_CONST(0x0000000001000000) */ +#define FW_FEATURE_HPT_RESIZE ASM_CONST(0x0000000001000000) #define FW_FEATURE_CMO ASM_CONST(0x0000000002000000) #define FW_FEATURE_VPHN ASM_CONST(0x0000000004000000) #define FW_FEATURE_XCMO ASM_CONST(0x0000000008000000) @@ -66,7 +66,8 @@ enum { FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR | FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO | FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY | - FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN, + FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN | + FW_FEATURE_HPT_RESIZE, FW_FEATURE_PSERIES_ALWAYS = 0, FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL, FW_FEATURE_POWERNV_ALWAYS = 0, diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 77ff1ba99d1f..490c4b9f4e3a 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -276,6 +276,8 @@ #define H_GET_MPP_X 0x314 #define H_SET_MODE 0x31C #define H_CLEAR_HPT 0x358 +#define H_RESIZE_HPT_PREPARE 0x36C +#define H_RESIZE_HPT_COMMIT 0x370 #define H_SIGNAL_SYS_RESET 0x380 #define MAX_HCALL_OPCODE H_SIGNAL_SYS_RESET diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h index 0bcc75e295e3..c7b164836bc3 100644 --- a/arch/powerpc/include/asm/plpar_wrappers.h +++ b/arch/powerpc/include/asm/plpar_wrappers.h @@ -210,6 +210,18 @@ static inline long plpar_pte_protect(unsigned long flags, unsigned long ptex, return plpar_hcall_norets(H_PROTECT, flags, ptex, avpn); } +static inline long plpar_resize_hpt_prepare(unsigned long flags, + unsigned long shift) +{ + return plpar_hcall_norets(H_RESIZE_HPT_PREPARE, flags, shift); +} + +static inline long plpar_resize_hpt_commit(unsigned long flags, + unsigned long shift) +{ + return plpar_hcall_norets(H_RESIZE_HPT_COMMIT, flags, shift); +} + static inline long plpar_tce_get(unsigned long liobn, unsigned long ioba, unsigned long *tce_ret) { diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c index ea7f09bd73b1..658c02df2f36 100644 --- a/arch/powerpc/platforms/pseries/firmware.c +++ b/arch/powerpc/platforms/pseries/firmware.c @@ -64,6 +64,7 @@ hypertas_fw_features_table[] = { {FW_FEATURE_VPHN, "hcall-vphn"}, {FW_FEATURE_SET_MODE, "hcall-set-mode"}, {FW_FEATURE_BEST_ENERGY, "hcall-best-energy-1*"}, + {FW_FEATURE_HPT_RESIZE, "hcall-hpt-resize"}, }; /* Build up the firmware features bitmask using the contents of -- cgit v1.2.3 From dbcf929c0062b758fbb6312ccaf30716c0c0a608 Mon Sep 17 00:00:00 2001 From: David Gibson Date: Fri, 9 Dec 2016 11:07:36 +1100 Subject: powerpc/pseries: Add support for hash table resizing This adds support for using two hypercalls to change the size of the main hash page table while running as a PAPR guest. For now these hypercalls are only in experimental qemu versions. The interface is two part: first H_RESIZE_HPT_PREPARE is used to allocate and prepare the new hash table. This may be slow, but can be done asynchronously. Then, H_RESIZE_HPT_COMMIT is used to switch to the new hash table. This requires that no CPUs be concurrently updating the HPT, and so must be run under stop_machine(). This also adds a debugfs file which can be used to manually control HPT resizing or testing purposes. Signed-off-by: David Gibson Reviewed-by: Paul Mackerras [mpe: Rename the debugfs file to "hpt_order"] Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/mmu-hash.h | 1 + arch/powerpc/mm/hash_utils_64.c | 33 ++++++++ arch/powerpc/platforms/pseries/lpar.c | 109 ++++++++++++++++++++++++++ 3 files changed, 143 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 823015cff149..52d8d1e4b772 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -157,6 +157,7 @@ struct mmu_hash_ops { unsigned long addr, unsigned char *hpte_slot_array, int psize, int ssize, int local); + int (*resize_hpt)(unsigned long shift); /* * Special for kexec. * To be called in real mode with interrupts disabled. No locks are diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 67e19a0821be..a3371d4e35b6 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -35,7 +35,9 @@ #include #include #include +#include +#include #include #include #include @@ -1795,3 +1797,34 @@ void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base, /* Finally limit subsequent allocations */ memblock_set_current_limit(ppc64_rma_size); } + +#ifdef CONFIG_DEBUG_FS + +static int hpt_order_get(void *data, u64 *val) +{ + *val = ppc64_pft_size; + return 0; +} + +static int hpt_order_set(void *data, u64 val) +{ + if (!mmu_hash_ops.resize_hpt) + return -ENODEV; + + return mmu_hash_ops.resize_hpt(val); +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, "%llu\n"); + +static int __init hash64_debugfs(void) +{ + if (!debugfs_create_file("hpt_order", 0600, powerpc_debugfs_root, + NULL, &fops_hpt_order)) { + pr_err("lpar: unable to create hpt_order debugsfs file\n"); + } + + return 0; +} +machine_device_initcall(pseries, hash64_debugfs); + +#endif /* CONFIG_DEBUG_FS */ diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 5dc1c3c6e716..c2e13a51f369 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -27,6 +27,8 @@ #include #include #include +#include +#include #include #include #include @@ -609,6 +611,112 @@ static int __init disable_bulk_remove(char *str) __setup("bulk_remove=", disable_bulk_remove); +#define HPT_RESIZE_TIMEOUT 10000 /* ms */ + +struct hpt_resize_state { + unsigned long shift; + int commit_rc; +}; + +static int pseries_lpar_resize_hpt_commit(void *data) +{ + struct hpt_resize_state *state = data; + + state->commit_rc = plpar_resize_hpt_commit(0, state->shift); + if (state->commit_rc != H_SUCCESS) + return -EIO; + + /* Hypervisor has transitioned the HTAB, update our globals */ + ppc64_pft_size = state->shift; + htab_size_bytes = 1UL << ppc64_pft_size; + htab_hash_mask = (htab_size_bytes >> 7) - 1; + + return 0; +} + +/* Must be called in user context */ +static int pseries_lpar_resize_hpt(unsigned long shift) +{ + struct hpt_resize_state state = { + .shift = shift, + .commit_rc = H_FUNCTION, + }; + unsigned int delay, total_delay = 0; + int rc; + ktime_t t0, t1, t2; + + might_sleep(); + + if (!firmware_has_feature(FW_FEATURE_HPT_RESIZE)) + return -ENODEV; + + printk(KERN_INFO "lpar: Attempting to resize HPT to shift %lu\n", + shift); + + t0 = ktime_get(); + + rc = plpar_resize_hpt_prepare(0, shift); + while (H_IS_LONG_BUSY(rc)) { + delay = get_longbusy_msecs(rc); + total_delay += delay; + if (total_delay > HPT_RESIZE_TIMEOUT) { + /* prepare with shift==0 cancels an in-progress resize */ + rc = plpar_resize_hpt_prepare(0, 0); + if (rc != H_SUCCESS) + printk(KERN_WARNING + "lpar: Unexpected error %d cancelling timed out HPT resize\n", + rc); + return -ETIMEDOUT; + } + msleep(delay); + rc = plpar_resize_hpt_prepare(0, shift); + }; + + switch (rc) { + case H_SUCCESS: + /* Continue on */ + break; + + case H_PARAMETER: + return -EINVAL; + case H_RESOURCE: + return -EPERM; + default: + printk(KERN_WARNING + "lpar: Unexpected error %d from H_RESIZE_HPT_PREPARE\n", + rc); + return -EIO; + } + + t1 = ktime_get(); + + rc = stop_machine(pseries_lpar_resize_hpt_commit, &state, NULL); + + t2 = ktime_get(); + + if (rc != 0) { + switch (state.commit_rc) { + case H_PTEG_FULL: + printk(KERN_WARNING + "lpar: Hash collision while resizing HPT\n"); + return -ENOSPC; + + default: + printk(KERN_WARNING + "lpar: Unexpected error %d from H_RESIZE_HPT_COMMIT\n", + state.commit_rc); + return -EIO; + }; + } + + printk(KERN_INFO + "lpar: HPT resize to shift %lu complete (%lld ms / %lld ms)\n", + shift, (long long) ktime_ms_delta(t1, t0), + (long long) ktime_ms_delta(t2, t1)); + + return 0; +} + void __init hpte_init_pseries(void) { mmu_hash_ops.hpte_invalidate = pSeries_lpar_hpte_invalidate; @@ -620,6 +728,7 @@ void __init hpte_init_pseries(void) mmu_hash_ops.flush_hash_range = pSeries_lpar_flush_hash_range; mmu_hash_ops.hpte_clear_all = pseries_hpte_clear_all; mmu_hash_ops.hugepage_invalidate = pSeries_lpar_hugepage_invalidate; + mmu_hash_ops.resize_hpt = pseries_lpar_resize_hpt; } #ifdef CONFIG_PPC_SMLPAR -- cgit v1.2.3 From 0de0fb09bbce1e1635a0d4c4781af6ec8cbfdb81 Mon Sep 17 00:00:00 2001 From: David Gibson Date: Fri, 9 Dec 2016 11:07:37 +1100 Subject: powerpc/pseries: Advertise HPT resizing support via CAS The hypervisor needs to know a guest is capable of using the HPT resizing PAPR extension in order to make full advantage of it for memory hotplug. If the hypervisor knows the guest is HPT resize aware, it can size the initial HPT based on the initial guest RAM size, relying on the guest to resize the HPT when more memory is hot-added. Without this, the hypervisor must size the HPT for the maximum possible guest RAM, which can lead to a huge waste of space if the guest never actually expends to that maximum size. This patch advertises the guest's support for HPT resizing via the ibm,client-architecture-support OF interface. We use bit 5 of byte 6 of option vector 5 for this purpose, as defined in the PAPR ACR "HPT resizing option". Signed-off-by: David Gibson Reviewed-by: Anshuman Khandual Reviewed-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/prom.h | 1 + arch/powerpc/kernel/prom_init.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index 5e57705b4759..00fcfcbdd053 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -151,6 +151,7 @@ struct of_drconf_cell { #define OV5_XCMO 0x0440 /* Page Coalescing */ #define OV5_TYPE1_AFFINITY 0x0580 /* Type 1 NUMA affinity */ #define OV5_PRRN 0x0540 /* Platform Resource Reassignment */ +#define OV5_RESIZE_HPT 0x0601 /* Hash Page Table resizing */ #define OV5_PFO_HW_RNG 0x0E80 /* PFO Random Number Generator */ #define OV5_PFO_HW_842 0x0E40 /* PFO Compression Accelerator */ #define OV5_PFO_HW_ENCR 0x0E20 /* PFO Encryption Accelerator */ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index ec47a939cbdd..d16b0f005290 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -826,7 +826,7 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = { 0, #endif .associativity = OV5_FEAT(OV5_TYPE1_AFFINITY) | OV5_FEAT(OV5_PRRN), - .bin_opts = 0, + .bin_opts = OV5_FEAT(OV5_RESIZE_HPT), .micro_checkpoint = 0, .reserved0 = 0, .max_cpus = cpu_to_be32(NR_CPUS), /* number of cores supported */ -- cgit v1.2.3 From 438cc81a41e8c2905d0f4f300d4690445b2ab240 Mon Sep 17 00:00:00 2001 From: David Gibson Date: Fri, 9 Dec 2016 11:07:38 +1100 Subject: powerpc/pseries: Automatically resize HPT for memory hot add/remove We've now implemented code in the pseries platform to use the new PAPR interface to allow resizing the hash page table (HPT) at runtime. This patch uses that interface to automatically attempt to resize the HPT when memory is hot added or removed. This tries to always keep the HPT at a reasonable size for our current memory size. Signed-off-by: David Gibson Reviewed-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/sparsemem.h | 1 + arch/powerpc/mm/hash_utils_64.c | 29 +++++++++++++++++++++++++++++ arch/powerpc/mm/mem.c | 4 ++++ 3 files changed, 34 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h index f6fc0ee813d7..737335c891e4 100644 --- a/arch/powerpc/include/asm/sparsemem.h +++ b/arch/powerpc/include/asm/sparsemem.h @@ -16,6 +16,7 @@ #endif /* CONFIG_SPARSEMEM */ #ifdef CONFIG_MEMORY_HOTPLUG +extern void resize_hpt_for_hotplug(unsigned long new_mem_size); extern int create_section_mapping(unsigned long start, unsigned long end); extern int remove_section_mapping(unsigned long start, unsigned long end); #ifdef CONFIG_NUMA diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index a3371d4e35b6..12d679df50bd 