Merge tag 'x86_urgent_for_v5.15_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Borislav Petkov:

 - Prevent a infinite loop in the MCE recovery on return to user space,
   which was caused by a second MCE queueing work for the same page and
   thereby creating a circular work list.

 - Make kern_addr_valid() handle existing PMD entries, which are marked
   not present in the higher level page table, correctly instead of
   blindly dereferencing them.

 - Pass a valid address to sanitize_phys(). This was caused by the
   mixture of inclusive and exclusive ranges. memtype_reserve() expect
   'end' being exclusive, but sanitize_phys() wants it inclusive. This
   worked so far, but with end being the end of the physical address
   space the fail is exposed.

 - Increase the maximum supported GPIO numbers for 64bit. Newer SoCs
   exceed the previous maximum.

* tag 'x86_urgent_for_v5.15_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Avoid infinite loop for copy from user recovery
  x86/mm: Fix kern_addr_valid() to cope with existing but not present entries
  x86/platform: Increase maximum GPIO number for X86_64
  x86/pat: Pass valid address to sanitize_phys()

5 files changed, 47 insertions, 15 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4e001bbbb425..dad7f85dcdea 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -339,6 +339,11 @@ config NEED_PER_CPU_PAGE_FIRST_CHUNK
 config ARCH_HIBERNATION_POSSIBLE
 	def_bool y
 
+config ARCH_NR_GPIO
+	int
+	default 1024 if X86_64
+	default 512
+
 config ARCH_SUSPEND_POSSIBLE
 	def_bool y
 
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 8cb7816d03b4..193204aee880 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1253,6 +1253,9 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin
 
 static void kill_me_now(struct callback_head *ch)
 {
+	struct task_struct *p = container_of(ch, struct task_struct, mce_kill_me);
+
+	p->mce_count = 0;
 	force_sig(SIGBUS);
 }
 
@@ -1262,6 +1265,7 @@ static void kill_me_maybe(struct callback_head *cb)
 	int flags = MF_ACTION_REQUIRED;
 	int ret;
 
+	p->mce_count = 0;
 	pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr);
 
 	if (!p->mce_ripv)
@@ -1290,17 +1294,34 @@ static void kill_me_maybe(struct callback_head *cb)
 	}
 }
 
-static void queue_task_work(struct mce *m, int kill_current_task)
+static void queue_task_work(struct mce *m, char *msg, int kill_current_task)
 {
-	current->mce_addr = m->addr;
-	current->mce_kflags = m->kflags;
-	current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV);
-	current->mce_whole_page = whole_page(m);
+	int count = ++current->mce_count;
 
-	if (kill_current_task)
-		current->mce_kill_me.func = kill_me_now;
-	else
-		current->mce_kill_me.func = kill_me_maybe;
+	/* First call, save all the details */
+	if (count == 1) {
+		current->mce_addr = m->addr;
+		current->mce_kflags = m->kflags;
+		current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV);
+		current->mce_whole_page = whole_page(m);
+
+		if (kill_current_task)
+			current->mce_kill_me.func = kill_me_now;
+		else
+			current->mce_kill_me.func = kill_me_maybe;
+	}
+
+	/* Ten is likely overkill. Don't expect more than two faults before task_work() */
+	if (count > 10)
+		mce_panic("Too many consecutive machine checks while accessing user data", m, msg);
+
+	/* Second or later call, make sure page address matches the one from first call */
+	if (count > 1 && (current->mce_addr >> PAGE_SHIFT) != (m->addr >> PAGE_SHIFT))
+		mce_panic("Consecutive machine checks to different user pages", m, msg);
+
+	/* Do not call task_work_add() more than once */
+	if (count > 1)
+		return;
 
 	task_work_add(current, &current->mce_kill_me, TWA_RESUME);
 }
@@ -1438,7 +1459,7 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		/* If this triggers there is no way to recover. Die hard. */
 		BUG_ON(!on_thread_stack() || !user_mode(regs));
 
-		queue_task_work(&m, kill_current_task);
+		queue_task_work(&m, msg, kill_current_task);
 
 	} else {
 		/*
@@ -1456,7 +1477,7 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		}
 
 		if (m.kflags & MCE_IN_KERNEL_COPYIN)
-			queue_task_work(&m, kill_current_task);
+			queue_task_work(&m, msg, kill_current_task);
 	}
 out:
 	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index a6e11763763f..36098226a957 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1432,18 +1432,18 @@ int kern_addr_valid(unsigned long addr)
 		return 0;
 
 	p4d = p4d_offset(pgd, addr);
-	if (p4d_none(*p4d))
+	if (!p4d_present(*p4d))
 		return 0;
 
 	pud = pud_offset(p4d, addr);
-	if (pud_none(*pud))
+	if (!pud_present(*pud))
 		return 0;
 
 	if (pud_large(*pud))
 		return pfn_valid(pud_pfn(*pud));
 
 	pmd = pmd_offset(pud, addr);
-	if (pmd_none(*pmd))
+	if (!pmd_present(*pmd))
 		return 0;
 
 	if (pmd_large(*pmd))
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 3112ca7786ed..4ba2a3ee4bce 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -583,7 +583,12 @@ int memtype_reserve(u64 start, u64 end, enum page_cache_mode req_type,
 	int err = 0;
 
 	start = sanitize_phys(start);
-	end = sanitize_phys(end);
+
+	/*
+	 * The end address passed into this function is exclusive, but
+	 * sanitize_phys() expects an inclusive address.
+	 */
+	end = sanitize_phys(end - 1) + 1;
 	if (start >= end) {
 		WARN(1, "%s failed: [mem %#010Lx-%#010Lx], req %s\n", __func__,
 				start, end - 1, cattr_name(req_type));
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e12b524426b0..39039ce8ac4c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1471,6 +1471,7 @@ struct task_struct {
 					mce_whole_page : 1,
 					__mce_reserved : 62;
 	struct callback_head		mce_kill_me;
+	int				mce_count;
 #endif
 
 #ifdef CONFIG_KRETPROBES