5 files changed, 210 insertions, 96 deletions

diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
index bcac4f55f9c1..c0557945939c 100644
--- a/arch/arm64/mm/contpte.c
+++ b/arch/arm64/mm/contpte.c
@@ -68,7 +68,144 @@ static void contpte_convert(struct mm_struct *mm, unsigned long addr,
 			pte = pte_mkyoung(pte);
 	}
 
-	__flush_tlb_range(&vma, start_addr, addr, PAGE_SIZE, true, 3);
+	/*
+	 * On eliding the __tlb_flush_range() under BBML2+noabort:
+	 *
+	 * NOTE: Instead of using N=16 as the contiguous block length, we use
+	 *       N=4 for clarity.
+	 *
+	 * NOTE: 'n' and 'c' are used to denote the "contiguous bit" being
+	 *       unset and set, respectively.
+	 *
+	 * We worry about two cases where contiguous bit is used:
+	 *  - When folding N smaller non-contiguous ptes as 1 contiguous block.
+	 *  - When unfolding a contiguous block into N smaller non-contiguous ptes.
+	 *
+	 * Currently, the BBML0 folding case looks as follows:
+	 *
+	 *  0) Initial page-table layout:
+	 *
+	 *   +----+----+----+----+
+	 *   |RO,n|RO,n|RO,n|RW,n| <--- last page being set as RO
+	 *   +----+----+----+----+
+	 *
+	 *  1) Aggregate AF + dirty flags using __ptep_get_and_clear():
+	 *
+	 *   +----+----+----+----+
+	 *   |  0 |  0 |  0 |  0 |
+	 *   +----+----+----+----+
+	 *
+	 *  2) __flush_tlb_range():
+	 *
+	 *   |____ tlbi + dsb ____|
+	 *
+	 *  3) __set_ptes() to repaint contiguous block:
+	 *
+	 *   +----+----+----+----+
+	 *   |RO,c|RO,c|RO,c|RO,c|
+	 *   +----+----+----+----+
+	 *
+	 *  4) The kernel will eventually __flush_tlb() for changed page:
+	 *
+	 *                  |____| <--- tlbi + dsb
+	 *
+	 * As expected, the intermediate tlbi+dsb ensures that other PEs
+	 * only ever see an invalid (0) entry, or the new contiguous TLB entry.
+	 * The final tlbi+dsb will always throw away the newly installed
+	 * contiguous TLB entry, which is a micro-optimisation opportunity,
+	 * but does not affect correctness.
+	 *
+	 * In the BBML2 case, the change is avoiding the intermediate tlbi+dsb.
+	 * This means a few things, but notably other PEs will still "see" any
+	 * stale cached TLB entries. This could lead to a "contiguous bit
+	 * misprogramming" issue until the final tlbi+dsb of the changed page,
+	 * which would clear out both the stale (RW,n) entry and the new (RO,c)
+	 * contiguous entry installed in its place.
+	 *
+	 * What this is saying, is the following:
+	 *
+	 *  +----+----+----+----+
+	 *  |RO,n|RO,n|RO,n|RW,n| <--- old page tables, all non-contiguous
+	 *  +----+----+----+----+
+	 *
+	 *  +----+----+----+----+
+	 *  |RO,c|RO,c|RO,c|RO,c| <--- new page tables, all contiguous
+	 *  +----+----+----+----+
+	 *   /\
+	 *   ||
+	 *
+	 *  If both the old single (RW,n) and new contiguous (RO,c) TLB entries
+	 *  are present, and a write is made to this address, do we fault or
