From 5bece3d66153d78f1fd62108a1553c3f15e71412 Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Tue, 20 Aug 2019 12:49:41 +1000 Subject: powerpc: support KASAN instrumentation of bitops The powerpc-specific bitops are not being picked up by the KASAN test suite. Instrumentation is done via the bitops/instrumented-{atomic,lock}.h headers. They require that arch-specific versions of bitop functions are renamed to arch_*. Do this renaming. For clear_bit_unlock_is_negative_byte, the current implementation uses the PG_waiters constant. This works because it's a preprocessor macro - so it's only actually evaluated in contexts where PG_waiters is defined. With instrumentation however, it becomes a static inline function, and all of a sudden we need the actual value of PG_waiters. Because of the order of header includes, it's not available and we fail to compile. Instead, manually specify that we care about bit 7. This is still correct: bit 7 is the bit that would mark a negative byte. While we're at it, replace __inline__ with inline across the file. Reviewed-by: Christophe Leroy Signed-off-by: Daniel Axtens Tested-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190820024941.12640-2-dja@axtens.net --- arch/powerpc/include/asm/bitops.h | 51 ++++++++++++++++++++++----------------- 1 file changed, 29 insertions(+), 22 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index 603aed229af7..28dcf8222943 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -64,7 +64,7 @@ /* Macro for generating the ***_bits() functions */ #define DEFINE_BITOP(fn, op, prefix) \ -static __inline__ void fn(unsigned long mask, \ +static inline void fn(unsigned long mask, \ volatile unsigned long *_p) \ { \ unsigned long old; \ @@ -86,22 +86,22 @@ DEFINE_BITOP(clear_bits, andc, "") DEFINE_BITOP(clear_bits_unlock, andc, PPC_RELEASE_BARRIER) DEFINE_BITOP(change_bits, xor, "") -static __inline__ void set_bit(int nr, volatile unsigned long *addr) +static inline void arch_set_bit(int nr, volatile unsigned long *addr) { set_bits(BIT_MASK(nr), addr + BIT_WORD(nr)); } -static __inline__ void clear_bit(int nr, volatile unsigned long *addr) +static inline void arch_clear_bit(int nr, volatile unsigned long *addr) { clear_bits(BIT_MASK(nr), addr + BIT_WORD(nr)); } -static __inline__ void clear_bit_unlock(int nr, volatile unsigned long *addr) +static inline void arch_clear_bit_unlock(int nr, volatile unsigned long *addr) { clear_bits_unlock(BIT_MASK(nr), addr + BIT_WORD(nr)); } -static __inline__ void change_bit(int nr, volatile unsigned long *addr) +static inline void arch_change_bit(int nr, volatile unsigned long *addr) { change_bits(BIT_MASK(nr), addr + BIT_WORD(nr)); } @@ -109,7 +109,7 @@ static __inline__ void change_bit(int nr, volatile unsigned long *addr) /* Like DEFINE_BITOP(), with changes to the arguments to 'op' and the output * operands. */ #define DEFINE_TESTOP(fn, op, prefix, postfix, eh) \ -static __inline__ unsigned long fn( \ +static inline unsigned long fn( \ unsigned long mask, \ volatile unsigned long *_p) \ { \ @@ -138,34 +138,34 @@ DEFINE_TESTOP(test_and_clear_bits, andc, PPC_ATOMIC_ENTRY_BARRIER, DEFINE_TESTOP(test_and_change_bits, xor, PPC_ATOMIC_ENTRY_BARRIER, PPC_ATOMIC_EXIT_BARRIER, 0) -static __inline__ int test_and_set_bit(unsigned long nr, - volatile unsigned long *addr) +static inline int arch_test_and_set_bit(unsigned long nr, + volatile unsigned long *addr) { return test_and_set_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0; } -static __inline__ int test_and_set_bit_lock(unsigned long nr, - volatile unsigned long *addr) +static inline int arch_test_and_set_bit_lock(unsigned long nr, + volatile unsigned long *addr) { return test_and_set_bits_lock(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0; } -static __inline__ int test_and_clear_bit(unsigned long nr, - volatile unsigned long *addr) +static inline int arch_test_and_clear_bit(unsigned long nr, + volatile unsigned long *addr) { return test_and_clear_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0; } -static __inline__ int test_and_change_bit(unsigned long nr, - volatile unsigned long *addr) +static inline int arch_test_and_change_bit(unsigned long nr, + volatile unsigned long *addr) { return test_and_change_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0; } #ifdef CONFIG_PPC64 -static __inline__ unsigned long clear_bit_unlock_return_word(int nr, - volatile unsigned long *addr) +static inline unsigned long +clear_bit_unlock_return_word(int nr, volatile unsigned long *addr) { unsigned long old, t; unsigned long *p = (unsigned long *)addr + BIT_WORD(nr); @@ -185,15 +185,18 @@ static __inline__ unsigned long clear_bit_unlock_return_word(int nr, return old; } -/* This is a special function for mm/filemap.c */ -#define clear_bit_unlock_is_negative_byte(nr, addr) \ - (clear_bit_unlock_return_word(nr, addr) & BIT_MASK(PG_waiters)) +/* + * This is a special function for mm/filemap.c + * Bit 7 corresponds to PG_waiters. + */ +#define arch_clear_bit_unlock_is_negative_byte(nr, addr) \ + (clear_bit_unlock_return_word(nr, addr) & BIT_MASK(7)) #endif /* CONFIG_PPC64 */ #include -static __inline__ void __clear_bit_unlock(int nr, volatile unsigned long *addr) +static inline void arch___clear_bit_unlock(int nr, volatile unsigned long *addr) { __asm__ __volatile__(PPC_RELEASE_BARRIER "" ::: "memory"); __clear_bit(nr, addr); @@ -215,14 +218,14 @@ static __inline__ void __clear_bit_unlock(int nr, volatile unsigned long *addr) * fls: find last (most-significant) bit set. * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. */ -static __inline__ int fls(unsigned int x) +static inline int fls(unsigned int x) { return 32 - __builtin_clz(x); } #include -static __inline__ int fls64(__u64 x) +static inline int fls64(__u64 x) { return 64 - __builtin_clzll(x); } @@ -239,6 +242,10 @@ unsigned long __arch_hweight64(__u64 w); #include +/* wrappers that deal with KASAN instrumentation */ +#include +#include + /* Little-endian versions */ #include -- cgit From ca9f4942670c37407bb109090eaf776ce2ccc54c Mon Sep 17 00:00:00 2001 From: Bharata B Rao Date: Mon, 25 Nov 2019 08:36:26 +0530 Subject: KVM: PPC: Book3S HV: Support for running secure guests A pseries guest can be run as secure guest on Ultravisor-enabled POWER platforms. On such platforms, this driver will be used to manage the movement of guest pages between the normal memory managed by hypervisor (HV) and secure memory managed by Ultravisor (UV). HV is informed about the guest's transition to secure mode via hcalls: H_SVM_INIT_START: Initiate securing a VM H_SVM_INIT_DONE: Conclude securing a VM As part of H_SVM_INIT_START, register all existing memslots with the UV. H_SVM_INIT_DONE call by UV informs HV that transition of the guest to secure mode is complete. These two states (transition to secure mode STARTED and transition to secure mode COMPLETED) are recorded in kvm->arch.secure_guest. Setting these states will cause the assembly code that enters the guest to call the UV_RETURN ucall instead of trying to enter the guest directly. Migration of pages betwen normal and secure memory of secure guest is implemented in H_SVM_PAGE_IN and H_SVM_PAGE_OUT hcalls. H_SVM_PAGE_IN: Move the content of a normal page to secure page H_SVM_PAGE_OUT: Move the content of a secure page to normal page Private ZONE_DEVICE memory equal to the amount of secure memory available in the platform for running secure guests is created. Whenever a page belonging to the guest becomes secure, a page from this private device memory is used to represent and track that secure page on the HV side. The movement of pages between normal and secure memory is done via migrate_vma_pages() using UV_PAGE_IN and UV_PAGE_OUT ucalls. In order to prevent the device private pages (that correspond to pages of secure guest) from participating in KSM merging, H_SVM_PAGE_IN calls ksm_madvise() under read version of mmap_sem. However ksm_madvise() needs to be under write lock. Hence we call kvmppc_svm_page_in with mmap_sem held for writing, and it then downgrades to a read lock after calling ksm_madvise. [paulus@ozlabs.org - roll in patch "KVM: PPC: Book3S HV: Take write mmap_sem when calling ksm_madvise"] Signed-off-by: Bharata B Rao Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/hvcall.h | 6 +++ arch/powerpc/include/asm/kvm_book3s_uvmem.h | 62 +++++++++++++++++++++++++++++ arch/powerpc/include/asm/kvm_host.h | 6 +++ arch/powerpc/include/asm/ultravisor-api.h | 3 ++ arch/powerpc/include/asm/ultravisor.h | 21 ++++++++++ 5 files changed, 98 insertions(+) create mode 100644 arch/powerpc/include/asm/kvm_book3s_uvmem.h (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 11112023e327..4150732c81a0 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -342,6 +342,12 @@ #define H_TLB_INVALIDATE 0xF808 #define H_COPY_TOFROM_GUEST 0xF80C +/* Platform-specific hcalls used by the Ultravisor */ +#define H_SVM_PAGE_IN 0xEF00 +#define H_SVM_PAGE_OUT 0xEF04 +#define H_SVM_INIT_START 0xEF08 +#define H_SVM_INIT_DONE 0xEF0C + /* Values for 2nd argument to H_SET_MODE */ #define H_SET_MODE_RESOURCE_SET_CIABR 1 #define H_SET_MODE_RESOURCE_SET_DAWR 2 diff --git a/arch/powerpc/include/asm/kvm_book3s_uvmem.h b/arch/powerpc/include/asm/kvm_book3s_uvmem.h new file mode 100644 index 000000000000..95f389c2937b --- /dev/null +++ b/arch/powerpc/include/asm/kvm_book3s_uvmem.