From a6e2c226c3d51fd93636320e47cabc8a8f0824c5 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Sun, 24 May 2020 15:08:19 +0530 Subject: powerpc: Fix kernel crash in show_instructions() w/DEBUG_VIRTUAL With CONFIG_DEBUG_VIRTUAL=y, we can hit a BUG() if we take a hard lockup watchdog interrupt when in OPAL mode. This happens in show_instructions() if the kernel takes the watchdog NMI IPI, or any other interrupt, with MSR_IR == 0. show_instructions() updates the variable pc in the loop and the second iteration will result in BUG(). We hit the BUG_ON due the below check in __va() #define __va(x) ({ VIRTUAL_BUG_ON((unsigned long)(x) >= PAGE_OFFSET); (void *)(unsigned long)((phys_addr_t)(x) | PAGE_OFFSET); }) Fix it by moving the check out of the loop. Also update nip so that the nip == pc check still matches. Fixes: 4dd7554a6456 ("powerpc/64: Add VIRTUAL_BUG_ON checks for __va and __pa addresses") Signed-off-by: Aneesh Kumar K.V [mpe: Use IS_ENABLED(), massage change log] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200524093822.423487-1-aneesh.kumar@linux.ibm.com --- arch/powerpc/kernel/process.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 7bb7faf84490..a2f1f0e70a4b 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1252,29 +1252,31 @@ struct task_struct *__switch_to(struct task_struct *prev, static void show_instructions(struct pt_regs *regs) { int i; + unsigned long nip = regs->nip; unsigned long pc = regs->nip - (NR_INSN_TO_PRINT * 3 / 4 * sizeof(int)); printk("Instruction dump:"); + /* + * If we were executing with the MMU off for instructions, adjust pc + * rather than printing XXXXXXXX. + */ + if (!IS_ENABLED(CONFIG_BOOKE) && !(regs->msr & MSR_IR)) { + pc = (unsigned long)phys_to_virt(pc); + nip = (unsigned long)phys_to_virt(regs->nip); + } + for (i = 0; i < NR_INSN_TO_PRINT; i++) { int instr; if (!(i % 8)) pr_cont("\n"); -#if !defined(CONFIG_BOOKE) - /* If executing with the IMMU off, adjust pc rather - * than print XXXXXXXX. - */ - if (!(regs->msr & MSR_IR)) - pc = (unsigned long)phys_to_virt(pc); -#endif - if (!__kernel_text_address(pc) || probe_kernel_address((const void *)pc, instr)) { pr_cont("XXXXXXXX "); } else { - if (regs->nip == pc) + if (nip == pc) pr_cont("<%08x> ", instr); else pr_cont("%08x ", instr); -- cgit v1.2.3 From 0bdcfa182506526fbe4e088ff9ca86a31b81828d Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Mon, 15 Jun 2020 16:12:47 +1000 Subject: powerpc/64s: Fix KVM interrupt using wrong save area The CTR register reload in the KVM interrupt path used the wrong save area for SLB (and NMI) interrupts. Fixes: 9600f261acaa ("powerpc/64s/exception: Move KVM test to common code") Cc: stable@vger.kernel.org # v5.7+ Reported-by: Christian Zigotzky Signed-off-by: Nicholas Piggin Tested-by: Christian Zigotzky Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200615061247.1310763-1-npiggin@gmail.com --- arch/powerpc/kernel/exceptions-64s.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index e70ebb5c318c..fa080694e581 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -270,7 +270,7 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_CFAR) .endif - ld r10,PACA_EXGEN+EX_CTR(r13) + ld r10,IAREA+EX_CTR(r13) mtctr r10 BEGIN_FTR_SECTION ld r10,IAREA+EX_PPR(r13) @@ -298,7 +298,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) .if IKVM_SKIP 89: mtocrf 0x80,r9 - ld r10,PACA_EXGEN+EX_CTR(r13) + ld r10,IAREA+EX_CTR(r13) mtctr r10 ld r9,IAREA+EX_R9(r13) ld r10,IAREA+EX_R10(r13) -- cgit v1.2.3 From 687993ccf3b05070598b89fad97410b26d7bc9d2 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 15 Jun 2020 12:22:29 +0300 Subject: powerpc/8xx: use pmd_off() to access a PMD entry in pte_update() The pte_update() implementation for PPC_8xx unfolds page table from the PGD level to access a PMD entry. Since 8xx has only 2-level page table this can be simplified with pmd_off() shortcut. Replace explicit unfolding with pmd_off() and drop defines of pgd_index() and pgd_offset() that are no longer needed. Signed-off-by: Mike Rapoport Reviewed-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200615092229.23142-1-rppt@kernel.org --- arch/powerpc/include/asm/nohash/32/pgtable.