diff options
Diffstat (limited to 'arch/powerpc/mm')
-rw-r--r-- | arch/powerpc/mm/mem.c | 1 | ||||
-rw-r--r-- | arch/powerpc/mm/mmu_context_book3s64.c | 5 | ||||
-rw-r--r-- | arch/powerpc/mm/pgtable-hash64.c | 44 | ||||
-rw-r--r-- | arch/powerpc/mm/pgtable-radix.c | 62 | ||||
-rw-r--r-- | arch/powerpc/mm/pgtable_64.c | 8 | ||||
-rw-r--r-- | arch/powerpc/mm/subpage-prot.c | 2 | ||||
-rw-r--r-- | arch/powerpc/mm/tlb-radix.c | 45 |
7 files changed, 143 insertions, 24 deletions
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 8541f18694a4..46b4e67d2372 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -402,6 +402,7 @@ void __init mem_init(void) void free_initmem(void) { ppc_md.progress = ppc_printk_progress; + mark_initmem_nx(); free_initmem_default(POISON_FREE_INITMEM); } diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index abed1fe6992f..a75f63833284 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -126,9 +126,10 @@ static int hash__init_new_context(struct mm_struct *mm) static int radix__init_new_context(struct mm_struct *mm) { unsigned long rts_field; - int index; + int index, max_id; - index = alloc_context_id(1, PRTB_ENTRIES - 1); + max_id = (1 << mmu_pid_bits) - 1; + index = alloc_context_id(mmu_base_pid, max_id); if (index < 0) return index; diff --git a/arch/powerpc/mm/pgtable-hash64.c b/arch/powerpc/mm/pgtable-hash64.c index 188b4107584d..443a2c66a304 100644 --- a/arch/powerpc/mm/pgtable-hash64.c +++ b/arch/powerpc/mm/pgtable-hash64.c @@ -425,33 +425,51 @@ int hash__has_transparent_hugepage(void) #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifdef CONFIG_STRICT_KERNEL_RWX -void hash__mark_rodata_ro(void) +static bool hash__change_memory_range(unsigned long start, unsigned long end, + unsigned long newpp) { - unsigned long start = (unsigned long)_stext; - unsigned long end = (unsigned long)__init_begin; unsigned long idx; unsigned int step, shift; - unsigned long newpp = PP_RXXX; shift = mmu_psize_defs[mmu_linear_psize].shift; step = 1 << shift; - start = ((start + step - 1) >> shift) << shift; - end = (end >> shift) << shift; + start = ALIGN_DOWN(start, step); + end = ALIGN(end, step); // aligns up - pr_devel("marking ro start %lx, end %lx, step %x\n", - start, end, step); + if (start >= end) + return false; - if (start == end) { - pr_warn("could not set rodata ro, relocate the start" - " of the kernel to a 0x%x boundary\n", step); - return; - } + pr_debug("Changing page protection on range 0x%lx-0x%lx, to 0x%lx, step 0x%x\n", + start, end, newpp, step); for (idx = start; idx < end; idx += step) /* Not sure if we can do much with the return value */ mmu_hash_ops.hpte_updateboltedpp(newpp, idx, mmu_linear_psize, mmu_kernel_ssize); + return true; +} + +void hash__mark_rodata_ro(void) +{ + unsigned long start, end; + + start = (unsigned long)_stext; + end = (unsigned long)__init_begin; + + WARN_ON(!hash__change_memory_range(start, end, PP_RXXX)); +} + +void hash__mark_initmem_nx(void) +{ + unsigned long start, end, pp; + + start = (unsigned long)__init_begin; + end = (unsigned long)__init_end; + + pp = htab_convert_pte_flags(pgprot_val(PAGE_KERNEL)); + + WARN_ON(!hash__change_memory_range(start, end, pp)); } #endif diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 8c13e4282308..671a45d86c18 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -25,6 +25,9 @@ #include <trace/events/thp.h> +unsigned int mmu_pid_bits; +unsigned int mmu_base_pid; + static int native_register_process_table(unsigned long base, unsigned long pg_sz, unsigned long table_size) { @@ -112,10 +115,9 @@ set_the_pte: } #ifdef CONFIG_STRICT_KERNEL_RWX -void radix__mark_rodata_ro(void) +void radix__change_memory_range(unsigned long start, unsigned long end, + unsigned long clear) { - unsigned long start = (unsigned long)_stext; - unsigned long end = (unsigned long)__init_begin; unsigned long idx; pgd_t *pgdp; pud_t *pudp; @@ -125,7 +127,8 @@ void radix__mark_rodata_ro(void) start = ALIGN_DOWN(start, PAGE_SIZE); end = PAGE_ALIGN(end); // aligns up - pr_devel("marking ro start %lx, end %lx\n", start, end); + pr_debug("Changing flags on range %lx-%lx removing 0x%lx\n", + start, end, clear); for (idx = start; idx < end; idx += PAGE_SIZE) { pgdp = pgd_offset_k(idx); @@ -147,11 +150,29 @@ void radix__mark_rodata_ro(void) if (!ptep) continue; update_the_pte: - radix__pte_update(&init_mm, idx, ptep, _PAGE_WRITE, 0, 0); + radix__pte_update(&init_mm, idx, ptep, clear, 0, 0); } radix__flush_tlb_kernel_range(start, end); } + +void radix__mark_rodata_ro(void) +{ + unsigned