13 files changed, 66 insertions, 127 deletions

diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 7abf82a698d3..985cabdd7f67 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1621,8 +1621,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
 }
 EXPORT_SYMBOL_GPL(hash_page);
 
-DECLARE_INTERRUPT_HANDLER(__do_hash_fault);
-DEFINE_INTERRUPT_HANDLER(__do_hash_fault)
+DEFINE_INTERRUPT_HANDLER(do_hash_fault)
 {
 	unsigned long ea = regs->dar;
 	unsigned long dsisr = regs->dsisr;
@@ -1681,35 +1680,6 @@ DEFINE_INTERRUPT_HANDLER(__do_hash_fault)
 	}
 }
 
-/*
- * The _RAW interrupt entry checks for the in_nmi() case before
- * running the full handler.
- */
-DEFINE_INTERRUPT_HANDLER_RAW(do_hash_fault)
-{
-	/*
-	 * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then
-	 * don't call hash_page, just fail the fault. This is required to
-	 * prevent re-entrancy problems in the hash code, namely perf
-	 * interrupts hitting while something holds H_PAGE_BUSY, and taking a
-	 * hash fault. See the comment in hash_preload().
-	 *
-	 * We come here as a result of a DSI at a point where we don't want
-	 * to call hash_page, such as when we are accessing memory (possibly
-	 * user memory) inside a PMU interrupt that occurred while interrupts
-	 * were soft-disabled.  We want to invoke the exception handler for
-	 * the access, or panic if there isn't a handler.
-	 */
-	if (unlikely(in_nmi())) {
-		do_bad_page_fault_segv(regs);
-		return 0;
-	}
-
-	__do_hash_fault(regs);
-
-	return 0;
-}
-
 #ifdef CONFIG_PPC_MM_SLICES
 static bool should_hash_preload(struct mm_struct *mm, unsigned long ea)
 {
@@ -1776,26 +1746,18 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea,
 #endif /* CONFIG_PPC_64K_PAGES */
 
 	/*
-	 * __hash_page_* must run with interrupts off, as it sets the
-	 * H_PAGE_BUSY bit. It's possible for perf interrupts to hit at any
-	 * time and may take a hash fault reading the user stack, see
-	 * read_user_stack_slow() in the powerpc/perf code.
-	 *
-	 * If that takes a hash fault on the same page as we lock here, it
-	 * will bail out when seeing H_PAGE_BUSY set, and retry the access
-	 * leading to an infinite loop.
+	 * __hash_page_* must run with interrupts off, including PMI interrupts
+	 * off, as it sets the H_PAGE_BUSY bit.
 	 *
-	 * Disabling interrupts here does not prevent perf interrupts, but it
-	 * will prevent them taking hash faults (see the NMI test in
-	 * do_hash_page), then read_user_stack's copy_from_user_nofault will
-	 * fail and perf will fall back to read_user_stack_slow(), which
-	 * walks the Linux page tables.
+	 * It's otherwise possible for perf interrupts to hit at any time and
+	 * may take a hash fault reading the user stack, which could take a
+	 * hash miss and deadlock on the same H_PAGE_BUSY bit.
 	 *
 	 * Interrupts must also be off for the duration of the
 	 * mm_is_thread_local test and update, to prevent preempt running the
 	 * mm on another CPU (XXX: this may be racy vs kthread_use_mm).
 	 */
-	local_irq_save(flags);
+	powerpc_local_irq_pmu_save(flags);
 
 	/* Is that local to this CPU ? */
 	if (mm_is_thread_local(mm))
@@ -1820,7 +1782,7 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea,
 				   mm_ctx_user_psize(&mm->context),
 				   pte_val(*ptep));
 
-	local_irq_restore(flags);
+	powerpc_local_irq_pmu_restore(flags);
 }
 
 /*
diff --git a/arch/powerpc/mm/book3s64/hugetlbpage.c b/arch/powerpc/mm/book3s64/hugetlbpage.c
index ea8f83afb0ae..3bc0eb21b2a0 100644
--- a/arch/powerpc/mm/book3s64/hugetlbpage.c
+++ b/arch/powerpc/mm/book3s64/hugetlbpage.c
@@ -150,7 +150,7 @@ void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr
 	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
 }
 
