Merge tag 'kvm-s390-master-4.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

KVM: s390: Fixes for kvm/master (targeting 4.5)

1. Fallout of some bigger floating point/vector rework in s390
- memory leak -> stable 4.3+
- memory overwrite -> stable 4.4+

2. enable KVM-VFIO for s390

3 files changed, 71 insertions, 28 deletions

diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index a5cd40cd8ee1..f9cf1223422c 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -84,4 +84,7 @@
 #define SO_ATTACH_BPF		0x402B
 #define SO_DETACH_BPF		SO_DETACH_FILTER
 
+#define SO_ATTACH_REUSEPORT_CBPF	0x402C
+#define SO_ATTACH_REUSEPORT_EBPF	0x402D
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c
index 3c63a820fcda..b9d75d9fa9ac 100644
--- a/arch/parisc/kernel/module.c
+++ b/arch/parisc/kernel/module.c
@@ -42,9 +42,9 @@
  *      We are not doing SEGREL32 handling correctly. According to the ABI, we
  *      should do a value offset, like this:
  *			if (in_init(me, (void *)val))
- *				val -= (uint32_t)me->module_init;
+ *				val -= (uint32_t)me->init_layout.base;
  *			else
- *				val -= (uint32_t)me->module_core;
+ *				val -= (uint32_t)me->core_layout.base;
  *	However, SEGREL32 is used only for PARISC unwind entries, and we want
  *	those entries to have an absolute address, and not just an offset.
  *
@@ -100,14 +100,14 @@
  * or init pieces the location is */
 static inline int in_init(struct module *me, void *loc)
 {
-	return (loc >= me->module_init &&
-		loc <= (me->module_init + me->init_size));
+	return (loc >= me->init_layout.base &&
+		loc <= (me->init_layout.base + me->init_layout.size));
 }
 
 static inline int in_core(struct module *me, void *loc)
 {
-	return (loc >= me->module_core &&
-		loc <= (me->module_core + me->core_size));
+	return (loc >= me->core_layout.base &&
+		loc <= (me->core_layout.base + me->core_layout.size));
 }
 
 static inline int in_local(struct module *me, void *loc)
@@ -367,13 +367,13 @@ int module_frob_arch_sections(CONST Elf_Ehdr *hdr,
 	}
 
 	/* align things a bit */
-	me->core_size = ALIGN(me->core_size, 16);
-	me->arch.got_offset = me->core_size;
-	me->core_size += gots * sizeof(struct got_entry);
+	me->core_layout.size = ALIGN(me->core_layout.size, 16);
+	me->arch.got_offset = me->core_layout.size;
+	me->core_layout.size += gots * sizeof(struct got_entry);
 
-	me->core_size = ALIGN(me->core_size, 16);
-	me->arch.fdesc_offset = me->core_size;
-	me->core_size += fdescs * sizeof(Elf_Fdesc);
+	me->core_layout.size = ALIGN(me->core_layout.size, 16);
+	me->arch.fdesc_offset = me->core_layout.size;
+	me->core_layout.size += fdescs * sizeof(Elf_Fdesc);
 
 	me->arch.got_max = gots;
 	me->arch.fdesc_max = fdescs;
@@ -391,7 +391,7 @@ static Elf64_Word get_got(struct module *me, unsigned long value, long addend)
 
 	BUG_ON(value == 0);
 
-	got = me->module_core + me->arch.got_offset;
+	got = me->core_layout.base + me->arch.got_offset;
 	for (i = 0; got[i].addr; i++)
 		if (got[i].addr == value)
 			goto out;
@@ -409,7 +409,7 @@ static Elf64_Word get_got(struct module *me, unsigned long value, long addend)
 #ifdef CONFIG_64BIT
 static Elf_Addr get_fdesc(struct module *me, unsigned long value)
 {
-	Elf_Fdesc *fdesc = me->module_core + me->arch.fdesc_offset;
+	Elf_Fdesc *fdesc = me->core_layout.base + me->arch.fdesc_offset;
 
 	if (!value) {
 		printk(KERN_ERR "%s: zero OPD requested!\n", me->name);
@@ -427,7 +427,7 @@ static Elf_Addr get_fdesc(struct module *me, unsigned long value)
 