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -749,6 +749,35 @@ static unsigned long __init htab_get_table_size(void) } #ifdef CONFIG_MEMORY_HOTPLUG +void resize_hpt_for_hotplug(unsigned long new_mem_size) +{ + unsigned target_hpt_shift; + + if (!mmu_hash_ops.resize_hpt) + return; + + target_hpt_shift = htab_shift_for_mem_size(new_mem_size); + + /* + * To avoid lots of HPT resizes if memory size is fluctuating + * across a boundary, we deliberately have some hysterisis + * here: we immediately increase the HPT size if the target + * shift exceeds the current shift, but we won't attempt to + * reduce unless the target shift is at least 2 below the + * current shift + */ + if ((target_hpt_shift > ppc64_pft_size) + || (target_hpt_shift < (ppc64_pft_size - 1))) { + int rc; + + rc = mmu_hash_ops.resize_hpt(target_hpt_shift); + if (rc) + printk(KERN_WARNING + "Unable to resize hash page table to target order %d: %d\n", + target_hpt_shift, rc); + } +} + int hash__create_section_mapping(unsigned long start, unsigned long end) { int rc = htab_bolt_mapping(start, end, __pa(start), diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 5f844337de21..9ee536ec0739 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -134,6 +134,8 @@ int arch_add_memory(int nid, u64 start, u64 size, bool for_device) unsigned long nr_pages = size >> PAGE_SHIFT; int rc; + resize_hpt_for_hotplug(memblock_phys_mem_size()); + pgdata = NODE_DATA(nid); start = (unsigned long)__va(start); @@ -174,6 +176,8 @@ int arch_remove_memory(u64 start, u64 size) */ vm_unmap_aliases(); + resize_hpt_for_hotplug(memblock_phys_mem_size()); + return ret; } #endif -- cgit v1.2.3 From c233f5979b3dbb39a5b2473b5fcaf58baec8f1bd Mon Sep 17 00:00:00 2001 From: "Naveen N. Rao" Date: Wed, 8 Feb 2017 14:27:29 +0530 Subject: powerpc/bpf: Introduce __PPC_SH64() Introduce __PPC_SH64() as a 64-bit variant to encode shift field in some of the shift and rotate instructions operating on double-words. Convert some of the BPF instruction macros to use the same. Signed-off-by: Naveen N. Rao Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/ppc-opcode.h | 1 + arch/powerpc/net/bpf_jit.h | 11 +++++------ 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index c4ced1d01d57..d99bd442aacb 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -306,6 +306,7 @@ #define __PPC_WC(w) (((w) & 0x3) << 21) #define __PPC_WS(w) (((w) & 0x1f) << 11) #define __PPC_SH(s) __PPC_WS(s) +#define __PPC_SH64(s) (__PPC_SH(s) | (((s) & 0x20) >> 4)) #define __PPC_MB(s) (((s) & 0x1f) << 6) #define __PPC_ME(s) (((s) & 0x1f) << 1) #define __PPC_MB64(s) (__PPC_MB(s) | ((s) & 0x20)) diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 89f70073dec8..30cf03f53428 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -157,8 +157,7 @@ #define PPC_SRAD(d, a, s) EMIT(PPC_INST_SRAD | ___PPC_RA(d) | \ ___PPC_RS(a) | ___PPC_RB(s)) #define PPC_SRADI(d, a, i) EMIT(PPC_INST_SRADI | ___PPC_RA(d) | \ - ___PPC_RS(a) | __PPC_SH(i) | \ - (((i) & 0x20) >> 4)) + ___PPC_RS(a) | __PPC_SH64(i)) #define PPC_RLWINM(d, a, i, mb, me) EMIT(PPC_INST_RLWINM | ___PPC_RA(d) | \ ___PPC_RS(a) | __PPC_SH(i) | \ __PPC_MB(mb) | __PPC_ME(me)) @@ -166,11 +165,11 @@ ___PPC_RS(a) | __PPC_SH(i) | \ __PPC_MB(mb) | __PPC_ME(me)) #define PPC_RLDICL(d, a, i, mb) EMIT(PPC_INST_RLDICL | ___PPC_RA(d) | \ - ___PPC_RS(a) | __PPC_SH(i) | \ - __PPC_MB64(mb) | (((i) & 0x20) >> 4)) + ___PPC_RS(a) | __PPC_SH64(i) | \ + __PPC_MB64(mb)) #define PPC_RLDICR(d, a, i, me) EMIT(PPC_INST_RLDICR | ___PPC_RA(d) | \ - ___PPC_RS(a) | __PPC_SH(i) | \ - __PPC_ME64(me) | (((i) & 0x20) >> 4)) + ___PPC_RS(a) | __PPC_SH64(i) | \ + __PPC_ME64(me)) /* slwi = rlwinm Rx, Ry, n, 0, 31-n */ #define PPC_SLWI(d, a, i) PPC_RLWINM(d, a, i, 0, 31-(i)) -- cgit v1.2.3 From ebfa50df435eed18e1389a43e0596246228e7298 Mon Sep 17 00:00:00 2001 From: Anju T Date: Wed, 8 Feb 2017 14:27:30 +0530 Subject: powerpc: Add helper to check if offset is within relative branch range To permit the use of relative branch instruction in powerpc, the target address has to be relatively nearby, since the address is specified in an immediate field (24 bit filed) in the instruction opcode itself. Here nearby refers to 32MB on either side of the current instruction. This patch verifies whether the target address is within +/- 32MB range or not. Signed-off-by: Naveen N. Rao Signed-off-by: Anju T Sudhakar Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/code-patching.h | 1 + arch/powerpc/lib/code-patching.c | 24 +++++++++++++++++++++++- 2 files changed, 24 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index 2015b072422c..75ee4f4ac840 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -22,6 +22,7 @@ #define BRANCH_SET_LINK 0x1 #define BRANCH_ABSOLUTE 0x2 +bool is_offset_in_branch_range(long offset); unsigned int create_branch(const unsigned int *addr, unsigned long target, int flags); unsigned int create_cond_branch(const unsigned int *addr, diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index c1746df0f88e..4ccf16a822cc 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -32,6 +32,28 @@ int patch_branch(unsigned int *addr, unsigned long target, int flags) return patch_instruction(addr, create_branch(addr, target, flags)); } +bool is_offset_in_branch_range(long offset) +{ + /* + * Powerpc branch instruction is : + * + * 0 6 30 31 + * +---------+----------------+---+---+ + * | opcode | LI |AA |LK | + * +---------+----------------+---+---+ + * Where AA = 0 and LK = 0 + * + * LI is a signed 24 bits integer. The real branch offset is computed + * by: imm32 = SignExtend(LI:'0b00', 32); + * + * So the maximum forward branch should be: + * (0x007fffff << 2) = 0x01fffffc = 0x1fffffc + * The maximum backward branch should be: + * (0xff800000 << 2) = 0xfe000000 = -0x2000000 + */ + return (offset >= -0x2000000 && offset <= 0x1fffffc && !