-void __init hugetlbpage_init_default(void)
+void __init hugetlbpage_init_defaultsize(void)
 {
 	/* Set default large page size. Currently, we pick 16M or 1M
 	 * depending on what is available
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 79ce3c22a29d..052e6590f84f 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -6,6 +6,7 @@
 #include <linux/sched.h>
 #include <linux/mm_types.h>
 #include <linux/memblock.h>
+#include <linux/memremap.h>
 #include <linux/debugfs.h>
 #include <misc/cxl-base.h>
 
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index 31f4cef3adac..81091b9587f6 100644
--- a/arch/powerpc/mm/book3s64/slb.c
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -9,7 +9,6 @@
  * Copyright (C) 2002 Anton Blanchard <anton@au.ibm.com>, IBM
  */
 
-#include <asm/asm-prototypes.h>
 #include <asm/interrupt.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
diff --git a/arch/powerpc/mm/book3s64/trace.c b/arch/powerpc/mm/book3s64/trace.c
index b86e7b906257..ccd64b5e6cac 100644
--- a/arch/powerpc/mm/book3s64/trace.c
+++ b/arch/powerpc/mm/book3s64/trace.c
@@ -3,6 +3,5 @@
  * This file is for defining trace points and trace related helpers.
  */
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define CREATE_TRACE_POINTS
 #include <trace/events/thp.h>
 #endif
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index eb8ecd7343a9..d53fed4eccbd 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -35,7 +35,6 @@
 #include <linux/kfence.h>
 #include <linux/pkeys.h>
 
-#include <asm/asm-prototypes.h>
 #include <asm/firmware.h>
 #include <asm/interrupt.h>
 #include <asm/page.h>
@@ -567,18 +566,24 @@ NOKPROBE_SYMBOL(hash__do_page_fault);
 static void __bad_page_fault(struct pt_regs *regs, int sig)
 {
 	int is_write = page_fault_is_write(regs->dsisr);
+	const char *msg;
 
 	/* kernel has accessed a bad area */
 
+	if (regs->dar < PAGE_SIZE)
+		msg = "Kernel NULL pointer dereference";
+	else
+		msg = "Unable to handle kernel data access";
+
 	switch (TRAP(regs)) {
 	case INTERRUPT_DATA_STORAGE:
-	case INTERRUPT_DATA_SEGMENT:
 	case INTERRUPT_H_DATA_STORAGE:
-		pr_alert("BUG: %s on %s at 0x%08lx\n",
-			 regs->dar < PAGE_SIZE ? "Kernel NULL pointer dereference" :
-			 "Unable to handle kernel data access",
+		pr_alert("BUG: %s on %s at 0x%08lx\n", msg,
 			 is_write ? "write" : "read", regs->dar);
 		break;
+	case INTERRUPT_DATA_SEGMENT:
+		pr_alert("BUG: %s at 0x%08lx\n", msg, regs->dar);
+		break;
 	case INTERRUPT_INST_STORAGE:
 	case INTERRUPT_INST_SEGMENT:
 		pr_alert("BUG: Unable to handle kernel instruction fetch%s",
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index ddead41e2194..b642a5a8668f 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -664,10 +664,7 @@ static int __init hugetlbpage_init(void)
 		configured = true;
 	}
 
-	if (configured) {
-		if (IS_ENABLED(CONFIG_HUGETLB_PAGE_SIZE_VARIABLE))
-			hugetlbpage_init_default();
-	} else
+	if (!configured)
 		pr_info("Failed to initialize. Disabling HugeTLB");
 
 	return 0;
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 35f46bf54281..83c0ee9fbf05 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -59,6 +59,7 @@
 #include <asm/sections.h>
 #include <asm/iommu.h>
 #include <asm/vdso.h>
+#include <asm/hugetlb.h>
 
 #include <mm/mmu_decl.h>
 
@@ -513,6 +514,9 @@ void __init mmu_early_init_devtree(void)
 	} else
 		hash__early_init_devtree();
 
+	if (IS_ENABLED(CONFIG_HUGETLB_PAGE_SIZE_VARIABLE))
+		hugetlbpage_init_defaultsize();
+
 	if (!(cur_cpu_spec->mmu_features & MMU_FTR_HPTE_TABLE) &&
 	    !(cur_cpu_spec->mmu_features & MMU_FTR_TYPE_RADIX))
 		panic("kernel does not support any MMU type offered by platform");
diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c
index cf8770b1a692..f3e4d069e0ba 100644
--- a/arch/powerpc/mm/kasan/kasan_init_32.c
+++ b/arch/powerpc/mm/kasan/kasan_init_32.c
@@ -83,13 +83,12 @@ void __init
 kasan_update_early_region(unsigned long k_start, unsigned long k_end, pte_t pte)
 {
 	unsigned long k_cur;
-	phys_addr_t pa = __pa(kasan_early_shadow_page);
 
 	for (k_cur = k_start; k_cur != k_end; k_cur += PAGE_SIZE) {
 		pmd_t *pmd = pmd_off_k(k_cur);
 		pte_t *ptep = pte_offset_kernel(pmd, k_cur);
 