+	 *  is the write permitted (via amalgamation)?
+	 *
+	 * The relevant Arm ARM DDI 0487L.a requirements are RNGLXZ and RJQQTC,
+	 * and together state that when BBML1 or BBML2 are implemented, either
+	 * a TLB conflict abort is raised (which we expressly forbid), or will
+	 * "produce an OA, access permissions, and memory attributes that are
+	 * consistent with any of the programmed translation table values".
+	 *
+	 * That is to say, will either raise a TLB conflict, or produce one of
+	 * the cached TLB entries, but never amalgamate.
+	 *
+	 * Thus, as the page tables are only considered "consistent" after
+	 * the final tlbi+dsb (which evicts both the single stale (RW,n) TLB
+	 * entry as well as the new contiguous (RO,c) TLB entry), omitting the
+	 * initial tlbi+dsb is correct.
+	 *
+	 * It is also important to note that at the end of the BBML2 folding
+	 * case, we are still left with potentially all N TLB entries still
+	 * cached (the N-1 non-contiguous ptes, and the single contiguous
+	 * block). However, over time, natural TLB pressure will cause the
+	 * non-contiguous pte TLB entries to be flushed, leaving only the
+	 * contiguous block TLB entry. This means that omitting the tlbi+dsb is
+	 * not only correct, but also keeps our eventual performance benefits.
+	 *
+	 * For the unfolding case, BBML0 looks as follows:
+	 *
+	 *  0) Initial page-table layout:
+	 *
+	 *   +----+----+----+----+
+	 *   |RW,c|RW,c|RW,c|RW,c| <--- last page being set as RO
+	 *   +----+----+----+----+
+	 *
+	 *  1) Aggregate AF + dirty flags using __ptep_get_and_clear():
+	 *
+	 *   +----+----+----+----+
+	 *   |  0 |  0 |  0 |  0 |
+	 *   +----+----+----+----+
+	 *
+	 *  2) __flush_tlb_range():
+	 *
+	 *   |____ tlbi + dsb ____|
+	 *
+	 *  3) __set_ptes() to repaint as non-contiguous:
+	 *
+	 *   +----+----+----+----+
+	 *   |RW,n|RW,n|RW,n|RW,n|
+	 *   +----+----+----+----+
+	 *
+	 *  4) Update changed page permissions:
+	 *
+	 *   +----+----+----+----+
+	 *   |RW,n|RW,n|RW,n|RO,n| <--- last page permissions set
+	 *   +----+----+----+----+
+	 *
+	 *  5) The kernel will eventually __flush_tlb() for changed page:
+	 *
+	 *                  |____| <--- tlbi + dsb
+	 *
+	 * For BBML2, we again remove the intermediate tlbi+dsb. Here, there
+	 * are no issues, as the final tlbi+dsb covering the changed page is
+	 * guaranteed to remove the original large contiguous (RW,c) TLB entry,
+	 * as well as the intermediate (RW,n) TLB entry; the next access will
+	 * install the new (RO,n) TLB entry and the page tables are only
+	 * considered "consistent" after the final tlbi+dsb, so software must
+	 * be prepared for this inconsistency prior to finishing the mm dance
+	 * regardless.
+	 */
+
+	if (!system_supports_bbml2_noabort())
+		__flush_tlb_range(&vma, start_addr, addr, PAGE_SIZE, true, 3);
 