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_KVM_BOOK3S_UVMEM_H__ +#define __ASM_KVM_BOOK3S_UVMEM_H__ + +#ifdef CONFIG_PPC_UV +int kvmppc_uvmem_init(void); +void kvmppc_uvmem_free(void); +int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot); +void kvmppc_uvmem_slot_free(struct kvm *kvm, + const struct kvm_memory_slot *slot); +unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, + unsigned long gra, + unsigned long flags, + unsigned long page_shift); +unsigned long kvmppc_h_svm_page_out(struct kvm *kvm, + unsigned long gra, + unsigned long flags, + unsigned long page_shift); +unsigned long kvmppc_h_svm_init_start(struct kvm *kvm); +unsigned long kvmppc_h_svm_init_done(struct kvm *kvm); +#else +static inline int kvmppc_uvmem_init(void) +{ + return 0; +} + +static inline void kvmppc_uvmem_free(void) { } + +static inline int +kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot) +{ + return 0; +} + +static inline void +kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot) { } + +static inline unsigned long +kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gra, + unsigned long flags, unsigned long page_shift) +{ + return H_UNSUPPORTED; +} + +static inline unsigned long +kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long gra, + unsigned long flags, unsigned long page_shift) +{ + return H_UNSUPPORTED; +} + +static inline unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) +{ + return H_UNSUPPORTED; +} + +static inline unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) +{ + return H_UNSUPPORTED; +} +#endif /* CONFIG_PPC_UV */ +#endif /* __ASM_KVM_BOOK3S_UVMEM_H__ */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 4273e799203d..0a398f2321c2 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -275,6 +275,10 @@ struct kvm_hpt_info { struct kvm_resize_hpt; +/* Flag values for kvm_arch.secure_guest */ +#define KVMPPC_SECURE_INIT_START 0x1 /* H_SVM_INIT_START has been called */ +#define KVMPPC_SECURE_INIT_DONE 0x2 /* H_SVM_INIT_DONE completed */ + struct kvm_arch { unsigned int lpid; unsigned int smt_mode; /* # vcpus per virtual core */ @@ -330,6 +334,8 @@ struct kvm_arch { #endif struct kvmppc_ops *kvm_ops; #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + struct mutex uvmem_lock; + struct list_head uvmem_pfns; struct mutex mmu_setup_lock; /* nests inside vcpu mutexes */ u64 l1_ptcr; int max_nested_lpid; diff --git a/arch/powerpc/include/asm/ultravisor-api.h b/arch/powerpc/include/asm/ultravisor-api.h index 4fcda1d5793d..2483f15bd71a 100644 --- a/arch/powerpc/include/asm/ultravisor-api.h +++ b/arch/powerpc/include/asm/ultravisor-api.h @@ -26,6 +26,9 @@ #define UV_WRITE_PATE 0xF104 #define UV_RETURN 0xF11C #define UV_ESM 0xF110 +#define UV_REGISTER_MEM_SLOT 0xF120 +#define UV_PAGE_IN 0xF128 +#define UV_PAGE_OUT 0xF12C #define UV_SHARE_PAGE 0xF130 #define UV_UNSHARE_PAGE 0xF134 #define UV_UNSHARE_ALL_PAGES 0xF140 diff --git a/arch/powerpc/include/asm/ultravisor.h b/arch/powerpc/include/asm/ultravisor.h index b1bc2e043ed4..79bb005e8ee9 100644 --- a/arch/powerpc/include/asm/ultravisor.h +++ b/arch/powerpc/include/asm/ultravisor.h @@ -46,4 +46,25 @@ static inline int uv_unshare_all_pages(void) return ucall_norets(UV_UNSHARE_ALL_PAGES); } +static inline int uv_page_in(u64 lpid, u64 src_ra, u64 dst_gpa, u64 flags, + u64 page_shift) +{ + return ucall_norets(UV_PAGE_IN, lpid, src_ra, dst_gpa, flags, + page_shift); +} + +static inline int uv_page_out(u64 lpid, u64 dst_ra, u64 src_gpa, u64 flags, + u64 page_shift) +{ + return ucall_norets(UV_PAGE_OUT, lpid, dst_ra, src_gpa, flags, + page_shift); +} + +static inline int uv_register_mem_slot(u64 lpid, u64 start_gpa, u64 size, + u64 flags, u64 slotid) +{ + return ucall_norets(UV_REGISTER_MEM_SLOT, lpid, start_gpa, + size, flags, slotid); +} + #endif /* _ASM_POWERPC_ULTRAVISOR_H */ -- cgit From 60f0a643aa44e4bed3a74ea671110707dd64d892 Mon Sep 17 00:00:00 2001 From: Bharata B Rao Date: Mon, 25 Nov 2019 08:36:27 +0530 Subject: KVM: PPC: Book3S HV: Shared pages support for secure guests A secure guest will share some of its pages with hypervisor (Eg. virtio bounce buffers etc). Support sharing of pages between hypervisor and ultravisor. Shared page is reachable via both HV and UV side page tables. Once a secure page is converted to shared page, the device page that represents the secure page is unmapped from the HV side page tables. Signed-off-by: Bharata B Rao Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/hvcall.