 	/* Create new one */
 	fdesc->addr = value;
-	fdesc->gp = (Elf_Addr)me->module_core + me->arch.got_offset;
+	fdesc->gp = (Elf_Addr)me->core_layout.base + me->arch.got_offset;
 	return (Elf_Addr)fdesc;
 }
 #endif /* CONFIG_64BIT */
@@ -839,7 +839,7 @@ register_unwind_table(struct module *me,
 
 	table = (unsigned char *)sechdrs[me->arch.unwind_section].sh_addr;
 	end = table + sechdrs[me->arch.unwind_section].sh_size;
-	gp = (Elf_Addr)me->module_core + me->arch.got_offset;
+	gp = (Elf_Addr)me->core_layout.base + me->arch.got_offset;
 
 	DEBUGP("register_unwind_table(), sect = %d at 0x%p - 0x%p (gp=0x%lx)\n",
 	       me->arch.unwind_section, table, end, gp);
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index dc1ea796fd60..2264f68f3c2f 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -435,6 +435,55 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs, int in_syscall)
 		regs->gr[28]);
 }
 
+/*
+ * Check how the syscall number gets loaded into %r20 within
+ * the delay branch in userspace and adjust as needed.
+ */
+
+static void check_syscallno_in_delay_branch(struct pt_regs *regs)
+{
+	u32 opcode, source_reg;
+	u32 __user *uaddr;
+	int err;
+
+	/* Usually we don't have to restore %r20 (the system call number)
+	 * because it gets loaded in the delay slot of the branch external
+	 * instruction via the ldi instruction.
+	 * In some cases a register-to-register copy instruction might have
+	 * been used instead, in which case we need to copy the syscall
+	 * number into the source register before returning to userspace.
+	 */
+
+	/* A syscall is just a branch, so all we have to do is fiddle the
+	 * return pointer so that the ble instruction gets executed again.
+	 */
+	regs->gr[31] -= 8; /* delayed branching */
+
+	/* Get assembler opcode of code in delay branch */
+	uaddr = (unsigned int *) ((regs->gr[31] & ~3) + 4);
+	err = get_user(opcode, uaddr);
+	if (err)
+		return;
+
+	/* Check if delay branch uses "ldi int,%r20" */
+	if ((opcode & 0xffff0000) == 0x34140000)
+		return;	/* everything ok, just return */
+
+	/* Check if delay branch uses "nop" */
+	if (opcode == INSN_NOP)
+		return;
+
+	/* Check if delay branch uses "copy %rX,%r20" */
+	if ((opcode & 0xffe0ffff) == 0x08000254) {
+		source_reg = (opcode >> 16) & 31;
+		regs->gr[source_reg] = regs->gr[20];
+		return;
+	}
+
+	pr_warn("syscall restart: %s (pid %d): unexpected opcode 0x%08x\n",
+		current->comm, task_pid_nr(current), opcode);
+}
+
 static inline void
 syscall_restart(struct pt_regs *regs, struct k_sigaction *ka)
 {
@@ -457,10 +506,7 @@ syscall_restart(struct pt_regs *regs, struct k_sigaction *ka)
 		}
 		/* fallthrough */
 	case -ERESTARTNOINTR:
-		/* A syscall is just a branch, so all
-		 * we have to do is fiddle the return pointer.
-		 */
-		regs->gr[31] -= 8; /* delayed branching */
+		check_syscallno_in_delay_branch(regs);
 		break;
 	}
 }
@@ -510,15 +556,9 @@ insert_restart_trampoline(struct pt_regs *regs)
 	}
 	case -ERESTARTNOHAND:
 	case -ERESTARTSYS:
-	case -ERESTARTNOINTR: {
-		/* Hooray for delayed branching.  We don't
-		 * have to restore %r20 (the system call
-		 * number) because it gets loaded in the delay
-		 * slot of the branch external instruction.
-		 */
-		regs->gr[31] -= 8;
+	case -ERESTARTNOINTR:
+		check_syscallno_in_delay_branch(regs);
 		return;
-	}
 	default:
 		break;
 	}