Merge tag 's390-6.10-2' of git://git.kernel.org/pub/scm/linux/kernel/…

…git/s390/linux

Pull more s390 updates from Alexander Gordeev:

 - Switch read and write software bits for PUDs

 - Add missing hardware bits for PUDs and PMDs

 - Generate unwind information for C modules to fix GDB unwind error for
   vDSO functions

 - Create .build-id links for unstripped vDSO files to enable vDSO
   debugging with symbols

 - Use standard stack frame layout for vDSO generated stack frames to
   manually walk stack frames without DWARF information

 - Rework perf_callchain_user() and arch_stack_walk_user() functions to
   reduce code duplication

 - Skip first stack frame when walking user stack

 - Add basic checks to identify invalid instruction pointers when
   walking stack frames

 - Introduce and use struct stack_frame_vdso_wrapper within vDSO user
   wrapper code to automatically generate an asm-offset define. Also use
   STACK_FRAME_USER_OVERHEAD instead of STACK_FRAME_OVERHEAD to document
   that the code works with user space stack

 - Clear the backchain of the extra stack frame added by the vDSO user
   wrapper code. This allows the user stack walker to detect and skip
   the non-standard stack frame. Without this an incorrect instruction
   pointer would be added to stack traces.

 - Rewrite psw_idle() function in C to ease maintenance and further
   enhancements

 - Remove get_vtimer() function and use get_cpu_timer() instead

 - Mark psw variable in __load_psw_mask() as __unitialized to avoid
   superfluous clearing of PSW

 - Remove obsolete and superfluous comment about removed TIF_FPU flag

 - Replace memzero_explicit() and kfree() with kfree_sensitive() to fix
   warnings reported by Coccinelle

 - Wipe sensitive data and all copies of protected- or secure-keys from
   stack when an IOCTL fails

 - Both do_airq_interrupt() and do_io_interrupt() functions set
   CIF_NOHZ_DELAY flag. Move it in do_io_irq() to simplify the code

 - Provide iucv_alloc_device() and iucv_release_device() helpers, which
   can be used to deduplicate more or less identical IUCV device
   allocation and release code in four different drivers

 - Make use of iucv_alloc_device() and iucv_release_device() helpers to
   get rid of quite some code and also remove a cast to an incompatible
   function (clang W=1)

 - There is no user of iucv_root outside of the core IUCV code left.
   Therefore remove the EXPORT_SYMBOL

 - __apply_alternatives() contains a runtime check which verifies that
   the size of the to be patched code area is even. Convert this to a
   compile time check

 - Increase size of buffers for sending z/VM CP DIAGNOSE X'008' commands
   from 128 to 240

 - Do not accept z/VM CP DIAGNOSE X'008' commands longer than maximally
   allowed

 - Use correct defines IPL_BP_NVME_LEN and IPL_BP0_NVME_LEN instead of
   IPL_BP_FCP_LEN and IPL_BP0_FCP_LEN ones to initialize NVMe reIPL
   block on 'scp_data' sysfs attribute update

 - Initialize the correct fields of the NVMe dump block, which were
   confused with FCP fields

 - Refactor macros for 'scp_data' (re-)IPL sysfs attribute to reduce
   code duplication

 - Introduce 'scp_data' sysfs attribute for dump IPL to allow tools such
   as dumpconf passing additional kernel command line parameters to a
   stand-alone dumper

 - Rework the CPACF query functions to use the correct RRE or RRF
   instruction formats and set instruction register fields correctly

 - Instead of calling BUG() at runtime force a link error during compile
   when a unsupported opcode is used with __cpacf_query() or
   __cpacf_check_opcode() functions

 - Fix a crash in ap_parse_bitmap_str() function on /sys/bus/ap/apmask
   or /sys/bus/ap/aqmask sysfs file update with a relative mask value

 - Fix "bindings complete" udev event which should be sent once all AP
   devices have been bound to device drivers and again when unbind/bind
   actions take place and all AP devices are bound again

 - Facility list alt_stfle_fac_list is nowhere used in the decompressor,
   therefore remove it there

 - Remove custom kprobes insn slot allocator in favour of the standard
   module_alloc() one, since kernel image and module areas are located
   within 4GB

 - Use kvcalloc() instead of kvmalloc_array() in zcrypt driver to avoid
   calling memset() with a large byte count and get rid of the sparse
   warning as result