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 4150732c81a0..13bd870609c3 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -342,6 +342,9 @@ #define H_TLB_INVALIDATE 0xF808 #define H_COPY_TOFROM_GUEST 0xF80C +/* Flags for H_SVM_PAGE_IN */ +#define H_PAGE_IN_SHARED 0x1 + /* Platform-specific hcalls used by the Ultravisor */ #define H_SVM_PAGE_IN 0xEF00 #define H_SVM_PAGE_OUT 0xEF04 -- cgit From 008e359c76d85facb10d10fa21fd5bc8c3a4e5d6 Mon Sep 17 00:00:00 2001 From: Bharata B Rao Date: Mon, 25 Nov 2019 08:36:28 +0530 Subject: KVM: PPC: Book3S HV: Radix changes for secure guest - After the guest becomes secure, when we handle a page fault of a page belonging to SVM in HV, send that page to UV via UV_PAGE_IN. - Whenever a page is unmapped on the HV side, inform UV via UV_PAGE_INVAL. - Ensure all those routines that walk the secondary page tables of the guest don't do so in case of secure VM. For secure guest, the active secondary page tables are in secure memory and the secondary page tables in HV are freed when guest becomes secure. Signed-off-by: Bharata B Rao Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/kvm_book3s_uvmem.h | 6 ++++++ arch/powerpc/include/asm/ultravisor-api.h | 1 + arch/powerpc/include/asm/ultravisor.h | 5 +++++ 3 files changed, 12 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_book3s_uvmem.h b/arch/powerpc/include/asm/kvm_book3s_uvmem.h index 95f389c2937b..3033a9585b43 100644 --- a/arch/powerpc/include/asm/kvm_book3s_uvmem.h +++ b/arch/powerpc/include/asm/kvm_book3s_uvmem.h @@ -18,6 +18,7 @@ unsigned long kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long page_shift); unsigned long kvmppc_h_svm_init_start(struct kvm *kvm); unsigned long kvmppc_h_svm_init_done(struct kvm *kvm); +int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn); #else static inline int kvmppc_uvmem_init(void) { @@ -58,5 +59,10 @@ static inline unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) { return H_UNSUPPORTED; } + +static inline int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn) +{ + return -EFAULT; +} #endif /* CONFIG_PPC_UV */ #endif /* __ASM_KVM_BOOK3S_UVMEM_H__ */ diff --git a/arch/powerpc/include/asm/ultravisor-api.h b/arch/powerpc/include/asm/ultravisor-api.h index 2483f15bd71a..e774274ab30e 100644 --- a/arch/powerpc/include/asm/ultravisor-api.h +++ b/arch/powerpc/include/asm/ultravisor-api.h @@ -32,5 +32,6 @@ #define UV_SHARE_PAGE 0xF130 #define UV_UNSHARE_PAGE 0xF134 #define UV_UNSHARE_ALL_PAGES 0xF140 +#define UV_PAGE_INVAL 0xF138 #endif /* _ASM_POWERPC_ULTRAVISOR_API_H */ diff --git a/arch/powerpc/include/asm/ultravisor.h b/arch/powerpc/include/asm/ultravisor.h index 79bb005e8ee9..40cc8bace654 100644 --- a/arch/powerpc/include/asm/ultravisor.h +++ b/arch/powerpc/include/asm/ultravisor.h @@ -67,4 +67,9 @@ static inline int uv_register_mem_slot(u64 lpid, u64 start_gpa, u64 size, size, flags, slotid); } +static inline int uv_page_inval(u64 lpid, u64 gpa, u64 page_shift) +{ + return ucall_norets(UV_PAGE_INVAL, lpid, gpa, page_shift); +} + #endif /* _ASM_POWERPC_ULTRAVISOR_H */ -- cgit From c32622575dd0ecb6fd0b41e3a451bd58152971ba Mon Sep 17 00:00:00 2001 From: Bharata B Rao Date: Mon, 25 Nov 2019 08:36:29 +0530 Subject: KVM: PPC: Book3S HV: Handle memory plug/unplug to secure VM Register the new memslot with UV during plug and unregister the memslot during unplug. In addition, release all the device pages during unplug. Signed-off-by: Bharata B Rao Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/kvm_book3s_uvmem.h | 6 ++++++ arch/powerpc/include/asm/ultravisor-api.h | 1 + arch/powerpc/include/asm/ultravisor.h | 5 +++++ 3 files changed, 12 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_book3s_uvmem.h b/arch/powerpc/include/asm/kvm_book3s_uvmem.h index 3033a9585b43..50204e228f16 100644 --- a/arch/powerpc/include/asm/kvm_book3s_uvmem.h +++ b/arch/powerpc/include/asm/kvm_book3s_uvmem.h @@ -19,6 +19,8 @@ unsigned long kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long kvmppc_h_svm_init_start(struct kvm *kvm); unsigned long kvmppc_h_svm_init_done(struct kvm *kvm); int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn); +void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free, + struct kvm *kvm); #else static inline int kvmppc_uvmem_init(void) { @@ -64,5 +66,9 @@ static inline int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn) { return -EFAULT; } + +static inline void +kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free, + struct kvm *kvm) { } #endif /* CONFIG_PPC_UV */ #endif /* __ASM_KVM_BOOK3S_UVMEM_H__ */ diff --git a/arch/powerpc/include/asm/ultravisor-api.h b/arch/powerpc/include/asm/ultravisor-api.h index e774274ab30e..4b0d044caa2a 100644 --- a/arch/powerpc/include/asm/ultravisor-api.h +++ b/arch/powerpc/include/asm/ultravisor-api.h @@ -27,6 +27,7 @@ #define UV_RETURN 0xF11C #define UV_ESM 0xF110 #define UV_REGISTER_MEM_SLOT 0xF120 +#define UV_UNREGISTER_MEM_SLOT 0xF124 #define UV_PAGE_IN 0xF128 #define UV_PAGE_OUT 0xF12C #define UV_SHARE_PAGE 0xF130 diff --git a/arch/powerpc/include/asm/ultravisor.h b/arch/powerpc/include/asm/ultravisor.h index 40cc8bace654..b8e59b7b4ac8 100644 --- a/arch/powerpc/include/asm/ultravisor.h +++ b/arch/powerpc/include/asm/ultravisor.h @@ -67,6 +67,11 @@ static inline int uv_register_mem_slot(u64 lpid, u64 start_gpa, u64 size, size, flags, slotid); } +static inline int uv_unregister_mem_slot(u64 lpid, u64 slotid) +{ + return ucall_norets(UV_UNREGISTER_MEM_SLOT, lpid, slotid); +} + static inline int uv_page_inval(u64 lpid, u64 gpa, u64 page_shift) { return ucall_norets(UV_PAGE_INVAL, lpid, gpa, page_shift); -- cgit From 22945688acd4d0ec2620b0670a53110401ed9c59 Mon Sep 17 00:00:00 2001 From: Bharata B Rao Date: Mon, 25 Nov 2019 08:36:30 +0530 Subject: KVM: PPC: Book3S HV: Support reset of secure guest Add support for reset of secure guest via a new ioctl KVM_PPC_SVM_OFF. This ioctl will be issued by QEMU during reset and includes the the following steps: - Release all device pages of the secure guest. - Ask UV to terminate the guest via UV_SVM_TERMINATE ucall - Unpin the VPA pages so that they can be migrated back to secure side when guest becomes secure again. This is required because pinned pages can't be migrated. - Reinit the partition scoped page tables After these steps, guest is ready to issue UV_ESM call once again to switch to secure mode. Signed-off-by: Bharata B Rao Signed-off-by: Sukadev Bhattiprolu [Implementation of uv_svm_terminate() and its call from guest shutdown path] Signed-off-by: Ram Pai [Unpinning of VPA pages] Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/kvm_ppc.h | 1 + arch/powerpc/include/asm/ultravisor-api.h | 1 + arch/powerpc/include/asm/ultravisor.h | 5 +++++ 3 files changed, 7 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index d63f649fe713..3d2f871241a8 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -322,6 +322,7 @@ struct kvmppc_ops { int size); int (*store_to_eaddr)(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr, int size); + int (*svm_off)(struct kvm *kvm); }; extern struct kvmppc_ops *kvmppc_hv_ops; diff --git a/arch/powerpc/include/asm/ultravisor-api.h b/arch/powerpc/include/asm/ultravisor-api.h index 4b0d044caa2a..b66f6db7be6c 100644 --- a/arch/powerpc/include/asm/ultravisor-api.h +++ b/arch/powerpc/include/asm/ultravisor-api.h @@ -34,5 +34,6 @@ #define UV_UNSHARE_PAGE 0xF134 #define UV_UNSHARE_ALL_PAGES 0xF140 #define UV_PAGE_INVAL 0xF138 +#define UV_SVM_TERMINATE 0xF13C #endif /* _ASM_POWERPC_ULTRAVISOR_API_H */ diff --git a/arch/powerpc/include/asm/ultravisor.h b/arch/powerpc/include/asm/ultravisor.h index b8e59b7b4ac8..790b0e63681f 100644 --- a/arch/powerpc/include/asm/ultravisor.h +++ b/arch/powerpc/include/asm/ultravisor.h @@ -77,4 +77,9 @@ static inline int uv_page_inval(u64 lpid, u64 gpa, u64 page_shift) return ucall_norets(UV_PAGE_INVAL, lpid, gpa, page_shift); } +static inline int uv_svm_terminate(u64 lpid) +{ + return ucall_norets(UV_SVM_TERMINATE, lpid); +} + #endif /* _ASM_POWERPC_ULTRAVISOR_H */ -- cgit From 552263456215ada7ee8700ce022d12b0cffe4802 Mon Sep 17 00:00:00 2001 From: Vincenzo Frascino Date: Mon, 2 Dec 2019 07:57:29 +0000 Subject: powerpc: Fix vDSO clock_getres() clock_getres in the vDSO library has to preserve the same behaviour of posix_get_hrtimer_res(). In particular, posix_get_hrtimer_res() does: sec = 0; ns = hrtimer_resolution; and hrtimer_resolution depends on the enablement of the high resolution timers that can happen either at compile or at run time. Fix the powerpc vdso implementation of clock_getres keeping a copy of hrtimer_resolution in vdso data and using that directly. Fixes: a7f290dad32e ("[PATCH] powerpc: Merge vdso's and add vdso support to 32 bits kernel") Cc: stable@vger.kernel.org Signed-off-by: Vincenzo Frascino Reviewed-by: Christophe Leroy Acked-by: Shuah Khan [chleroy: changed CLOCK_REALTIME_RES to CLOCK_HRTIMER_RES] Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/a55eca3a5e85233838c2349783bcb5164dae1d09.1575273217.git.christophe.leroy@c-s.fr --- arch/powerpc/include/asm/vdso_datapage.