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index b56f14160ae5..5a590ceaec14 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -205,10 +205,6 @@ static inline void pmd_clear(pmd_t *pmdp) *pmdp = __pmd(0); } -/* to find an entry in a page-table-directory */ -#define pgd_index(address) ((address) >> PGDIR_SHIFT) -#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) - /* * PTE updates. This function is called whenever an existing * valid PTE is updated. This does -not- include set_pte_at() @@ -230,6 +226,8 @@ static inline void pmd_clear(pmd_t *pmdp) * For other page sizes, we have a single entry in the table. */ #ifdef CONFIG_PPC_8xx +static pmd_t *pmd_off(struct mm_struct *mm, unsigned long addr); + static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, unsigned long clr, unsigned long set, int huge) { @@ -237,7 +235,7 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p pte_basic_t old = pte_val(*p); pte_basic_t new = (old & ~(pte_basic_t)clr) | set; int num, i; - pmd_t *pmd = pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, addr), addr), addr), addr); + pmd_t *pmd = pmd_off(mm, addr); if (!huge) num = PAGE_SIZE / SZ_4K; -- cgit v1.2.3 From 1497eea68624f6076bf3eaf66baec3771ea04045 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 16 Jun 2020 23:56:16 +1000 Subject: powerpc/syscalls: Use the number when building SPU syscall table Currently the macro that inserts entries into the SPU syscall table doesn't actually use the "nr" (syscall number) parameter. This does work, but it relies on the exact right number of syscall entries being emitted in order for the syscal numbers to line up with the array entries. If for example we had two entries with the same syscall number we wouldn't get an error, it would just cause all subsequent syscalls to be off by one in the spu_syscall_table. So instead change the macro to assign to the specific entry of the array, meaning any numbering overlap will be caught by the compiler. Signed-off-by: Michael Ellerman Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/20200616135617.2937252-1-mpe@ellerman.id.au --- arch/powerpc/platforms/cell/spu_callbacks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/cell/spu_callbacks.c b/arch/powerpc/platforms/cell/spu_callbacks.c index cbee3666da07..abdef9bcf432 100644 --- a/arch/powerpc/platforms/cell/spu_callbacks.c +++ b/arch/powerpc/platforms/cell/spu_callbacks.c @@ -35,7 +35,7 @@ */ static void *spu_syscall_table[] = { -#define __SYSCALL(nr, entry) entry, +#define __SYSCALL(nr, entry) [nr] = entry, #include #undef __SYSCALL }; -- cgit v1.2.3 From 55ca22633a9faa34c6a61d99433f9cc8e28dd7cc Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 15 Jun 2020 12:57:57 +0000 Subject: mm/gup: Use huge_ptep_get() in gup_hugepte() gup_hugepte() reads hugepage table entries, it can't read them directly, huge_ptep_get() must be used. Fixes: 9e343b467c70 ("READ_ONCE: Enforce atomicity for {READ,WRITE}_ONCE() memory accesses") Signed-off-by: Christophe Leroy Acked-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/ffc3714334c3bfaca6f13788ad039e8759ae413f.1592225558.git.christophe.leroy@csgroup.eu --- mm/gup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/gup.c b/mm/gup.c index de9e36262ccb..761df4944ef5 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2425,7 +2425,7 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, if (pte_end < end) end = pte_end; - pte = READ_ONCE(*ptep); + pte = huge_ptep_get(ptep); if (!pte_access_permitted(pte, flags & FOLL_WRITE)) return 0; -- cgit v1.2.3 From 481e980a7c199c5a4634fd7ea308067dd4ba75fa Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 15 Jun 2020 12:57:58 +0000 Subject: mm: Allow arches to provide ptep_get() Since commit 9e343b467c70 ("READ_ONCE: Enforce atomicity for {READ,WRITE}_ONCE() memory accesses") it is not possible anymore to use READ_ONCE() to access complex page table entries like the one defined for powerpc 8xx with 16k size pages. Define a ptep_get() helper that architectures can override instead of performing a READ_ONCE() on the page table entry pointer. Fixes: 9e343b467c70 ("READ_ONCE: Enforce atomicity for {READ,WRITE}_ONCE() memory accesses") Signed-off-by: Christophe Leroy Acked-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/087fa12b6e920e32315136b998aa834f99242695.1592225558.git.christophe.leroy@csgroup.eu --- include/asm-generic/hugetlb.h | 2 +- include/linux/pgtable.h | 7 +++++++ mm/gup.c | 2 +- 3 files changed, 9 insertions(+), 2 deletions(-) diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h index 