(offset & 0x3)); +} + unsigned int create_branch(const unsigned int *addr, unsigned long target, int flags) { @@ -43,7 +65,7 @@ unsigned int create_branch(const unsigned int *addr, offset = offset - (unsigned long)addr; /* Check we can represent the target in the instruction format */ - if (offset < -0x2000000 || offset > 0x1fffffc || offset & 0x3) + if (!is_offset_in_branch_range(offset)) return 0; /* Mask out the flags and target, so they don't step on each other. */ -- cgit v1.2.3 From 30176466e36aadba01e1a630cf42397a3438efa4 Mon Sep 17 00:00:00 2001 From: "Naveen N. Rao" Date: Wed, 8 Feb 2017 14:27:31 +0530 Subject: powerpc/kprobes: Fixes for kprobe_lookup_name() on BE Fix two issues with kprobes.h on BE which were exposed with the optprobes work: - one, having to do with a missing include for linux/module.h for MODULE_NAME_LEN -- this didn't show up previously since the only users of kprobe_lookup_name were in kprobes.c, which included linux/module.h through other headers, and - two, with a missing const qualifier for a local variable which ends up referring a string literal. Again, this is unique to how kprobe_lookup_name is being invoked in optprobes.c Signed-off-by: Naveen N. Rao Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/kprobes.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h index 97b8c1f83453..77885d89f548 100644 --- a/arch/powerpc/include/asm/kprobes.h +++ b/arch/powerpc/include/asm/kprobes.h @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -61,7 +62,7 @@ typedef ppc_opcode_t kprobe_opcode_t; #define kprobe_lookup_name(name, addr) \ { \ char dot_name[MODULE_NAME_LEN + 1 + KSYM_NAME_LEN]; \ - char *modsym; \ + const char *modsym; \ bool dot_appended = false; \ if ((modsym = strchr(name, ':')) != NULL) { \ modsym++; \ -- cgit v1.2.3 From 51c9c0843993528bffc920c54c2121d9e6f8b090 Mon Sep 17 00:00:00 2001 From: Anju T Date: Wed, 8 Feb 2017 15:20:51 +0530 Subject: powerpc/kprobes: Implement Optprobes Current infrastructure of kprobe uses the unconditional trap instruction to probe a running kernel. Optprobe allows kprobe to replace the trap with a branch instruction to a detour buffer. Detour buffer contains instructions to create an in memory pt_regs. Detour buffer also has a call to optimized_callback() which in turn call the pre_handler(). After the execution of the pre-handler, a call is made for instruction emulation. The NIP is determined in advanced through dummy instruction emulation and a branch instruction is created to the NIP at the end of the trampoline. To address the limitation of branch instruction in POWER architecture, detour buffer slot is allocated from a reserved area. For the time being, 64KB is reserved in memory for this purpose. Instructions which can be emulated using analyse_instr() are the candidates for optimization. Before optimization ensure that the address range between the detour buffer allocated and the instruction being probed is within +/- 32MB. Signed-off-by: Anju T Sudhakar Signed-off-by: Naveen N. Rao Acked-by: Masami Hiramatsu Signed-off-by: Michael Ellerman --- arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/code-patching.h | 1 + arch/powerpc/include/asm/kprobes.h | 24 ++- arch/powerpc/kernel/Makefile | 1 + arch/powerpc/kernel/optprobes.c | 348 +++++++++++++++++++++++++++++++ arch/powerpc/kernel/optprobes_head.S | 135 ++++++++++++ arch/powerpc/lib/code-patching.c | 21 ++ 7 files changed, 530 insertions(+), 1 deletion(-) create mode 100644 arch/powerpc/kernel/optprobes.c create mode 100644 arch/powerpc/kernel/optprobes_head.S (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index bfdd80e7754c..f26c2253fdf2 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -100,6 +100,7 @@ config PPC select HAVE_IOREMAP_PROT select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU) select HAVE_KPROBES + select HAVE_OPTPROBES if PPC64 select HAVE_ARCH_KGDB select HAVE_KRETPROBES select HAVE_ARCH_TRACEHOOK diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index 75ee4f4ac840..8ab937771068 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -35,6 +35,7 @@ int instr_is_branch_to_addr(const unsigned int *instr, unsigned long addr); unsigned long branch_target(const unsigned int *instr); unsigned int translate_branch(const unsigned int *dest, const unsigned int *src); +extern bool is_conditional_branch(unsigned int instr); #ifdef CONFIG_PPC_BOOK3E_64 void __patch_exception(int exc, unsigned long addr); #define patch_exception(exc, name) do { \ diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h index 77885d89f548..d821835ade86 100644 --- a/arch/powerpc/include/asm/kprobes.h +++ b/arch/powerpc/include/asm/kprobes.h @@ -40,7 +40,23 @@ struct pt_regs; struct kprobe; typedef ppc_opcode_t kprobe_opcode_t; -#define MAX_INSN_SIZE 1 + +extern kprobe_opcode_t optinsn_slot; + +/* Optinsn template address */ +extern kprobe_opcode_t optprobe_template_entry[]; +extern kprobe_opcode_t optprobe_template_op_address[]; +extern kprobe_opcode_t optprobe_template_call_handler[]; +extern kprobe_opcode_t optprobe_template_insn[]; +extern kprobe_opcode_t optprobe_template_call_emulate[]; +extern kprobe_opcode_t optprobe_template_ret[]; +extern kprobe_opcode_t optprobe_template_end[]; + +/* Fixed instruction size for powerpc */ +#define MAX_INSN_SIZE 1 +#define MAX_OPTIMIZED_LENGTH sizeof(kprobe_opcode_t) /* 4 bytes */ +#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 */ @@ -126,6 +142,12 @@ struct kprobe_ctlblk { struct prev_kprobe prev_kprobe; }; +struct arch_optimized_insn { + kprobe_opcode_t copied_insn[1]; + /* detour buffer */ + kprobe_opcode_t *insn; +}; + extern int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data); extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr); diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index f4898e6ad18d..a048b37b9b27 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -100,6 +100,7 @@ obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_BOOTX_TEXT) += btext.