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h index a115970a6809..40f13f3626d3 100644 --- a/arch/powerpc/include/asm/vdso_datapage.h +++ b/arch/powerpc/include/asm/vdso_datapage.h @@ -83,6 +83,7 @@ struct vdso_data { __s64 wtom_clock_sec; /* Wall to monotonic clock sec */ __s64 stamp_xtime_sec; /* xtime secs as at tb_orig_stamp */ __s64 stamp_xtime_nsec; /* xtime nsecs as at tb_orig_stamp */ + __u32 hrtimer_res; /* hrtimer resolution */ __u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */ __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ }; @@ -105,6 +106,7 @@ struct vdso_data { __s32 stamp_xtime_sec; /* xtime seconds as at tb_orig_stamp */ __s32 stamp_xtime_nsec; /* xtime nsecs as at tb_orig_stamp */ __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */ + __u32 hrtimer_res; /* hrtimer resolution */ __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ __u32 dcache_block_size; /* L1 d-cache block size */ __u32 icache_block_size; /* L1 i-cache block size */ -- cgit From b6afd1234cf93aa0d71b4be4788c47534905f0be Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 4 Dec 2019 11:50:15 +0000 Subject: powerpc/archrandom: fix arch_get_random_seed_int() Commit 01c9348c7620ec65 powerpc: Use hardware RNG for arch_get_random_seed_* not arch_get_random_* updated arch_get_random_[int|long]() to be NOPs, and moved the hardware RNG backing to arch_get_random_seed_[int|long]() instead. However, it failed to take into account that arch_get_random_int() was implemented in terms of arch_get_random_long(), and so we ended up with a version of the former that is essentially a NOP as well. Fix this by calling arch_get_random_seed_long() from arch_get_random_seed_int() instead. Fixes: 01c9348c7620ec65 ("powerpc: Use hardware RNG for arch_get_random_seed_* not arch_get_random_*") Signed-off-by: Ard Biesheuvel Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20191204115015.18015-1-ardb@kernel.org --- arch/powerpc/include/asm/archrandom.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/archrandom.h b/arch/powerpc/include/asm/archrandom.h index 9c63b596e6ce..a09595f00cab 100644 --- a/arch/powerpc/include/asm/archrandom.h +++ b/arch/powerpc/include/asm/archrandom.h @@ -28,7 +28,7 @@ static inline int arch_get_random_seed_int(unsigned int *v) unsigned long val; int rc; - rc = arch_get_random_long(&val); + rc = arch_get_random_seed_long(&val); if (rc) *v = val; -- cgit From 9ef0e004181956e158fb7ceb9b43810a193f80cd Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 4 Dec 2019 16:53:00 -0800 Subject: arch: msgbuf.h: make uapi asm/msgbuf.h self-contained Userspace cannot compile due to some missing type definitions. For example, building it for x86 fails as follows: CC usr/include/asm/msgbuf.h.s In file included from usr/include/asm/msgbuf.h:6:0, from :32: usr/include/asm-generic/msgbuf.h:25:20: error: field `msg_perm' has incomplete type struct ipc64_perm msg_perm; ^~~~~~~~ usr/include/asm-generic/msgbuf.h:27:2: error: unknown type name `__kernel_time_t' __kernel_time_t msg_stime; /* last msgsnd time */ ^~~~~~~~~~~~~~~ usr/include/asm-generic/msgbuf.h:28:2: error: unknown type name `__kernel_time_t' __kernel_time_t msg_rtime; /* last msgrcv time */ ^~~~~~~~~~~~~~~ usr/include/asm-generic/msgbuf.h:29:2: error: unknown type name `__kernel_time_t' __kernel_time_t msg_ctime; /* last change time */ ^~~~~~~~~~~~~~~ usr/include/asm-generic/msgbuf.h:41:2: error: unknown type name `__kernel_pid_t' __kernel_pid_t msg_lspid; /* pid of last msgsnd */ ^~~~~~~~~~~~~~ usr/include/asm-generic/msgbuf.h:42:2: error: unknown type name `__kernel_pid_t' __kernel_pid_t msg_lrpid; /* last receive pid */ ^~~~~~~~~~~~~~ It is just a matter of missing include directive. Include to make it self-contained, and add it to the compile-test coverage. Link: http://lkml.kernel.org/r/20191030063855.9989-2-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/include/uapi/asm/msgbuf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/uapi/asm/msgbuf.h b/arch/powerpc/include/uapi/asm/msgbuf.h index 969bd83e4d3d..7919b2ba41b5 100644 --- a/arch/powerpc/include/uapi/asm/msgbuf.h +++ b/arch/powerpc/include/uapi/asm/msgbuf.h @@ -2,6 +2,8 @@ #ifndef _ASM_POWERPC_MSGBUF_H #define _ASM_POWERPC_MSGBUF_H +#include + /* * The msqid64_ds structure for the PowerPC architecture. * Note extra padding because this structure is passed back and forth -- cgit From 0fb9dc28679a627f84974165c8011e0630529ece Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 4 Dec 2019 16:53:03 -0800 Subject: arch: sembuf.h: make uapi asm/sembuf.h self-contained Userspace cannot compile due to some missing type definitions. For example, building it for x86 fails as follows: CC usr/include/asm/sembuf.h.s In file included from :32:0: usr/include/asm/sembuf.h:17:20: error: field `sem_perm' has incomplete type struct ipc64_perm sem_perm; /* permissions .. see ipc.h */ ^~~~~~~~ usr/include/asm/sembuf.h:24:2: error: unknown type name `__kernel_time_t' __kernel_time_t sem_otime; /* last semop time */ ^~~~~~~~~~~~~~~ usr/include/asm/sembuf.h:25:2: error: unknown type name `__kernel_ulong_t' __kernel_ulong_t __unused1; ^~~~~~~~~~~~~~~~ usr/include/asm/sembuf.h:26:2: error: unknown type name `__kernel_time_t' __kernel_time_t sem_ctime; /* last change time */ ^~~~~~~~~~~~~~~ usr/include/asm/sembuf.h:27:2: error: unknown type name `__kernel_ulong_t' __kernel_ulong_t __unused2; ^~~~~~~~~~~~~~~~ usr/include/asm/sembuf.h:29:2: error: unknown type name `__kernel_ulong_t' __kernel_ulong_t sem_nsems; /* no. of semaphores in array */ ^~~~~~~~~~~~~~~~ usr/include/asm/sembuf.h:30:2: error: unknown type name `__kernel_ulong_t' __kernel_ulong_t __unused3; ^~~~~~~~~~~~~~~~ usr/include/asm/sembuf.h:31:2: error: unknown type name `__kernel_ulong_t' __kernel_ulong_t __unused4; ^~~~~~~~~~~~~~~~ It is just a matter of missing include directive. Include to make it self-contained, and add it to the compile-test coverage. Link: http://lkml.kernel.org/r/20191030063855.9989-3-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/include/uapi/asm/sembuf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/uapi/asm/sembuf.h b/arch/powerpc/include/uapi/asm/sembuf.h index 008ae77c6746..85e96ccb5f0f 100644 --- a/arch/powerpc/include/uapi/asm/sembuf.h +++ b/arch/powerpc/include/uapi/asm/sembuf.h @@ -2,6 +2,8 @@ #ifndef _ASM_POWERPC_SEMBUF_H #define _ASM_POWERPC_SEMBUF_H +#include + /* * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License -- cgit From 14c73bd344da60abaf7da3ea2e7733ddda35bbac Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Thu, 5 Dec 2019 14:02:17 +0530 Subject: powerpc/vcpu: Assume dedicated processors as non-preempt With commit 247f2f6f3c70 ("sched/core: Don't schedule threads on pre-empted vCPUs"), the scheduler avoids preempted vCPUs to schedule tasks on wakeup. This leads to wrong choice of CPU, which in-turn leads to larger wakeup latencies. Eventually, it leads to performance regression in latency sensitive benchmarks like soltp, schbench etc. On Powerpc, vcpu_is_preempted() only looks at yield_count. If the yield_count is odd, the vCPU is assumed to be preempted. However yield_count is increased whenever the LPAR enters CEDE state (idle). So any CPU that has entered CEDE state is assumed to be preempted. Even if vCPU of dedicated LPAR is preempted/donated, it should have right of first-use since they are supposed to own the vCPU. On a Power9 System with 32 cores: # lscpu Architecture: ppc64le Byte Order: Little Endian CPU(s): 128 On-line CPU(s) list: 0-127 Thread(s) per core: 8 Core(s) per socket: 1 Socket(s): 16 NUMA node(s): 2 Model: 2.2 (pvr 004e 0202) Model name: POWER9 (architected), altivec supported Hypervisor vendor: pHyp Virtualization type: para L1d cache: 32K L1i cache: 32K L2 cache: 512K L3 cache: 10240K NUMA node0 CPU(s): 0-63 NUMA node1 CPU(s): 64-127 # perf stat -a -r 5 ./schbench v5.4 v5.4 + patch Latency percentiles (usec) Latency percentiles (usec) 50.0000th: 45 50.0th: 45 75.0000th: 62 75.0th: 63 90.0000th: 71 90.0th: 74 95.0000th: 77 95.0th: 78 *99.0000th: 91 *99.0th: 82 99.5000th: 707 99.5th: 83 99.9000th: 6920 99.9th: 86 min=0, max=10048 min=0, max=96 Latency percentiles (usec) Latency percentiles (usec) 50.0000th: 45 50.0th: 46 75.0000th: 61 75.0th: 64 90.0000th: 72 90.0th: 75 95.0000th: 79 95.0th: 79 *99.0000th: 691 *99.0th: 83 99.5000th: 3972 99.5th: 85 99.9000th: 8368 99.9th: 91 min=0, max=16606 min=0, max=117 Latency percentiles (usec) Latency percentiles (usec) 50.0000th: 45 50.0th: 46 75.0000th: 61 75.0th: 64 90.0000th: 71 90.0th: 75 95.0000th: 77 95.0th: 79 *99.0000th: 106 *99.0th: 83 99.5000th: 2364 99.5th: 84 99.9000th: 7480 99.9th: 90 min=0, max=10001 min=0, max=95 Latency percentiles (usec) Latency percentiles (usec) 50.0000th: 45 50.0th: 47 75.0000th: 62 75.0th: 65 90.0000th: 72 90.0th: 75 95.0000th: 78 95.0th: 79 *99.0000th: 93 *99.0th: 84 99.5000th: 108 99.5th: 85 99.9000th: 6792 99.9th: 90 min=0, max=17681 min=0, max=117 Latency percentiles (usec) Latency percentiles (usec) 50.0000th: 46 50.0th: 45 75.0000th: 62 75.0th: 64 90.0000th: 73 90.0th: 75 95.0000th: 79 95.0th: 79 *99.0000th: 113 *99.0th: 82 99.5000th: 2724 99.5th: 83 99.9000th: 6184 99.9th: 93 min=0, max=9887 min=0, max=111 Performance counter stats for 'system wide' (5 runs): context-switches 43,373 ( +- 