 	__set_ptes(mm, start_addr, start_ptep, pte, CONT_PTES);
 }
@@ -169,17 +306,46 @@ pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte)
 	for (i = 0; i < CONT_PTES; i++, ptep++) {
 		pte = __ptep_get(ptep);
 
-		if (pte_dirty(pte))
+		if (pte_dirty(pte)) {
 			orig_pte = pte_mkdirty(orig_pte);
-
-		if (pte_young(pte))
+			for (; i < CONT_PTES; i++, ptep++) {
+				pte = __ptep_get(ptep);
+				if (pte_young(pte)) {
+					orig_pte = pte_mkyoung(orig_pte);
+					break;
+				}
+			}
+			break;
+		}
+
+		if (pte_young(pte)) {
 			orig_pte = pte_mkyoung(orig_pte);
+			i++;
+			ptep++;
+			for (; i < CONT_PTES; i++, ptep++) {
+				pte = __ptep_get(ptep);
+				if (pte_dirty(pte)) {
+					orig_pte = pte_mkdirty(orig_pte);
+					break;
+				}
+			}
+			break;
+		}
 	}
 
 	return orig_pte;
 }
 EXPORT_SYMBOL_GPL(contpte_ptep_get);
 
+static inline bool contpte_is_consistent(pte_t pte, unsigned long pfn,
+					pgprot_t orig_prot)
+{
+	pgprot_t prot = pte_pgprot(pte_mkold(pte_mkclean(pte)));
+
+	return pte_valid_cont(pte) && pte_pfn(pte) == pfn &&
+			pgprot_val(prot) == pgprot_val(orig_prot);
+}
+
 pte_t contpte_ptep_get_lockless(pte_t *orig_ptep)
 {
 	/*
@@ -202,7 +368,6 @@ pte_t contpte_ptep_get_lockless(pte_t *orig_ptep)
 	pgprot_t orig_prot;
 	unsigned long pfn;
 	pte_t orig_pte;
-	pgprot_t prot;
 	pte_t *ptep;
 	pte_t pte;
 	int i;
@@ -219,18 +384,44 @@ retry:
 
 	for (i = 0; i < CONT_PTES; i++, ptep++, pfn++) {
 		pte = __ptep_get(ptep);
-		prot = pte_pgprot(pte_mkold(pte_mkclean(pte)));
 
-		if (!pte_valid_cont(pte) ||
-		   pte_pfn(pte) != pfn ||
-		   pgprot_val(prot) != pgprot_val(orig_prot))
+		if (!contpte_is_consistent(pte, pfn, orig_prot))
 			goto retry;
 
-		if (pte_dirty(pte))
+		if (pte_dirty(pte)) {
 			orig_pte = pte_mkdirty(orig_pte);
+			for (; i < CONT_PTES; i++, ptep++, pfn++) {
+				pte = __ptep_get(ptep);
+
+				if (!contpte_is_consistent(pte, pfn, orig_prot))
+					goto retry;
+
+				if (pte_young(pte)) {
+					orig_pte = pte_mkyoung(orig_pte);
+					break;
+				}
+			}
+			break;
+		}
 
-		if (pte_young(pte))
+		if (pte_young(pte)) {
 			orig_pte = pte_mkyoung(orig_pte);
+			i++;
+			ptep++;
+			pfn++;
+			for (; i < CONT_PTES; i++, ptep++, pfn++) {
+				pte = __ptep_get(ptep);
+
+				if (!contpte_is_consistent(pte, pfn, orig_prot))
+					goto retry;
+
+				if (pte_dirty(pte)) {
+					orig_pte = pte_mkdirty(orig_pte);
+					break;
+				}
+			}
+			break;
+		}
 	}
 
 	return orig_pte;
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 11eb8d1adc84..fcc783e8e9bb 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -53,18 +53,12 @@ struct fault_info {
 };
 
 static const struct fault_info fault_info[];
-static struct fault_info debug_fault_info[];
 
 static inline const struct fault_info *esr_to_fault_info(unsigned long esr)
 {
 	return fault_info + (esr & ESR_ELx_FSC);
 }
 
-static inline const struct fault_info *esr_to_debug_fault_info(unsigned long esr)
-{
-	return debug_fault_info + DBG_ESR_EVT(esr);
-}
-
 static void data_abort_decode(unsigned long esr)
 {
 	unsigned long iss2 = ESR_ELx_ISS2(esr);
@@ -838,6 +832,7 @@ static int do_sea(unsigned long far, unsigned long esr, struct pt_regs *regs)
 		 */
 		siaddr  = untagged_addr(far);
 	}
+	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK);
 	arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr);
 
 	return 0;
@@ -849,9 +844,12 @@ static int do_tag_check_fault(unsigned long far, unsigned long esr,
 	/*
 	 * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN
 	 * for tag check faults. Set them to corresponding bits in the untagged
-	 * address.
+	 * address if ARM64_MTE_FAR isn't supported.
+	 * Otherwise, bits 63:60 of FAR_EL1 are not UNKNOWN.
 	 */
-	far = (__untagged_addr(far) & ~MTE_TAG_MASK) | (far & MTE_TAG_MASK);
+	if (!cpus_have_cap(ARM64_MTE_FAR))
+		far = (__untagged_addr(far) & ~MTE_TAG_MASK) | (far & MTE_TAG_MASK);
+
 	do_bad_area(far, esr, regs);
 	return 0;
 }
@@ -951,75 +949,6 @@ void do_sp_pc_abort(unsigned long addr, unsigned long esr, struct pt_regs *regs)
 NOKPROBE_SYMBOL(do_sp_pc_abort);
 