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_KPROBES) += kprobes.o +obj-$(CONFIG_OPTPROBES) += optprobes.o optprobes_head.o obj-$(CONFIG_UPROBES) += uprobes.o obj-$(CONFIG_PPC_UDBG_16550) += legacy_serial.o udbg_16550.o obj-$(CONFIG_STACKTRACE) += stacktrace.o diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c new file mode 100644 index 000000000000..17f4c94142d3 --- /dev/null +++ b/arch/powerpc/kernel/optprobes.c @@ -0,0 +1,348 @@ +/* + * Code for Kernel probes Jump optimization. + * + * Copyright 2017, Anju T, IBM Corp. + * + * 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 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define TMPL_CALL_HDLR_IDX \ + (optprobe_template_call_handler - optprobe_template_entry) +#define TMPL_EMULATE_IDX \ + (optprobe_template_call_emulate - optprobe_template_entry) +#define TMPL_RET_IDX \ + (optprobe_template_ret - optprobe_template_entry) +#define TMPL_OP_IDX \ + (optprobe_template_op_address - optprobe_template_entry) +#define TMPL_INSN_IDX \ + (optprobe_template_insn - optprobe_template_entry) +#define TMPL_END_IDX \ + (optprobe_template_end - optprobe_template_entry) + +DEFINE_INSN_CACHE_OPS(ppc_optinsn); + +static bool insn_page_in_use; + +static void *__ppc_alloc_insn_page(void) +{ + if (insn_page_in_use) + return NULL; + insn_page_in_use = true; + return &optinsn_slot; +} + +static void __ppc_free_insn_page(void *page __maybe_unused) +{ + insn_page_in_use = false; +} + +struct kprobe_insn_cache kprobe_ppc_optinsn_slots = { + .mutex = __MUTEX_INITIALIZER(kprobe_ppc_optinsn_slots.mutex), + .pages = LIST_HEAD_INIT(kprobe_ppc_optinsn_slots.pages), + /* insn_size initialized later */ + .alloc = __ppc_alloc_insn_page, + .free = __ppc_free_insn_page, + .nr_garbage = 0, +}; + +/* + * Check if we can optimize this probe. Returns NIP post-emulation if this can + * be optimized and 0 otherwise. + */ +static unsigned long can_optimize(struct kprobe *p) +{ + struct pt_regs regs; + struct instruction_op op; + unsigned long nip = 0; + + /* + * kprobe placed for kretprobe during boot time + * is not optimizing now. + * + * TODO: Optimize kprobe in kretprobe_trampoline + */ + if (p->addr == (kprobe_opcode_t *)&kretprobe_trampoline) + return 0; + + /* + * We only support optimizing kernel addresses, but not + * module addresses. + * + * FIXME: Optimize kprobes placed in module addresses. + */ + if (!is_kernel_addr((unsigned long)p->addr)) + return 0; + + memset(®s, 0, sizeof(struct pt_regs)); + regs.nip = (unsigned long)p->addr; + regs.trap = 0x0; + regs.msr = MSR_KERNEL; + + /* + * Kprobe placed in conditional branch instructions are + * not optimized, as we can't predict the nip prior with + * dummy pt_regs and can not ensure that the return branch + * from detour buffer falls in the range of address (i.e 32MB). + * A branch back from trampoline is set up in the detour buffer + * to the nip returned by the analyse_instr() here. + * + * Ensure that the instruction is not a conditional branch, + * and that can be emulated. + */ + if (!is_conditional_branch(*p->ainsn.insn) && + analyse_instr(&op, ®s, *p->ainsn.insn)) + nip = regs.nip; + + return nip; +} + +static void optimized_callback(struct optimized_kprobe *op, + struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + unsigned long flags; + + /* This is possible if op is under delayed unoptimizing */ + if (kprobe_disabled(&op->kp)) + return; + + local_irq_save(flags); + hard_irq_disable(); + + if (kprobe_running()) { + kprobes_inc_nmissed_count(&op->kp); + } else { + __this_cpu_write(current_kprobe, &op->kp); + regs->nip = (unsigned long)op->kp.addr; + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + opt_pre_handler(&op->kp, regs); + __this_cpu_write(current_kprobe, NULL); + } + + /* + * No need for an explicit __hard_irq_enable() here. + * local_irq_restore() will re-enable interrupts, + * if they were hard disabled. + */ + local_irq_restore(flags); +} +NOKPROBE_SYMBOL(optimized_callback); + +void arch_remove_optimized_kprobe(struct optimized_kprobe *op) +{ + if (op->optinsn.insn) { + free_ppc_optinsn_slot(op->optinsn.insn, 1); + op->optinsn.insn = NULL; + } +} + +/* + * emulate_step() requires insn to be emulated as + * second parameter. Load register 'r4' with the + * instruction. + */ +void patch_imm32_load_insns(unsigned int val, kprobe_opcode_t *addr) +{ + /* addis r4,0,(insn)@h */ + *addr++ = PPC_INST_ADDIS | ___PPC_RT(4) | + ((val >> 16) & 0xffff); + + /* ori r4,r4,(insn)@l */ + *addr = PPC_INST_ORI | ___PPC_RA(4) | ___PPC_RS(4) | + (val & 0xffff); +} + +/* + * Generate instructions to load provided immediate 64-bit value + * to register 'r3' and patch these instructions at 'addr'. + */ +void patch_imm64_load_insns(unsigned long val, kprobe_opcode_t *addr) +{ + /* lis r3,(op)@highest */ + *addr++ = PPC_INST_ADDIS | ___PPC_RT(3) | + ((val >> 48) & 0xffff); + + /* ori r3,r3,(op)@higher */ + *addr++ = PPC_INST_ORI | ___PPC_RA(3) | ___PPC_RS(3) | + ((val >> 32) & 0xffff); + + /* rldicr r3,r3,32,31 */ + *addr++ = PPC_INST_RLDICR | ___PPC_RA(3) | ___PPC_RS(3) | + __PPC_SH64(32) | __PPC_ME64(31); + + /* oris r3,r3,(op)@h */ + *addr++ = PPC_INST_ORIS | ___PPC_RA(3) | ___PPC_RS(3) | + ((val >> 16) & 0xffff); + + /* ori r3,r3,(op)@l */ + *addr = PPC_INST_ORI | ___PPC_RA(3) | ___PPC_RS(3) | + (val & 0xffff); +} + +int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p) +{ + kprobe_opcode_t *buff, branch_op_callback, branch_emulate_step; + kprobe_opcode_t *op_callback_addr, *emulate_step_addr; + long b_offset; + unsigned long nip; + + kprobe_ppc_optinsn_slots.insn_size = MAX_OPTINSN_SIZE; + + nip = can_optimize(p); + if (!nip) + return -EILSEQ; + + /* Allocate instruction slot for detour buffer */ + buff = get_ppc_optinsn_slot(); + if (!buff) + return -ENOMEM; + + /* + * OPTPROBE uses 'b' instruction to branch to optinsn.insn. + * + * The target address has to be relatively nearby, to permit use + * of branch instruction in powerpc, because the address is specified + * in an immediate field in the instruction opcode itself, ie 24 bits + * in the opcode specify the address. Therefore the address should + * be within 32MB on either side of the current instruction. + */ + b_offset = (unsigned long)buff - (unsigned long)p->addr; + if (!is_offset_in_branch_range(b_offset)) + goto error; + + /* Check if the return address is also within 32MB range */ + b_offset = (unsigned long)(buff + TMPL_RET_IDX) - + (unsigned long)nip; + if (!is_offset_in_branch_range(b_offset)) + goto error; + + /* Setup template */ + memcpy(buff, optprobe_template_entry, + TMPL_END_IDX * sizeof(kprobe_opcode_t)); + + /* + * Fixup the template with instructions to: + * 1. load the address of the actual probepoint + */ + patch_imm64_load_insns((unsigned long)op, buff + TMPL_OP_IDX); + + /* + * 2. branch to optimized_callback() and emulate_step() + */ + kprobe_lookup_name("optimized_callback", op_callback_addr); + kprobe_lookup_name("emulate_step", emulate_step_addr); + if (!op_callback_addr || !emulate_step_addr) { + WARN(1, "kprobe_lookup_name() failed\n"); + goto error; + } + + branch_op_callback = create_branch((unsigned int *)buff + TMPL_CALL_HDLR_IDX, + (unsigned long)op_callback_addr, + BRANCH_SET_LINK); + + branch_emulate_step = create_branch((unsigned int *)buff + TMPL_EMULATE_IDX, + (unsigned long)emulate_step_addr, + BRANCH_SET_LINK); + + if (!branch_op_callback || !branch_emulate_step) + goto error; + + buff[TMPL_CALL_HDLR_IDX] = branch_op_callback; + buff[TMPL_EMULATE_IDX] = branch_emulate_step; + + /* + * 3. load instruction to be emulated into relevant register, and + */ + patch_imm32_load_insns(*p->ainsn.insn, buff + TMPL_INSN_IDX); + + /* + * 4. branch back from trampoline + */ + buff[TMPL_RET_IDX] = create_branch((unsigned int *)buff + TMPL_RET_IDX, + (unsigned long)nip, 0); + + flush_icache_range((unsigned long)buff, + (unsigned long)(&buff[TMPL_END_IDX])); + + op->optinsn.insn = buff; + + return 0; + +error: + free_ppc_optinsn_slot(buff, 0); + return -ERANGE; + +} + +int arch_prepared_optinsn(struct arch_optimized_insn *optinsn) +{ + return optinsn->insn != NULL; +} + +/* + * On powerpc, Optprobes always replaces one instruction (4 bytes + * aligned and 4 bytes long). It is impossible to encounter another + * kprobe in this address range. So always return 0. + */ +int arch_check_optimized_kprobe(struct optimized_kprobe *op) +{ + return 0; +} + +void arch_optimize_kprobes(struct list_head *oplist) +{ + struct optimized_kprobe *op; + struct optimized_kprobe *tmp; + + list_for_each_entry_safe(op, tmp, oplist, list) { + /* + * Backup instructions which will be replaced + * by jump address + */ + memcpy(op->optinsn.copied_insn, op->kp.addr, + RELATIVEJUMP_SIZE); + patch_instruction(op->kp.addr, + create_branch((unsigned int *)op->kp.addr, + (unsigned long)op->optinsn.insn, 0)); + list_del_init(&op->list); + } +} + +void arch_unoptimize_kprobe(struct optimized_kprobe *op) +{ + arch_arm_kprobe(&op->kp); +} + +void arch_unoptimize_kprobes(struct list_head *oplist, + struct list_head *done_list) +{ + struct optimized_kprobe *op; + struct optimized_kprobe *tmp; + + list_for_each_entry_safe(op, tmp, oplist, list) { + arch_unoptimize_kprobe(op); + list_move(&op->list, done_list); + } +} + +int arch_within_optimized_kprobe(struct optimized_kprobe *op, + unsigned long addr) +{ + return ((unsigned long)op->kp.addr <= addr && + (unsigned long)op->kp.addr + RELATIVEJUMP_SIZE > addr); +} diff --git a/arch/powerpc/kernel/optprobes_head.S b/arch/powerpc/kernel/optprobes_head.S new file mode 100644 index 000000000000..53e429b5a29d --- /dev/null +++ b/arch/powerpc/kernel/optprobes_head.S @@ -0,0 +1,135 @@ +/* + * Code to prepare detour buffer for optprobes in Kernel. + * + * Copyright 2017, Anju T, IBM Corp. + * + * 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 +#include +#include + +#define OPT_SLOT_SIZE 65536 + + .balign 4 + + /* + * Reserve an area to allocate slots for detour buffer. + * This is part of .text section (rather than vmalloc area) + * as this needs to be within 32MB of the probed address. + */ + .global optinsn_slot +optinsn_slot: + .space OPT_SLOT_SIZE + + /* + * Optprobe template: + * This template gets copied into one of the slots in optinsn_slot + * and gets fixed up with real optprobe structures et al. + */ + .global optprobe_template_entry +optprobe_template_entry: + /* Create an in-memory pt_regs */ + stdu r1,-INT_FRAME_SIZE(r1) + SAVE_GPR(0,r1) + /* Save the previous SP into stack */ + addi r0,r1,INT_FRAME_SIZE + std r0,GPR1(r1) + SAVE_10GPRS(2,r1) + SAVE_10GPRS(12,r1) + SAVE_10GPRS(22,r1) + /* Save SPRS */ + mfmsr r5 + std r5,_MSR(r1) + li r5,0x700 + std r5,_TRAP(r1) + li r5,0 + std r5,ORIG_GPR3(r1) + std r5,RESULT(r1) + mfctr r5 + std r5,_CTR(r1) + mflr r5 + std r5,_LINK(r1) + mfspr r5,SPRN_XER + std r5,_XER(r1) + mfcr r5 + std r5,_CCR(r1) + lbz r5,PACASOFTIRQEN(r13) + std r5,SOFTE(r1) + mfdar r5 + std r5,_DAR(r1) + mfdsisr r5 + std r5,_DSISR(r1) + + .global optprobe_template_op_address +optprobe_template_op_address: + /* + * Parameters to optimized_callback(): + * 1. optimized_kprobe structure in r3 + */ + nop + nop + nop + nop + nop + /* 2. pt_regs