long start, end; + + start = (unsigned long)_stext; + end = (unsigned long)__init_begin; + + radix__change_memory_range(start, end, _PAGE_WRITE); +} + +void radix__mark_initmem_nx(void) +{ + unsigned long start = (unsigned long)__init_begin; + unsigned long end = (unsigned long)__init_end; + + radix__change_memory_range(start, end, _PAGE_EXEC); +} #endif /* CONFIG_STRICT_KERNEL_RWX */ static inline void __meminit print_mapping(unsigned long start, @@ -243,11 +264,34 @@ static void __init radix_init_pgtable(void) for_each_memblock(memory, reg) WARN_ON(create_physical_mapping(reg->base, reg->base + reg->size)); + + /* Find out how many PID bits are supported */ + if (cpu_has_feature(CPU_FTR_HVMODE)) { + if (!mmu_pid_bits) + mmu_pid_bits = 20; +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + /* + * When KVM is possible, we only use the top half of the + * PID space to avoid collisions between host and guest PIDs + * which can cause problems due to prefetch when exiting the + * guest with AIL=3 + */ + mmu_base_pid = 1 << (mmu_pid_bits - 1); +#else + mmu_base_pid = 1; +#endif + } else { + /* The guest uses the bottom half of the PID space */ + if (!mmu_pid_bits) + mmu_pid_bits = 19; + mmu_base_pid = 1; + } + /* * Allocate Partition table and process table for the * host. */ - BUILD_BUG_ON_MSG((PRTB_SIZE_SHIFT > 36), "Process table size too large."); + BUG_ON(PRTB_SIZE_SHIFT > 36); process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT); /* * Fill in the process table. @@ -321,6 +365,12 @@ static int __init radix_dt_scan_page_sizes(unsigned long node, if (type == NULL || strcmp(type, "cpu") != 0) return 0; + /* Find MMU PID size */ + prop = of_get_flat_dt_prop(node, "ibm,mmu-pid-bits", &size); + if (prop && size == 4) + mmu_pid_bits = be32_to_cpup(prop); + + /* Grab page size encodings */ prop = of_get_flat_dt_prop(node, "ibm,processor-radix-AP-encodings", &size); if (!prop) return 0; diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 5c0b795d656c..0736e94c7615 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -505,4 +505,12 @@ void mark_rodata_ro(void) else hash__mark_rodata_ro(); } + +void mark_initmem_nx(void) +{ + if (radix_enabled()) + radix__mark_initmem_nx(); + else + hash__mark_initmem_nx(); +} #endif diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c index e94fbd4c8845..781532d7bc4d 100644 --- a/arch/powerpc/mm/subpage-prot.c +++ b/arch/powerpc/mm/subpage-prot.c @@ -36,7 +36,7 @@ void subpage_prot_free(struct mm_struct *mm) } } addr = 0; - for (i = 0; i < 2; ++i) { + for (i = 0; i < (TASK_SIZE_USER64 >> 43); ++i) { p = spt->protptrs[i]; if (!p) continue; diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 744e0164ecf5..16ae1bbe13f0 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -12,12 +12,12 @@ #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/memblock.h> -#include <asm/ppc-opcode.h> +#include <asm/ppc-opcode.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include <asm/trace.h> - +#include <asm/cputhreads.h> #define RIC_FLUSH_TLB 0 #define RIC_FLUSH_PWC 1 @@ -454,3 +454,44 @@ void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm, else radix__flush_tlb_page_psize(mm, address, mmu_virtual_psize); } + +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +extern void radix_kvm_prefetch_workaround(struct mm_struct *mm) +{ + unsigned int pid = mm->context.id; + + if (unlikely(pid == MMU_NO_CONTEXT)) + return; + + /* + * If this context hasn't run on that CPU before and KVM is + * around, there's a slim chance that the guest on another + * CPU just brought in obsolete translation into the TLB of + * this CPU due to a bad prefetch using the guest PID on + * the way into the hypervisor. + * + * We work around this here. If KVM is possible, we check if + * any sibling thread is in KVM. If it is, the window may exist + * and thus we flush that PID from the core. + * + * A potential future improvement would be to mark which PIDs + * have never been used on the system and avoid it if the PID + * is new and the process has no other cpumask bit set. + */ + if (cpu_has_feature(CPU_FTR_HVMODE) && radix_enabled()) { + int cpu = smp_processor_id(); + int sib = cpu_first_thread_sibling(cpu); + bool flush = false; + + for (; sib <= cpu_last_thread_sibling(cpu) && !flush; sib++) { + if (sib == cpu) + continue; + if (paca[sib].kvm_hstate.kvm_vcpu) + flush = true; + } + if (flush) + _tlbiel_pid(pid, RIC_FLUSH_ALL); + } +} +EXPORT_SYMBOL_GPL(radix_kvm_prefetch_workaround); +#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ |