Merge tag 'v6.6-rc5' into locking/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

12 files changed, 77 insertions, 53 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 54b9387c3691..3aaadfd2c8eb 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -255,7 +255,7 @@ config PPC
 	select HAVE_KPROBES
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_KRETPROBES
-	select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if HAVE_OBJTOOL_MCOUNT
+	select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if HAVE_OBJTOOL_MCOUNT && (!ARCH_USING_PATCHABLE_FUNCTION_ENTRY || (!CC_IS_GCC || GCC_VERSION >= 110100))
 	select HAVE_LIVEPATCH			if HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI				if PERF_EVENTS || (PPC64 && PPC_BOOK3S)
diff --git a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
index de092b04ee1a..92df40c6cc6b 100644
--- a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
@@ -46,7 +46,8 @@ static inline int check_and_get_huge_psize(int shift)
 }
 
 #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte);
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		     pte_t pte, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTE_CLEAR
 static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index b8513dc3e53a..a1318ce18d0e 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -230,13 +230,15 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs)
 	struct arch_hw_breakpoint *info;
 	int i;
 
+	preempt_disable();
+
 	for (i = 0; i < nr_wp_slots(); i++) {
 		struct perf_event *bp = __this_cpu_read(bp_per_reg[i]);
 
 		if (unlikely(bp && counter_arch_bp(bp)->perf_single_step))
 			goto reset;
 	}
-	return;
+	goto out;
 
 reset:
 	regs_set_return_msr(regs, regs->msr & ~MSR_SE);
@@ -245,6 +247,9 @@ reset:
 		__set_breakpoint(i, info);
 		info->perf_single_step = false;
 	}
+
+out:
+	preempt_enable();
 }
 
 static bool is_larx_stcx_instr(int type)
@@ -363,6 +368,11 @@ static void handle_p10dd1_spurious_exception(struct perf_event **bp,
 	}
 }
 
+/*
+ * Handle a DABR or DAWR exception.
+ *
+ * Called in atomic context.
+ */
 int hw_breakpoint_handler(struct die_args *args)
 {
 	bool err = false;
@@ -490,6 +500,8 @@ NOKPROBE_SYMBOL(hw_breakpoint_handler);
 
 /*
  * Handle single-step exceptions following a DABR hit.
+ *
+ * Called in atomic context.
  */
 static int single_step_dabr_instruction(struct die_args *args)
 {
@@ -541,6 +553,8 @@ NOKPROBE_SYMBOL(single_step_dabr_instruction);
 
 /*
  * Handle debug exception notifications.
+ *
+ * Called in atomic context.
  */
 int hw_breakpoint_exceptions_notify(
 		struct notifier_block *unused, unsigned long val, void *data)
diff --git a/arch/powerpc/kernel/hw_breakpoint_constraints.c b/arch/powerpc/kernel/hw_breakpoint_constraints.c
index a74623025f3a..9e51801c4915 100644
--- a/arch/powerpc/kernel/hw_breakpoint_constraints.c
+++ b/arch/powerpc/kernel/hw_breakpoint_constraints.c
@@ -131,8 +131,13 @@ void wp_get_instr_detail(struct pt_regs *regs, ppc_inst_t *instr,
 			 int *type, int *size, unsigned long *ea)
 {
 	struct instruction_op op;
+	int err;
 
-	if (__get_user_instr(*instr, (void __user *)regs->nip))
+	pagefault_disable();
+	err = __get_user_instr(*instr, (void __user *)regs->nip);
+	pagefault_enable();
+
+	if (err)
 		return;
 
 	analyse_instr(&op, regs, *instr);
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index b15f15dcacb5..e6a958a5da27 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -73,29 +73,12 @@ int __no_sanitize_address arch_stack_walk_reliable(stack_trace_consume_fn consum
 	bool firstframe;
 
 	stack_end = stack_page + THREAD_SIZE;
-	if (!is_idle_task(task)) {
-		/*
-		 * For user tasks, this is the SP value loaded on
-		 * kernel entry, see "PACAKSAVE(r13)" in _switch() and
-		 * system_call_common().
-		 *
-		 * Likewise for non-swapper kernel threads,
-		 * this also happens to be the top of the stack
-		 * as setup by copy_thread().
-		 *
-		 * Note that stack backlinks are not properly setup by
-		 * copy_thread() and thus, a forked task() will have
-		 * an unreliable stack trace until it's been
-		 * _switch()'ed to for the first time.
-		 */
-		stack_end -= STACK_USER_INT_FRAME_SIZE;
-	} else {
-		/*
-		 * idle tasks have a custom stack layout,
-		 * c.f. cpu_idle_thread_init().
-		 */
+
+	// See copy_thread() for details.
+	if (task->flags & PF_KTHREAD)
 		stack_end -= STACK_FRAME_MIN_SIZE;
-	}
+	else
+		stack_end -= STACK_USER_INT_FRAME_SIZE;
 
 	if (task == current)
 		sp = current_stack_frame();
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index eeff136b83d9..64ff37721fd0 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1512,23 +1512,11 @@ static void do_program_check(struct pt_regs *regs)
 			return;
 		}
 
-		if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE) && user_mode(regs)) {
-			ppc_inst_t insn;
-
-			if (get_user_instr(insn, (void __user *)regs->nip)) {
-				_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
-				return;
-			}
-
-			if (ppc_inst_primary_opcode(insn) == 31 &&
-			    get_xop(ppc_inst_val(insn)) == OP_31_XOP_HASHCHK) {
-				_exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
-				return;
-			}
+		/* User mode considers other cases after enabling IRQs */
+		if (!user_mode(regs)) {
+			_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
+			return;
 		}
-
-		_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
-		return;
 	}
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	if (reason & REASON_TM) {
@@ -1561,16 +1549,44 @@ static void do_program_check(struct pt_regs *regs)
 
 	/*
 	 * If we took the program check in the kernel skip down to sending a
-	 * SIGILL. The subsequent cases all relate to emulating instructions
-	 * which we should only do for userspace. We also do not want to enable
-	 * interrupts for kernel faults because that might lead to further
-	 * faults, and loose the context of the original exception.
+	 * SIGILL. The subsequent cases all relate to user space, such as
+	 * emulating instructions which we should only do for user space. We
+	 * also do not want to enable interrupts for kernel faults because that
+	 * might lead to further faults, and loose the context of the original
+	 * exception.
 	 */
 	if (!user_mode(regs))
 		goto sigill;
 
 	interrupt_cond_local_irq_enable(regs);
 
+	/*
+	 * (reason & REASON_TRAP) is mostly handled before enabling IRQs,
+	 * except get_user_instr() can sleep so we cannot reliably inspect the
+	 * current instruction in that context. Now that we know we are
+	 * handling a user space trap and can sleep, we can check if the trap
+	 * was a hashchk failure.
+	 */
+	if (reason & REASON_TRAP) {
+		if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) {
+			ppc_inst_t insn;
+
+			if (get_user_instr(insn, (void __user *)regs->nip)) {
+				_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
+				return;
+			}
+
+			if (ppc_inst_primary_opcode(insn) == 31 &&
+			    get_xop(ppc_inst_val(insn)) == OP_31_XOP_HASHCHK) {
+				_exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
+				return;
+			}
+		}
+
+		_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
+		return;
+	}
+
 	/* (reason & REASON_ILLEGAL) would be the obvious thing here,
 	 * but there seems to be a hardware bug on the 405GP (RevD)
 	 * that means ESR is sometimes set incorrectly - either to
diff --git a/arch/powerpc/mm/book3s64/hugetlbpage.c b/arch/powerpc/mm/book3s64/hugetlbpage.c
index 3bc0eb21b2a0..5a2e512e96db 100644
--- a/arch/powerpc/mm/book3s64/hugetlbpage.c
+++ b/arch/powerpc/mm/book3s64/hugetlbpage.c
@@ -143,11 +143,14 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
 void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 				  pte_t *ptep, pte_t old_pte, pte_t pte)
 {
+	unsigned long psize;
 
 	if (radix_enabled())
 		return radix__huge_ptep_modify_prot_commit(vma, addr, ptep,
 							   old_pte, pte);
-	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+
+	psize = huge_page_size(hstate_vma(vma));
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
 }
 
 void __init hugetlbpage_init_defaultsize(void)
diff --git a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
index 17075c78d4bc..35fd2a95be24 100644
--- a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
+++ b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
@@ -47,6 +47,7 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 					 pte_t old_pte, pte_t pte)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	unsigned long psize = huge_page_size(hstate_vma(vma));
 
 	/*
 	 * POWER9 NMMU must flush the TLB after clearing the PTE before
@@ -58,5 +59,5 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 	    atomic_read(&mm->context.copros) > 0)
 		radix__flush_hugetlb_page(vma, addr);
 
-	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
 }
diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c
index dbbfe897455d..a642a7929892 100644
--- a/arch/powerpc/mm/nohash/8xx.c
+++ b/arch/powerpc/mm/nohash/8xx.c
@@ -91,7 +91,8 @@ static int __ref __early_map_kernel_hugepage(unsigned long va, phys_addr_t pa,
 	if (new && WARN_ON(pte_present(*ptep) && pgprot_val(prot)))
 		return -EINVAL;
 
-	set_huge_pte_at(&init_mm, va, ptep, pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)));
+	set_huge_pte_at(&init_mm, va, ptep,
+			pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)), psize);
 
 	return 0;
 }
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 3f86fd217690..3ba9fe411604 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -288,7 +288,8 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 }
 
 #if defined(CONFIG_PPC_8xx)
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		     pte_t pte, unsigned long sz)
 {
 	pmd_t *pmd = pmd_off(mm, addr);
 	pte_basic_t val;
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 317175791d23..3449be7c0d51 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -1418,7 +1418,7 @@ static int h_24x7_event_init(struct perf_event *event)
 	}
 
 	domain = event_get_domain(event);
-	if (domain >= HV_PERF_DOMAIN_MAX) {
+	if (domain  == 0 || domain >= HV_PERF_DOMAIN_MAX) {
 		pr_devel("invalid domain %d\n", domain);
 		return -EINVAL;
 	}
diff --git a/arch/powerpc/platforms/82xx/Kconfig b/arch/powerpc/platforms/82xx/Kconfig
index d9f1a2a83158..1824536cf6f2 100644
--- a/arch/powerpc/platforms/82xx/Kconfig
+++ b/arch/powerpc/platforms/82xx/Kconfig
@@ -2,6 +2,7 @@
 menuconfig PPC_82xx
 	bool "82xx-based boards (PQ II)"
 	depends on PPC_BOOK3S_32
+	select FSL_SOC
 
 if PPC_82xx
 
@@ -9,7 +10,6 @@ config EP8248E
 	bool "Embedded Planet EP8248E (a.k.a. CWH-PPC-8248N-VE)"
 	select CPM2
 	select PPC_INDIRECT_PCI if PCI
-	select FSL_SOC
 	select PHYLIB if NETDEVICES
 	select MDIO_BITBANG if PHYLIB
 	help
@@ -22,7 +22,6 @@ config MGCOGE
 	bool "Keymile MGCOGE"
 	select CPM2
 	select PPC_INDIRECT_PCI if PCI
-	select FSL_SOC
 	help
 	  This enables support for the Keymile MGCOGE board.