pointer in r4 */ + addi r4,r1,STACK_FRAME_OVERHEAD + + .global optprobe_template_call_handler +optprobe_template_call_handler: + /* Branch to optimized_callback() */ + nop + + /* + * Parameters for instruction emulation: + * 1. Pass SP in register r3. + */ + addi r3,r1,STACK_FRAME_OVERHEAD + + .global optprobe_template_insn +optprobe_template_insn: + /* 2, Pass instruction to be emulated in r4 */ + nop + nop + + .global optprobe_template_call_emulate +optprobe_template_call_emulate: + /* Branch to emulate_step() */ + nop + + /* + * All done. + * Now, restore the registers... + */ + ld r5,_MSR(r1) + mtmsr r5 + ld r5,_CTR(r1) + mtctr r5 + ld r5,_LINK(r1) + mtlr r5 + ld r5,_XER(r1) + mtxer r5 + ld r5,_CCR(r1) + mtcr r5 + ld r5,_DAR(r1) + mtdar r5 + ld r5,_DSISR(r1) + mtdsisr r5 + REST_GPR(0,r1) + REST_10GPRS(2,r1) + REST_10GPRS(12,r1) + REST_10GPRS(22,r1) + /* Restore the previous SP */ + addi r1,r1,INT_FRAME_SIZE + + .global optprobe_template_ret +optprobe_template_ret: + /* ... and jump back from trampoline */ + nop + + .global optprobe_template_end +optprobe_template_end: diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index 4ccf16a822cc..0899315e1434 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -54,6 +54,27 @@ bool is_offset_in_branch_range(long offset) return (offset >= -0x2000000 && offset <= 0x1fffffc && !(offset & 0x3)); } +/* + * Helper to check if a given instruction is a conditional branch + * Derived from the conditional checks in analyse_instr() + */ +bool __kprobes is_conditional_branch(unsigned int instr) +{ + unsigned int opcode = instr >> 26; + + if (opcode == 16) /* bc, bca, bcl, bcla */ + return true; + if (opcode == 19) { + switch ((instr >> 1) & 0x3ff) { + case 16: /* bclr, bclrl */ + case 528: /* bcctr, bcctrl */ + case 560: /* bctar, bctarl */ + return true; + } + } + return false; +} + unsigned int create_branch(const unsigned int *addr, unsigned long target, int flags) { -- cgit v1.2.3 From 99ad503287daf78e19e64e0e51f1d60a2a592217 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 9 Feb 2017 23:55:43 +1100 Subject: powerpc: Add a prototype for mcount() so it can be versioned Currently we get a warning that _mcount() can't be versioned: WARNING: EXPORT symbol "_mcount" [vmlinux] version generation failed, symbol will not be versioned. Add a prototype to asm-prototypes.h to fix it. The prototype is not really correct, mcount() is not a normal function, it has a special ABI. But for the purpose of versioning it doesn't matter. Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/asm-prototypes.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index ba47c70712f9..f6c5264287e5 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -120,4 +120,6 @@ extern s64 __ashrdi3(s64, int); extern int __cmpdi2(s64, s64); extern int __ucmpdi2(u64, u64); +void _mcount(void); + #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */ -- cgit v1.2.3 From aad71e3928bec48639a70facd21814ea28d27dcb Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 14 Feb 2017 13:11:38 +1100 Subject: powerpc/mm: Fix build break with RADIX=y & HUGETLBFS=n If we enable RADIX but disable HUGETLBFS, the build breaks with: arch/powerpc/mm/pgtable-radix.c:557:7: error: implicit declaration of function 'pmd_huge' arch/powerpc/mm/pgtable-radix.c:588:7: error: implicit declaration of function 'pud_huge' Fix it by stubbing those functions when HUGETLBFS=n. Fixes: 4b5d62ca17a1 ("powerpc/mm: add radix__remove_section_mapping()") Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/pgtable-4k.h | 5 +++++ arch/powerpc/include/asm/book3s/64/pgtable-64k.h | 3 +++ 2 files changed, 8 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h index 9db83b4e017d..8708a0239a56 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h @@ -47,7 +47,12 @@ static inline int hugepd_ok(hugepd_t hpd) return hash__hugepd_ok(hpd); } #define is_hugepd(hpd) (hugepd_ok(hpd)) + +#else /* !CONFIG_HUGETLB_PAGE */ +static inline int pmd_huge(pmd_t pmd) { return 0; } +static inline int pud_huge(pud_t pud) { return 0; } #endif /* CONFIG_HUGETLB_PAGE */ + #endif /* __ASSEMBLY__ */ #endif /*_ASM_POWERPC_BOOK3S_64_PGTABLE_4K_H */ diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h index 198aff33c380..2ce4209399ed 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h @@ -46,6 +46,9 @@ static inline int hugepd_ok(hugepd_t hpd) } #define is_hugepd(pdep) 0 +#else /* !CONFIG_HUGETLB_PAGE */ +static inline int pmd_huge(pmd_t pmd) { return 0; } +static inline int pud_huge(pud_t pud) { return 0; } #endif /* CONFIG_HUGETLB_PAGE */ static inline int remap_4k_pfn(struct vm_area_struct *vma, unsigned long addr, -- cgit v1.2.3 From 36b390fd624a7f3a64bda5de54fa58ebcf956ffc Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 15 Feb 2017 19:54:55 +1100 Subject: powerpc/mm: Fix build break with BOOK3S_64=n and MEMORY_HOTPLUG=y The recently merged HPT (Hash Page Table) resize support broke the build when BOOK3S_64=n (ie. 32-bit or 64-bit Book3E) and MEMORY_HOTPLUG=y: arch/powerpc/mm/mem.o: In function `.arch_add_memory': (.text+0x4e4): undefined reference to `.resize_hpt_for_hotplug' Fix it by adding a dummy version. Fixes: 438cc81a41e8 ("powerpc/pseries: Automatically resize HPT for memory hot add/remove") Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/sparsemem.