-		if ((pte_val(*ptep) & PTE_RPN_MASK) != pa)
+		if (pte_page(*ptep) != virt_to_page(lm_alias(kasan_early_shadow_page)))
 			continue;
 
 		__set_pte_at(&init_mm, k_cur, ptep, pte, 0);
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 9d5f710d2c20..b9b7fefbb64b 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -956,7 +956,9 @@ static int __init parse_numa_properties(void)
 			of_node_put(cpu);
 		}
 
-		node_set_online(nid);
+		/* node_set_online() is an UB if 'nid' is negative */
+		if (likely(nid >= 0))
+			node_set_online(nid);
 	}
 
 	get_n_mem_cells(&n_mem_addr_cells, &n_mem_size_cells);
diff --git a/arch/powerpc/mm/pageattr.c b/arch/powerpc/mm/pageattr.c
index edea388e9d3f..85753e32a4de 100644
--- a/arch/powerpc/mm/pageattr.c
+++ b/arch/powerpc/mm/pageattr.c
@@ -15,12 +15,14 @@
 #include <asm/pgtable.h>
 
 
+static pte_basic_t pte_update_delta(pte_t *ptep, unsigned long addr,
+				    unsigned long old, unsigned long new)
+{
+	return pte_update(&init_mm, addr, ptep, old & ~new, new & ~old, 0);
+}
+
 /*
- * Updates the attributes of a page in three steps:
- *
- * 1. take the page_table_lock
- * 2. install the new entry with the updated attributes
- * 3. flush the TLB
+ * Updates the attributes of a page atomically.
  *
  * This sequence is safe against concurrent updates, and also allows updating the
  * attributes of a page currently being executed or accessed.
@@ -28,41 +30,39 @@
 static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
 {
 	long action = (long)data;
-	pte_t pte;
 
-	spin_lock(&init_mm.page_table_lock);
-
-	pte = ptep_get(ptep);
-
-	/* modify the PTE bits as desired, then apply */
+	/* modify the PTE bits as desired */
 	switch (action) {
 	case SET_MEMORY_RO:
-		pte = pte_wrprotect(pte);
+		/* Don't clear DIRTY bit */
+		pte_update_delta(ptep, addr, _PAGE_KERNEL_RW & ~_PAGE_DIRTY, _PAGE_KERNEL_RO);
 		break;
 	case SET_MEMORY_RW:
-		pte = pte_mkwrite(pte_mkdirty(pte));
+		pte_update_delta(ptep, addr, _PAGE_KERNEL_RO, _PAGE_KERNEL_RW);
 		break;
 	case SET_MEMORY_NX:
-		pte = pte_exprotect(pte);
+		pte_update_delta(ptep, addr, _PAGE_KERNEL_ROX, _PAGE_KERNEL_RO);
 		break;
 	case SET_MEMORY_X:
-		pte = pte_mkexec(pte);
+		pte_update_delta(ptep, addr, _PAGE_KERNEL_RO, _PAGE_KERNEL_ROX);
+		break;
+	case SET_MEMORY_NP:
+		pte_update(&init_mm, addr, ptep, _PAGE_PRESENT, 0, 0);
+		break;
+	case SET_MEMORY_P:
+		pte_update(&init_mm, addr, ptep, 0, _PAGE_PRESENT, 0);
 		break;
 	default:
 		WARN_ON_ONCE(1);
 		break;
 	}
 
-	pte_update(&init_mm, addr, ptep, ~0UL, pte_val(pte), 0);
-
 	/* See ptesync comment in radix__set_pte_at() */
 	if (radix_enabled())
 		asm volatile("ptesync": : :"memory");
 