* tag 's390-6.10-2' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (39 commits)
  s390/zcrypt: Use kvcalloc() instead of kvmalloc_array()
  s390/kprobes: Remove custom insn slot allocator
  s390/boot: Remove alt_stfle_fac_list from decompressor
  s390/ap: Fix bind complete udev event sent after each AP bus scan
  s390/ap: Fix crash in AP internal function modify_bitmap()
  s390/cpacf: Make use of invalid opcode produce a link error
  s390/cpacf: Split and rework cpacf query functions
  s390/ipl: Introduce sysfs attribute 'scp_data' for dump ipl
  s390/ipl: Introduce macros for (re)ipl sysfs attribute 'scp_data'
  s390/ipl: Fix incorrect initialization of nvme dump block
  s390/ipl: Fix incorrect initialization of len fields in nvme reipl block
  s390/ipl: Do not accept z/VM CP diag X'008' cmds longer than max length
  s390/ipl: Fix size of vmcmd buffers for sending z/VM CP diag X'008' cmds
  s390/alternatives: Convert runtime sanity check into compile time check
  s390/iucv: Unexport iucv_root
  tty: hvc-iucv: Make use of iucv_alloc_device()
  s390/smsgiucv_app: Make use of iucv_alloc_device()
  s390/netiucv: Make use of iucv_alloc_device()
  s390/vmlogrdr: Make use of iucv_alloc_device()
  s390/iucv: Provide iucv_alloc_device() / iucv_release_device()
  ...

arch/s390/boot/startup.c

@@ -32,7 +32,6 @@ unsigned long __bootdata_preserved(MODULES_END);
 unsigned long __bootdata_preserved(max_mappable);
 
 u64 __bootdata_preserved(stfle_fac_list[16]);
-u64 __bootdata_preserved(alt_stfle_fac_list[16]);
 struct oldmem_data __bootdata_preserved(oldmem_data);
 
 struct machine_info machine;

arch/s390/include/asm/alternative-asm.h

@@ -15,6 +15,7 @@
 	.long	\alt_start - .
 	.word	\feature
 	.byte	\orig_end - \orig_start
+	.org	. - ( \orig_end - \orig_start ) & 1
 	.org	. - ( \orig_end - \orig_start ) + ( \alt_end - \alt_start )
 	.org	. - ( \alt_end - \alt_start ) + ( \orig_end - \orig_start )
 .endm

arch/s390/include/asm/alternative.h

@@ -53,6 +53,7 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
 	"\t.long " b_altinstr(num)"b - .\n"	/* alt instruction */	\
 	"\t.word " __stringify(facility) "\n"	/* facility bit    */	\
 	"\t.byte " oldinstr_len "\n"		/* instruction len */	\
+	"\t.org . - (" oldinstr_len ") & 1\n"				\
 	"\t.org . - (" oldinstr_len ") + (" altinstr_len(num) ")\n"	\
 	"\t.org . - (" altinstr_len(num) ") + (" oldinstr_len ")\n"
 

arch/s390/include/asm/cpacf.h

@@ -166,28 +166,86 @@
 
 typedef struct { unsigned char bytes[16]; } cpacf_mask_t;
 