40f85decc2ee..8e1e6244a89d 100644 --- a/include/asm-generic/hugetlb.h +++ b/include/asm-generic/hugetlb.h @@ -122,7 +122,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, #ifndef __HAVE_ARCH_HUGE_PTEP_GET static inline pte_t huge_ptep_get(pte_t *ptep) { - return READ_ONCE(*ptep); + return ptep_get(ptep); } #endif diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 32b6c52d41b9..56c1e8eb7bb0 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -249,6 +249,13 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, } #endif +#ifndef __HAVE_ARCH_PTEP_GET +static inline pte_t ptep_get(pte_t *ptep) +{ + return READ_ONCE(*ptep); +} +#endif + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, diff --git a/mm/gup.c b/mm/gup.c index 761df4944ef5..6f47697f8fb0 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2196,7 +2196,7 @@ static inline pte_t gup_get_pte(pte_t *ptep) */ static inline pte_t gup_get_pte(pte_t *ptep) { - return READ_ONCE(*ptep); + return ptep_get(ptep); } #endif /* CONFIG_GUP_GET_PTE_LOW_HIGH */ -- cgit v1.2.3 From c0e1c8c22bebecef40097c80c1c74492ff96d081 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 15 Jun 2020 12:57:59 +0000 Subject: powerpc/8xx: Provide ptep_get() with 16k pages READ_ONCE() now enforces atomic read, which leads to: CC mm/gup.o In file included from ./include/linux/kernel.h:11:0, from mm/gup.c:2: In function 'gup_hugepte.constprop', inlined from 'gup_huge_pd.isra.79' at mm/gup.c:2465:8: ./include/linux/compiler.h:392:38: error: call to '__compiletime_assert_222' declared with attribute error: Unsupported access size for {READ,WRITE}_ONCE(). _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__) ^ ./include/linux/compiler.h:373:4: note: in definition of macro '__compiletime_assert' prefix ## suffix(); \ ^ ./include/linux/compiler.h:392:2: note: in expansion of macro '_compiletime_assert' _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__) ^ ./include/linux/compiler.h:405:2: note: in expansion of macro 'compiletime_assert' compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \ ^ ./include/linux/compiler.h:291:2: note: in expansion of macro 'compiletime_assert_rwonce_type' compiletime_assert_rwonce_type(x); \ ^ mm/gup.c:2428:8: note: in expansion of macro 'READ_ONCE' pte = READ_ONCE(*ptep); ^ In function 'gup_get_pte', inlined from 'gup_pte_range' at mm/gup.c:2228:9, inlined from 'gup_pmd_range' at mm/gup.c:2613:15, inlined from 'gup_pud_range' at mm/gup.c:2641:15, inlined from 'gup_p4d_range' at mm/gup.c:2666:15, inlined from 'gup_pgd_range' at mm/gup.c:2694:15, inlined from 'internal_get_user_pages_fast' at mm/gup.c:2795:3: ./include/linux/compiler.h:392:38: error: call to '__compiletime_assert_219' declared with attribute error: Unsupported access size for {READ,WRITE}_ONCE(). _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__) ^ ./include/linux/compiler.h:373:4: note: in definition of macro '__compiletime_assert' prefix ## suffix(); \ ^ ./include/linux/compiler.h:392:2: note: in expansion of macro '_compiletime_assert' _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__) ^ ./include/linux/compiler.h:405:2: note: in expansion of macro 'compiletime_assert' compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \ ^ ./include/linux/compiler.h:291:2: note: in expansion of macro 'compiletime_assert_rwonce_type' compiletime_assert_rwonce_type(x); \ ^ mm/gup.c:2199:9: note: in expansion of macro 'READ_ONCE' return READ_ONCE(*ptep); ^ make[2]: *** [mm/gup.o] Error 1 Define ptep_get() on 8xx when using 16k pages. Fixes: 9e343b467c70 ("READ_ONCE: Enforce atomicity for {READ,WRITE}_ONCE() memory accesses") Signed-off-by: Christophe Leroy Acked-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/341688399c1b102756046d19ea6ce39db1ae4742.1592225558.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/nohash/32/pgtable.h | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 5a590ceaec14..b0afbdd07740 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -284,6 +284,16 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, return __pte(pte_update(mm, addr, ptep, ~0, 0, 0)); } +#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES) +#define __HAVE_ARCH_PTEP_GET +static inline pte_t ptep_get(pte_t *ptep) +{ + pte_t pte = {READ_ONCE(ptep->pte), 0, 0, 0}; + + return pte; +} +#endif + #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) -- cgit v1.2.3