 /*
- * __refdata because early_brk64 is __init, but the reference to it is
- * clobbered at arch_initcall time.
- * See traps.c and debug-monitors.c:debug_traps_init().
- */
-static struct fault_info __refdata debug_fault_info[] = {
-	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware breakpoint"	},
-	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware single-step"	},
-	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware watchpoint"	},
-	{ do_bad,	SIGKILL,	SI_KERNEL,	"unknown 3"		},
-	{ do_bad,	SIGTRAP,	TRAP_BRKPT,	"aarch32 BKPT"		},
-	{ do_bad,	SIGKILL,	SI_KERNEL,	"aarch32 vector catch"	},
-	{ early_brk64,	SIGTRAP,	TRAP_BRKPT,	"aarch64 BRK"		},
-	{ do_bad,	SIGKILL,	SI_KERNEL,	"unknown 7"		},
-};
-
-void __init hook_debug_fault_code(int nr,
-				  int (*fn)(unsigned long, unsigned long, struct pt_regs *),
-				  int sig, int code, const char *name)
-{
-	BUG_ON(nr < 0 || nr >= ARRAY_SIZE(debug_fault_info));
-
-	debug_fault_info[nr].fn		= fn;
-	debug_fault_info[nr].sig	= sig;
-	debug_fault_info[nr].code	= code;
-	debug_fault_info[nr].name	= name;
-}
-
-/*
- * In debug exception context, we explicitly disable preemption despite
- * having interrupts disabled.
- * This serves two purposes: it makes it much less likely that we would
- * accidentally schedule in exception context and it will force a warning
- * if we somehow manage to schedule by accident.
- */
-static void debug_exception_enter(struct pt_regs *regs)
-{
-	preempt_disable();
-
-	/* This code is a bit fragile.  Test it. */
-	RCU_LOCKDEP_WARN(!rcu_is_watching(), "exception_enter didn't work");
-}
-NOKPROBE_SYMBOL(debug_exception_enter);
-
-static void debug_exception_exit(struct pt_regs *regs)
-{
-	preempt_enable_no_resched();
-}
-NOKPROBE_SYMBOL(debug_exception_exit);
-
-void do_debug_exception(unsigned long addr_if_watchpoint, unsigned long esr,
-			struct pt_regs *regs)
-{
-	const struct fault_info *inf = esr_to_debug_fault_info(esr);
-	unsigned long pc = instruction_pointer(regs);
-
-	debug_exception_enter(regs);
-
-	if (user_mode(regs) && !is_ttbr0_addr(pc))
-		arm64_apply_bp_hardening();
-
-	if (inf->fn(addr_if_watchpoint, esr, regs)) {
-		arm64_notify_die(inf->name, regs, inf->sig, inf->code, pc, esr);
-	}
-
-	debug_exception_exit(regs);
-}
-NOKPROBE_SYMBOL(do_debug_exception);
-
-/*
  * Used during anonymous page fault handling.
  */
 struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma,
diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c
index 5c46ec527b1c..6e93f78de79b 100644
--- a/arch/arm64/mm/gcs.c
+++ b/arch/arm64/mm/gcs.c
@@ -157,12 +157,6 @@ void gcs_free(struct task_struct *task)
 	if (!system_supports_gcs())
 		return;
 
-	/*
-	 * When fork() with CLONE_VM fails, the child (tsk) already
-	 * has a GCS allocated, and exit_thread() calls this function
-	 * to free it.  In this case the parent (current) and the
-	 * child share the same mm struct.
-	 */
 	if (!task->mm || task->mm != current->mm)
 		return;
 
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 0c8737f4f2ce..1d90a7e75333 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -225,7 +225,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 	ncontig = num_contig_ptes(sz, &pgsize);
 
 	if (!pte_present(pte)) {
-		for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
+		for (i = 0; i < ncontig; i++, ptep++)
 			__set_ptes_anysz(mm, ptep, pte, 1, pgsize);
 		return;
 	}
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 54dccfd6aa11..8c75965afc9e 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -454,7 +454,7 @@ SYM_FUNC_START(__cpu_setup)
 	dsb	nsh
 
 	msr	cpacr_el1, xzr			// Reset cpacr_el1
-	mov	x1, #1 << 12			// Reset mdscr_el1 and disable
+	mov	x1, MDSCR_EL1_TDCC		// Reset mdscr_el1 and disable
 	msr	mdscr_el1, x1			// access to the DCC from EL0
 	reset_pmuserenr_el0 x1			// Disable PMU access from EL0
 	reset_amuserenr_el0 x1			// Disable AMU access from EL0