-/**
- * cpacf_query() - check if a specific CPACF function is available
- * @opcode: the opcode of the crypto instruction
- * @func: the function code to test for
- *
- * Executes the query function for the given crypto instruction @opcode
- * and checks if @func is available
- *
- * Returns 1 if @func is available for @opcode, 0 otherwise
+/*
+ * Prototype for a not existing function to produce a link
+ * error if __cpacf_query() or __cpacf_check_opcode() is used
+ * with an invalid compile time const opcode.
  */
-static __always_inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask)
+void __cpacf_bad_opcode(void);
+
+static __always_inline void __cpacf_query_rre(u32 opc, u8 r1, u8 r2,
+					      cpacf_mask_t *mask)
 {
 	asm volatile(
-		"	lghi	0,0\n" /* query function */
-		"	lgr	1,%[mask]\n"
-		"	spm	0\n" /* pckmo doesn't change the cc */
-		/* Parameter regs are ignored, but must be nonzero and unique */
-		"0:	.insn	rrf,%[opc] << 16,2,4,6,0\n"
-		"	brc	1,0b\n"	/* handle partial completion */
-		: "=m" (*mask)
-		: [mask] "d" ((unsigned long)mask), [opc] "i" (opcode)
-		: "cc", "0", "1");
+		"	la	%%r1,%[mask]\n"
+		"	xgr	%%r0,%%r0\n"
+		"	.insn	rre,%[opc] << 16,%[r1],%[r2]\n"
+		: [mask] "=R" (*mask)
+		: [opc] "i" (opc),
+		  [r1] "i" (r1), [r2] "i" (r2)
+		: "cc", "r0", "r1");
+}
+
+static __always_inline void __cpacf_query_rrf(u32 opc,
+					      u8 r1, u8 r2, u8 r3, u8 m4,
+					      cpacf_mask_t *mask)
+{
+	asm volatile(
+		"	la	%%r1,%[mask]\n"
+		"	xgr	%%r0,%%r0\n"
+		"	.insn	rrf,%[opc] << 16,%[r1],%[r2],%[r3],%[m4]\n"
+		: [mask] "=R" (*mask)
+		: [opc] "i" (opc), [r1] "i" (r1), [r2] "i" (r2),
+		  [r3] "i" (r3), [m4] "i" (m4)
+		: "cc", "r0", "r1");
+}
+
+static __always_inline void __cpacf_query(unsigned int opcode,
+					  cpacf_mask_t *mask)
+{
+	switch (opcode) {
+	case CPACF_KDSA:
+		__cpacf_query_rre(CPACF_KDSA, 0, 2, mask);
+		break;
+	case CPACF_KIMD:
+		__cpacf_query_rre(CPACF_KIMD, 0, 2, mask);
+		break;
+	case CPACF_KLMD:
+		__cpacf_query_rre(CPACF_KLMD, 0, 2, mask);
+		break;
+	case CPACF_KM:
+		__cpacf_query_rre(CPACF_KM, 2, 4, mask);
+		break;
+	case CPACF_KMA:
+		__cpacf_query_rrf(CPACF_KMA, 2, 4, 6, 0, mask);
+		break;
+	case CPACF_KMAC:
+		__cpacf_query_rre(CPACF_KMAC, 0, 2, mask);
+		break;
+	case CPACF_KMC:
+		__cpacf_query_rre(CPACF_KMC, 2, 4, mask);
+		break;
+	case CPACF_KMCTR:
+		__cpacf_query_rrf(CPACF_KMCTR, 2, 4, 6, 0, mask);
+		break;
+	case CPACF_KMF:
+		__cpacf_query_rre(CPACF_KMF, 2, 4, mask);
+		break;
+	case CPACF_KMO:
+		__cpacf_query_rre(CPACF_KMO, 2, 4, mask);
+		break;
+	case CPACF_PCC:
+		__cpacf_query_rre(CPACF_PCC, 0, 0, mask);
+		break;
+	case CPACF_PCKMO:
+		__cpacf_query_rre(CPACF_PCKMO, 0, 0, mask);
+		break;
+	case CPACF_PRNO:
+		__cpacf_query_rre(CPACF_PRNO, 2, 4, mask);
+		break;
+	default:
+		__cpacf_bad_opcode();
+	}
 }
 
 static __always_inline int __cpacf_check_opcode(unsigned int opcode)
@@ -211,10 +269,21 @@ static __always_inline int __cpacf_check_opcode(unsigned int opcode)
 	case CPACF_KMA:
 		return test_facility(146);	/* check for MSA8 */
 	default:
-		BUG();
+		__cpacf_bad_opcode();
+		return 0;
 	}
 }
 
+/**
+ * cpacf_query() - check if a specific CPACF function is available
+ * @opcode: the opcode of the crypto instruction
+ * @func: the function code to test for
+ *
+ * Executes the query function for the given crypto instruction @opcode
+ * and checks if @func is available
+ *
+ * Returns 1 if @func is available for @opcode, 0 otherwise
+ */
 static __always_inline int cpacf_query(unsigned int opcode, cpacf_mask_t *mask)
 {
 	if (__cpacf_check_opcode(opcode)) {

arch/s390/include/asm/pgtable.h

@@ -268,12 +268,14 @@ static inline int is_module_addr(void *addr)
 #define _REGION3_ENTRY		(_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_LENGTH)
 #define _REGION3_ENTRY_EMPTY	(_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID)
 
+#define _REGION3_ENTRY_HARDWARE_BITS		0xfffffffffffff6ffUL
+#define _REGION3_ENTRY_HARDWARE_BITS_LARGE	0xffffffff8001073cUL
 #define _REGION3_ENTRY_ORIGIN_LARGE ~0x7fffffffUL /* large page address	     */
 #define _REGION3_ENTRY_DIRTY	0x2000	/* SW region dirty bit */
 #define _REGION3_ENTRY_YOUNG	0x1000	/* SW region young bit */
 #define _REGION3_ENTRY_LARGE	0x0400	/* RTTE-format control, large page  */
-#define _REGION3_ENTRY_READ	0x0002	/* SW region read bit */
-#define _REGION3_ENTRY_WRITE	0x0001	/* SW region write bit */
+#define _REGION3_ENTRY_WRITE	0x0002	/* SW region write bit */
+#define _REGION3_ENTRY_READ	0x0001	/* SW region read bit */
 
