From 941d810725ad48cc21948f4cff8cf70fa2a67cf9 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 16 Jul 2018 23:52:14 +1000 Subject: [PATCH 1/5] powerpc/xmon: Fix disassembly since printf changes The recent change to add printf annotations to xmon inadvertently made the disassembly output ugly, eg: c00000002001e058 7ee00026 mfcr r23 c00000002001e05c fffffffffae101a0 std r23,416(r1) c00000002001e060 fffffffff8230000 std r1,0(r3) The problem being that negative 32-bit values are being displayed in full 64-bits. The printf conversion was actually correct, we are passing unsigned long so it should use "lx". But powerpc instructions are only 4 bytes and the code only reads 4 bytes, so inst should really just be unsigned int, and that also fixes the printing to look the way we want: c00000002001e058 7ee00026 mfcr r23 c00000002001e05c fae101a0 std r23,416(r1) c00000002001e060 f8230000 std r1,0(r3) Fixes: e70d8f55268b ("powerpc/xmon: Add __printf annotation to xmon_printf()") Signed-off-by: Michael Ellerman --- arch/powerpc/xmon/xmon.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 47166ad2a669..196978733e64 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2734,7 +2734,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr, { int nr, dotted; unsigned long first_adr; - unsigned long inst, last_inst = 0; + unsigned int inst, last_inst = 0; unsigned char val[4]; dotted = 0; @@ -2758,7 +2758,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr, dotted = 0; last_inst = inst; if (praddr) - printf(REG" %.8lx", adr, inst); + printf(REG" %.8x", adr, inst); printf("\t"); dump_func(inst, adr); printf("\n"); From 1463edca6734d42ab4406fa2896e20b45478ea36 Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Tue, 17 Jul 2018 17:19:12 +1000 Subject: [PATCH 2/5] vfio/spapr: Use IOMMU pageshift rather than pagesize The size is always equal to 1 page so let's use this. Later on this will be used for other checks which use page shifts to check the granularity of access. This should cause no behavioral change. Cc: stable@vger.kernel.org # v4.12+ Reviewed-by: David Gibson Acked-by: Alex Williamson Signed-off-by: Alexey Kardashevskiy Signed-off-by: Michael Ellerman --- drivers/vfio/vfio_iommu_spapr_tce.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index 759a5bdd40e1..2da5f054257a 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -457,13 +457,13 @@ static void tce_iommu_unuse_page(struct tce_container *container, } static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container, - unsigned long tce, unsigned long size, + unsigned long tce, unsigned long shift, unsigned long *phpa, struct mm_iommu_table_group_mem_t **pmem) { long ret = 0; struct mm_iommu_table_group_mem_t *mem; - mem = mm_iommu_lookup(container->mm, tce, size); + mem = mm_iommu_lookup(container->mm, tce, 1ULL << shift); if (!mem) return -EINVAL; @@ -487,7 +487,7 @@ static void tce_iommu_unuse_page_v2(struct tce_container *container, if (!pua) return; - ret = tce_iommu_prereg_ua_to_hpa(container, *pua, IOMMU_PAGE_SIZE(tbl), + ret = tce_iommu_prereg_ua_to_hpa(container, *pua, tbl->it_page_shift, &hpa, &mem); if (ret) pr_debug("%s: tce %lx at #%lx was not cached, ret=%d\n", @@ -611,7 +611,7 @@ static long tce_iommu_build_v2(struct tce_container *container, entry + i); ret = tce_iommu_prereg_ua_to_hpa(container, - tce, IOMMU_PAGE_SIZE(tbl), &hpa, &mem); + tce, tbl->it_page_shift, &hpa, &mem); if (ret) break; From 76fa4975f3ed12d15762bc979ca44078598ed8ee Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Tue, 17 Jul 2018 17:19:13 +1000 Subject: [PATCH 3/5] KVM: PPC: Check if IOMMU page is contained in the pinned physical page A VM which has: - a DMA capable device passed through to it (eg. network card); - running a malicious kernel that ignores H_PUT_TCE failure; - capability of using IOMMU pages bigger that physical pages can create an IOMMU mapping that exposes (for example) 16MB of the host physical memory to the device when only 64K was allocated to the VM. The remaining 16MB - 64K will be some other content of host memory, possibly including pages of the VM, but also pages of host kernel memory, host programs or other VMs. The attacking VM does not control the location of the page it can map, and is only allowed to map as many pages as it has pages of RAM. We already have a check in drivers/vfio/vfio_iommu_spapr_tce.c that an IOMMU page is contained in the physical page so the PCI hardware won't get access to unassigned host memory; however this check is