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h index 737335c891e4..c88930c9db7f 100644 --- a/arch/powerpc/include/asm/sparsemem.h +++ b/arch/powerpc/include/asm/sparsemem.h @@ -16,9 +16,15 @@ #endif /* CONFIG_SPARSEMEM */ #ifdef CONFIG_MEMORY_HOTPLUG -extern void resize_hpt_for_hotplug(unsigned long new_mem_size); extern int create_section_mapping(unsigned long start, unsigned long end); extern int remove_section_mapping(unsigned long start, unsigned long end); + +#ifdef CONFIG_PPC_BOOK3S_64 +extern void resize_hpt_for_hotplug(unsigned long new_mem_size); +#else +static inline void resize_hpt_for_hotplug(unsigned long new_mem_size) { } +#endif + #ifdef CONFIG_NUMA extern int hot_add_scn_to_nid(unsigned long scn_addr); #else -- cgit v1.2.3 From ca94573b9c69d224e50e1084a2776772f4ea030d Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 9 Feb 2017 08:28:19 +0530 Subject: powerpc/mm/radix: Update pte update sequence for pte clear case In the kernel we do follow the below sequence in different code paths. pte = ptep_get_clear(ptep) .... set_pte_at(ptep, pte) We do that for mremap, autonuma protection update and softdirty clearing. This implies our optimization to skip a tlb flush when clearing a pte update is not valid, because for DD1 system that followup set_pte_at will be done witout doing the required tlbflush. Fix that by always doing the dd1 style pte update irrespective of new_pte value. In a later patch we will optimize the application exit case. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Aneesh Kumar K.V Tested-by: Michael Neuling Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/radix.h | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 0032b662284c..98c9ab37593c 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -144,16 +144,10 @@ static inline unsigned long radix__pte_update(struct mm_struct *mm, * new value of pte */ new_pte = (old_pte | set) & ~clr; - /* - * If we are trying to clear the pte, we can skip - * the below sequence and batch the tlb flush. The - * tlb flush batching is done by mmu gather code - */ - if (new_pte) { - asm volatile("ptesync" : : : "memory"); - radix__flush_tlb_pte_p9_dd1(old_pte, mm, addr); + asm volatile("ptesync" : : : "memory"); + radix__flush_tlb_pte_p9_dd1(old_pte, mm, addr); + if (new_pte) __radix_pte_update(ptep, 0, new_pte); - } } else old_pte = __radix_pte_update(ptep, clr, set); asm volatile("ptesync" : : : "memory"); -- cgit v1.2.3 From f4894b80b1ddfef00d4d2e5c58613ccef358a1b2 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 9 Feb 2017 08:28:20 +0530 Subject: powerpc/mm/radix: Use ptep_get_and_clear_full when clearing pte for full mm This helps us to do some optimization for application exit case, where we can skip the DD1 style pte update sequence. Signed-off-by: Aneesh Kumar K.V Tested-by: Michael Neuling Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/pgtable.h | 17 +++++++++++++++++ arch/powerpc/include/asm/book3s/64/radix.h | 23 ++++++++++++++++++++++- 2 files changed, 39 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 5905f0ff57d1..fef738229a68 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -371,6 +371,23 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, return __pte(old); } +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL +static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, int full) +{ + if (full && radix_enabled()) { + /* + * Let's skip the DD1 style pte update here. We know that + * this is a full mm pte clear and hence can be sure there is + * no parallel set_pte. + */ + return radix__ptep_get_and_clear_full(mm, addr, ptep, full); + } + return ptep_get_and_clear(mm, addr, ptep); +} + + static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t * ptep) { diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 98c9ab37593c..10a290094af4 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -139,7 +139,7 @@ static inline unsigned long radix__pte_update(struct mm_struct *mm, unsigned long new_pte; - old_pte = __radix_pte_update(ptep, ~0, 0); + old_pte = __radix_pte_update(ptep, ~0ul, 0); /* * new value of pte */ @@ -157,6 +157,27 @@ static inline unsigned long radix__pte_update(struct mm_struct *mm, return old_pte; } +static inline pte_t radix__ptep_get_and_clear_full(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, int full) +{ + unsigned long old_pte; + + if (full) { + /* + * If we are trying to clear the pte, we can skip + * the DD1 pte update sequence and batch the tlb flush. The + * tlb flush batching is done by mmu gather code. We + * still keep the cmp_xchg update to make sure we get + * correct R/C bit which might be updated via Nest MMU. + */ + old_pte = __radix_pte_update(ptep, ~0ul, 0); + } else + old_pte = radix__pte_update(mm, addr, ptep, ~0ul, 0, 0); + + return __pte(old_pte); +} + /* * Set the dirty and/or accessed bits atomically in a linux PTE, this * function doesn't need to invalidate tlb. -- cgit v1.2.3 From 438e69b52be776c035aa2a851ccc1709033d729b Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 9 Feb 2017 08:28:21 +0530 Subject: powerpc/mm/radix: Skip ptesync in pte update helpers We do them at the start of tlb flush, and we are sure a pte update will be followed by a tlbflush. Hence we can skip the ptesync in pte update helpers. Signed-off-by: Aneesh Kumar K.V Tested-by: Michael Neuling Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/radix.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 10a290094af4..9e0bb7cd6e22 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -144,13 +144,11 @@ static inline unsigned long radix__pte_update(struct mm_struct *mm, * new value of pte */ new_pte = (old_pte | set) & ~clr; - asm volatile("ptesync" : : : "memory"); radix__flush_tlb_pte_p9_dd1(old_pte, mm, addr); if (new_pte) __radix_pte_update(ptep, 0, new_pte); } else old_pte = __radix_pte_update(ptep, clr, set); - asm volatile("ptesync" : : : "memory"); if (!huge) assert_pte_locked(mm, addr); @@ -195,7 +193,6 @@ static inline void radix__ptep_set_access_flags(struct mm_struct *mm, unsigned long old_pte, new_pte; old_pte = __radix_pte_update(ptep, ~0, 0); - asm volatile("ptesync" : : : "memory"); /* * new value of pte */ -- cgit v1.2.3