 	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
 
-	spin_unlock(&init_mm.page_table_lock);
-
 	return 0;
 }
 
@@ -96,36 +96,3 @@ int change_memory_attr(unsigned long addr, int numpages, long action)
 	return apply_to_existing_page_range(&init_mm, start, size,
 					    change_page_attr, (void *)action);
 }
-
-/*
- * Set the attributes of a page:
- *
- * This function is used by PPC32 at the end of init to set final kernel memory
- * protection. It includes changing the maping of the page it is executing from
- * and data pages it is using.
- */
-static int set_page_attr(pte_t *ptep, unsigned long addr, void *data)
-{
-	pgprot_t prot = __pgprot((unsigned long)data);
-
-	spin_lock(&init_mm.page_table_lock);
-
-	set_pte_at(&init_mm, addr, ptep, pte_modify(*ptep, prot));
-	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
-
-	spin_unlock(&init_mm.page_table_lock);
-
-	return 0;
-}
-
-int set_memory_attr(unsigned long addr, int numpages, pgprot_t prot)
-{
-	unsigned long start = ALIGN_DOWN(addr, PAGE_SIZE);
-	unsigned long sz = numpages * PAGE_SIZE;
-
-	if (numpages <= 0)
-		return 0;
-
-	return apply_to_existing_page_range(&init_mm, start, sz, set_page_attr,
-					    (void *)pgprot_val(prot));
-}
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 906e4e4328b2..a56ade39dc68 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -135,10 +135,12 @@ void mark_initmem_nx(void)
 	unsigned long numpages = PFN_UP((unsigned long)_einittext) -
 				 PFN_DOWN((unsigned long)_sinittext);
 
-	if (v_block_mapped((unsigned long)_sinittext))
+	if (v_block_mapped((unsigned long)_sinittext)) {
 		mmu_mark_initmem_nx();
-	else
-		set_memory_attr((unsigned long)_sinittext, numpages, PAGE_KERNEL);
+	} else {
+		set_memory_nx((unsigned long)_sinittext, numpages);
+		set_memory_rw((unsigned long)_sinittext, numpages);
+	}
 }
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
@@ -146,24 +148,23 @@ void mark_rodata_ro(void)
 {
 	unsigned long numpages;
 
+	if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX) && mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		pr_warn("This platform has HASH MMU, STRICT_MODULE_RWX won't work\n");
+
 	if (v_block_mapped((unsigned long)_stext + 1)) {
 		mmu_mark_rodata_ro();
 		ptdump_check_wx();
 		return;
 	}
 
-	numpages = PFN_UP((unsigned long)_etext) -
-		   PFN_DOWN((unsigned long)_stext);
-
-	set_memory_attr((unsigned long)_stext, numpages, PAGE_KERNEL_ROX);
 	/*
-	 * mark .rodata as read only. Use __init_begin rather than __end_rodata
-	 * to cover NOTES and EXCEPTION_TABLE.
+	 * mark .text and .rodata as read only. Use __init_begin rather than
+	 * __end_rodata to cover NOTES and EXCEPTION_TABLE.
 	 */
 	numpages = PFN_UP((unsigned long)__init_begin) -
-		   PFN_DOWN((unsigned long)__start_rodata);
+		   PFN_DOWN((unsigned long)_stext);
 
-	set_memory_attr((unsigned long)__start_rodata, numpages, PAGE_KERNEL_RO);
+	set_memory_ro((unsigned long)_stext, numpages);
 
 	// mark_initmem_nx() should have already run by now
 	ptdump_check_wx();
@@ -179,8 +180,8 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 		return;
 
 	if (enable)
-		set_memory_attr(addr, numpages, PAGE_KERNEL);
+		set_memory_p(addr, numpages);
 	else
-		set_memory_attr(addr, numpages, __pgprot(0));
+		set_memory_np(addr, numpages);
 }
 #endif /* CONFIG_DEBUG_PAGEALLOC */
diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c
index c7f824d294b2..9a601587836b 100644
--- a/arch/powerpc/mm/ptdump/hashpagetable.c
+++ b/arch/powerpc/mm/ptdump/hashpagetable.c
@@ -238,7 +238,10 @@ static int native_find(unsigned long ea, int psize, bool primary, u64 *v, u64
 
 static int pseries_find(unsigned long ea, int psize, bool primary, u64 *v, u64 *r)
 {
-	struct hash_pte ptes[4];
+	struct {
+		unsigned long v;
+		unsigned long r;
+	} ptes[4];
 	unsigned long vsid, vpn, hash, hpte_group, want_v;
 	int i, j, ssize = mmu_kernel_ssize;
 	long lpar_rc = 0;