missing in the KVM fastpath (H_PUT_TCE accelerated code). We were lucky so far and did not hit this yet as the very first time when the mapping happens we do not have tbl::it_userspace allocated yet and fall back to the userspace which in turn calls VFIO IOMMU driver, this fails and the guest does not retry, This stores the smallest preregistered page size in the preregistered region descriptor and changes the mm_iommu_xxx API to check this against the IOMMU page size. This calculates maximum page size as a minimum of the natural region alignment and compound page size. For the page shift this uses the shift returned by find_linux_pte() which indicates how the page is mapped to the current userspace - if the page is huge and this is not a zero, then it is a leaf pte and the page is mapped within the range. Fixes: 121f80ba68f1 ("KVM: PPC: VFIO: Add in-kernel acceleration for VFIO") Cc: stable@vger.kernel.org # v4.12+ Signed-off-by: Alexey Kardashevskiy Reviewed-by: David Gibson Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/mmu_context.h | 4 +-- arch/powerpc/kvm/book3s_64_vio.c | 2 +- arch/powerpc/kvm/book3s_64_vio_hv.c | 6 +++-- arch/powerpc/mm/mmu_context_iommu.c | 37 ++++++++++++++++++++++++-- drivers/vfio/vfio_iommu_spapr_tce.c | 2 +- 5 files changed, 43 insertions(+), 8 deletions(-) diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 896efa559996..79d570cbf332 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -35,9 +35,9 @@ extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm( extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm, unsigned long ua, unsigned long entries); extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned long *hpa); + unsigned long ua, unsigned int pageshift, unsigned long *hpa); extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned long *hpa); + unsigned long ua, unsigned int pageshift, unsigned long *hpa); extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem); extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem); #endif diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index d066e37551ec..8c456fa691a5 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -449,7 +449,7 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, /* This only handles v2 IOMMU type, v1 is handled via ioctl() */ return H_TOO_HARD; - if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa))) + if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, tbl->it_page_shift, &hpa))) return H_HARDWARE; if (mm_iommu_mapped_inc(mem)) diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 925fc316a104..5b298f5a1a14 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -279,7 +279,8 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, if (!mem) return H_TOO_HARD; - if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa))) + if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, tbl->it_page_shift, + &hpa))) return H_HARDWARE; pua = (void *) vmalloc_to_phys(pua); @@ -469,7 +470,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K); if (mem) - prereg = mm_iommu_ua_to_hpa_rm(mem, ua, &tces) == 0; + prereg = mm_iommu_ua_to_hpa_rm(mem, ua, + IOMMU_PAGE_SHIFT_4K, &tces) == 0; } if (!prereg) { diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c index abb43646927a..a4ca57612558 100644 --- a/arch/powerpc/mm/mmu_context_iommu.c +++ b/arch/powerpc/mm/mmu_context_iommu.c @@ -19,6 +19,7 @@ #include #include #include +#include static DEFINE_MUTEX(mem_list_mutex); @@ -27,6 +28,7 @@ struct mm_iommu_table_group_mem_t { struct rcu_head rcu; unsigned long used; atomic64_t mapped; + unsigned int pageshift; u64 ua; /* userspace address */ u64 entries; /* number of entries in hpas[] */ u64 *hpas; /* vmalloc'ed */ @@ -125,6 +127,8 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries, { struct mm_iommu_table_group_mem_t *mem; long i, j, ret = 0, locked_entries = 0; + unsigned int pageshift; + unsigned long flags; struct page *page = NULL; mutex_lock(&mem_list_mutex); @@ -159,6 +163,12 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries, goto unlock_exit; } + /* + * For a starting point for a maximum page size calculation + * we use @ua and @entries natural alignment to allow IOMMU pages + * smaller than huge pages but still bigger than PAGE_SIZE. + */ + mem->pageshift = __ffs(ua | (entries << PAGE_SHIFT)); mem->hpas = vzalloc(array_size(entries, sizeof(mem->hpas[0]))); if (!mem->hpas) { kfree(mem); @@ -199,6 +209,23 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries, } } populate: + pageshift = PAGE_SHIFT; + if (PageCompound(page)) { + pte_t *pte; + struct page *head = compound_head(page); + unsigned int compshift = compound_order(head); + + local_irq_save(flags); /* disables as well */ + pte = find_linux_pte(mm->pgd, ua, NULL, &pageshift); + local_irq_restore(flags); + + /* Double check it is still the same pinned page */ + if (pte && pte_page(*pte) == head && + pageshift == compshift) + pageshift = max_t(unsigned int, pageshift, + PAGE_SHIFT); + } + mem->pageshift = min(mem->pageshift, pageshift); mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT; } @@ -349,7 +376,7 @@ struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm, EXPORT_SYMBOL_GPL(mm_iommu_find); long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned long *hpa) + unsigned long ua, unsigned int pageshift, unsigned long *hpa) { const long entry = (ua - mem->ua) >> PAGE_SHIFT; u64 *va = &mem->hpas[entry]; @@ -357,6 +384,9 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, if (entry >= mem->entries) return -EFAULT; + if (pageshift > mem->pageshift) + return -EFAULT; + *hpa = *va | (ua & ~PAGE_MASK); return 0; @@ -364,7 +394,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa); long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned long *hpa) + unsigned long ua, unsigned int pageshift, unsigned long *hpa) { const long entry = (ua - mem->ua) >> PAGE_SHIFT; void *va = &mem->hpas[entry]; @@ -373,6 +403,9 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, if (entry >= mem->entries) return -EFAULT; + if (pageshift > mem->pageshift) + return -EFAULT; + pa = (void *) vmalloc_to_phys(va); if (!pa) return -EFAULT; diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index 2da5f054257a..7cd63b0c1a46 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -467,7 +467,7 @@ static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container, if (!mem) return -EINVAL; - ret = mm_iommu_ua_to_hpa(mem, tce, phpa); + ret = mm_iommu_ua_to_hpa(mem, tce, shift, phpa); if (ret) return -EINVAL; From 4e4a4b75ccce827f9b8b04b6ee5c90169df4b6ee Mon Sep 17 00:00:00 2001 From: James Clarke Date: Thu, 12 Jul 2018 22:41:49 +0100 Subject: [PATCH 4/5] powerpc/Makefile: Assemble with -me500 when building for E500 Some of the assembly files use instructions specific to BookE or E500, which are rejected with the now-default -mcpu=powerpc, so we must pass -me500 to the assembler just as we pass -me200 for E200. Fixes: 4bf4f42a2feb ("powerpc/kbuild: Set default generic machine type for 32-bit compile") Signed-off-by: James Clarke Signed-off-by: Michael Ellerman --- arch/powerpc/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 2ea575cb3401..fb96206de317 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -243,6 +243,7 @@ endif cpu-as-$(CONFIG_4xx) += -Wa,-m405 cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec) cpu-as-$(CONFIG_E200) += -Wa,-me200 +cpu-as-$(CONFIG_E500) += -Wa,-me500 cpu-as-$(CONFIG_PPC_BOOK3S_64) += -Wa,-mpower4 cpu-as-$(CONFIG_PPC_E500MC) += $(call as-option,-Wa$(comma)-me500mc) From b03897cf318dfc47de33a7ecbc7655584266f034 Mon Sep 17 00:00:00 2001 From: "Gautham R. Shenoy" Date: Wed, 18 Jul 2018 14:03:16 +0530 Subject: [PATCH 5/5] powerpc/powernv: Fix save/restore of SPRG3 on entry/exit from stop (idle) On 64-bit servers, SPRN_SPRG3 and its userspace read-only mirror SPRN_USPRG3 are used as userspace VDSO write and read registers respectively. SPRN_SPRG3 is lost when we enter stop4 and above, and is currently not restored. As a result, any read from SPRN_USPRG3 returns zero on an exit from stop4 (Power9 only) and above. Thus in this situation, on POWER9, any call from sched_getcpu() always returns zero, as on powerpc, we call __kernel_getcpu() which relies upon SPRN_USPRG3 to report the CPU and NUMA node information. Fix this by restoring SPRN_SPRG3 on wake up from a deep stop state with the sprg_vdso value that is cached in PACA. Fixes: e1c1cfed5432 ("powerpc/powernv: Save/Restore additional SPRs for stop4 cpuidle") Cc: stable@vger.kernel.org # v4.14+ Reported-by: Florian Weimer Signed-off-by: Gautham R. Shenoy Reviewed-by: Michael Ellerman Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/idle_book3s.S | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index e734f6e45abc..689306118b48 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -144,7 +144,9 @@ power9_restore_additional_sprs: mtspr SPRN_MMCR1, r4 ld r3, STOP_MMCR2(r13) + ld r4, PACA_SPRG_VDSO(r13) mtspr SPRN_MMCR2, r3 + mtspr SPRN_SPRG3, r4 blr /*