0.40% ) 44,597 ( +- 0.55% ) cpu-migrations 1,211 ( +- 5.04% ) 220 ( +- 6.23% ) page-faults 15,983 ( +- 5.21% ) 15,360 ( +- 3.38% ) Waiman Long suggested using static_keys. Fixes: 247f2f6f3c70 ("sched/core: Don't schedule threads on pre-empted vCPUs") Cc: stable@vger.kernel.org # v4.18+ Reported-by: Parth Shah Reported-by: Ihor Pasichnyk Tested-by: Juri Lelli Acked-by: Waiman Long Reviewed-by: Gautham R. Shenoy Signed-off-by: Srikar Dronamraju Acked-by: Phil Auld Reviewed-by: Vaidyanathan Srinivasan Tested-by: Parth Shah [mpe: Move the key and setting of the key to pseries/setup.c] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20191213035036.6913-1-mpe@ellerman.id.au --- arch/powerpc/include/asm/spinlock.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index e9a960e28f3c..cac95a3f30c2 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -36,10 +36,12 @@ #endif #ifdef CONFIG_PPC_PSERIES +DECLARE_STATIC_KEY_FALSE(shared_processor); + #define vcpu_is_preempted vcpu_is_preempted static inline bool vcpu_is_preempted(int cpu) { - if (!firmware_has_feature(FW_FEATURE_SPLPAR)) + if (!static_branch_unlikely(&shared_processor)) return false; return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1); } -- cgit From 656c21d6af5d9279dd7b51ca7a4a71008127044b Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Thu, 5 Dec 2019 14:02:18 +0530 Subject: powerpc/shared: Use static key to detect shared processor With the static key shared processor available, is_shared_processor() can return without having to query the lppaca structure. Signed-off-by: Srikar Dronamraju Acked-by: Phil Auld Acked-by: Waiman Long Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20191213035036.6913-2-mpe@ellerman.id.au --- arch/powerpc/include/asm/spinlock.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index cac95a3f30c2..1b55fc08f853 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -112,13 +112,8 @@ static inline void splpar_rw_yield(arch_rwlock_t *lock) {}; static inline bool is_shared_processor(void) { -/* - * LPPACA is only available on Pseries so guard anything LPPACA related to - * allow other platforms (which include this common header) to compile. - */ -#ifdef CONFIG_PPC_PSERIES - return (IS_ENABLED(CONFIG_PPC_SPLPAR) && - lppaca_shared_proc(local_paca->lppaca_ptr)); +#ifdef CONFIG_PPC_SPLPAR + return static_branch_unlikely(&shared_processor); #else return false; #endif -- cgit From 61e3acd8c693a14fc69b824cb5b08d02cb90a6e7 Mon Sep 17 00:00:00 2001 From: Andrew Donnellan Date: Tue, 10 Dec 2019 00:22:21 +1100 Subject: powerpc: Fix __clear_user() with KUAP enabled The KUAP implementation adds calls in clear_user() to enable and disable access to userspace memory. However, it doesn't add these to __clear_user(), which is used in the ptrace regset code. As there's only one direct user of __clear_user() (the regset code), and the time taken to set the AMR for KUAP purposes is going to dominate the cost of a quick access_ok(), there's not much point having a separate path. Rename __clear_user() to __arch_clear_user(), and make __clear_user() just call clear_user(). Reported-by: syzbot+f25ecf4b2982d8c7a640@syzkaller-ppc64.appspotmail.com Reported-by: Daniel Axtens Suggested-by: Michael Ellerman Fixes: de78a9c42a79 ("powerpc: Add a framework for Kernel Userspace Access Protection") Signed-off-by: Andrew Donnellan [mpe: Use __arch_clear_user() for the asm version like arm64 & nds32] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20191209132221.15328-1-ajd@linux.ibm.com --- arch/powerpc/include/asm/uaccess.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 15002b51ff18..c92fe7fe9692 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -401,7 +401,7 @@ copy_to_user_mcsafe(void __user *to, const void *from, unsigned long n) return n; } -extern unsigned long __clear_user(void __user *addr, unsigned long size); +unsigned long __arch_clear_user(void __user *addr, unsigned long size); static inline unsigned long clear_user(void __user *addr, unsigned long size) { @@ -409,12 +409,17 @@ static inline unsigned long clear_user(void __user *addr, unsigned long size) might_fault(); if (likely(access_ok(addr, size))) { allow_write_to_user(addr, size); - ret = __clear_user(addr, size); + ret = __arch_clear_user(addr, size); prevent_write_to_user(addr, size); } return ret; } +static inline unsigned long __clear_user(void __user *addr, unsigned long size) +{ + return clear_user(addr, size); +} + extern long strncpy_from_user(char *dst, const char __user *src, long count); extern __must_check long strnlen_user(const char __user *str, long n); -- cgit