 #ifdef CONFIG_MEM_SOFT_DIRTY
 #define _REGION3_ENTRY_SOFT_DIRTY 0x4000 /* SW region soft dirty bit */
@@ -284,9 +286,9 @@ static inline int is_module_addr(void *addr)
 #define _REGION_ENTRY_BITS	 0xfffffffffffff22fUL
 
 /* Bits in the segment table entry */
-#define _SEGMENT_ENTRY_BITS			0xfffffffffffffe33UL
-#define _SEGMENT_ENTRY_HARDWARE_BITS		0xfffffffffffffe30UL
-#define _SEGMENT_ENTRY_HARDWARE_BITS_LARGE	0xfffffffffff00730UL
+#define _SEGMENT_ENTRY_BITS			0xfffffffffffffe3fUL
+#define _SEGMENT_ENTRY_HARDWARE_BITS		0xfffffffffffffe3cUL
+#define _SEGMENT_ENTRY_HARDWARE_BITS_LARGE	0xfffffffffff1073cUL
 #define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address	    */
 #define _SEGMENT_ENTRY_ORIGIN	~0x7ffUL/* page table origin		    */
 #define _SEGMENT_ENTRY_PROTECT	0x200	/* segment protection bit	    */

arch/s390/include/asm/processor.h

@@ -40,6 +40,7 @@
 #include <asm/setup.h>
 #include <asm/runtime_instr.h>
 #include <asm/irqflags.h>
+#include <asm/alternative.h>
 
 typedef long (*sys_call_ptr_t)(struct pt_regs *regs);
 
@@ -92,12 +93,21 @@ static inline void get_cpu_id(struct cpuid *ptr)
 	asm volatile("stidp %0" : "=Q" (*ptr));
 }
 
+static __always_inline unsigned long get_cpu_timer(void)
+{
+	unsigned long timer;
+
+	asm volatile("stpt	%[timer]" : [timer] "=Q" (timer));
+	return timer;
+}
+
 void s390_adjust_jiffies(void);
 void s390_update_cpu_mhz(void);
 void cpu_detect_mhz_feature(void);
 
 extern const struct seq_operations cpuinfo_op;
 extern void execve_tail(void);
+unsigned long vdso_text_size(void);
 unsigned long vdso_size(void);
 
 /*
@@ -304,8 +314,8 @@ static inline void __load_psw(psw_t psw)
  */
 static __always_inline void __load_psw_mask(unsigned long mask)
 {
+	psw_t psw __uninitialized;
 	unsigned long addr;
-	psw_t psw;
 
 	psw.mask = mask;
 
@@ -393,6 +403,11 @@ static __always_inline bool regs_irqs_disabled(struct pt_regs *regs)
 	return arch_irqs_disabled_flags(regs->psw.mask);
 }
 
+static __always_inline void bpon(void)
+{
+	asm volatile(ALTERNATIVE("nop", ".insn	rrf,0xb2e80000,0,0,13,0", 82));
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __ASM_S390_PROCESSOR_H */

arch/s390/include/asm/stacktrace.h

@@ -2,6 +2,7 @@
 #ifndef _ASM_S390_STACKTRACE_H
 #define _ASM_S390_STACKTRACE_H
 
+#include <linux/stacktrace.h>
 #include <linux/uaccess.h>
 #include <linux/ptrace.h>
 
@@ -12,6 +13,17 @@ struct stack_frame_user {
 	unsigned long empty2[4];
 };
 
+struct stack_frame_vdso_wrapper {
+	struct stack_frame_user sf;
+	unsigned long return_address;
+};
+
+struct perf_callchain_entry_ctx;
+
+void arch_stack_walk_user_common(stack_trace_consume_fn consume_entry, void *cookie,
+				 struct perf_callchain_entry_ctx *entry,
+				 const struct pt_regs *regs, bool perf);
+
 enum stack_type {
 	STACK_TYPE_UNKNOWN,
 	STACK_TYPE_TASK,

arch/s390/kernel/Makefile

@@ -59,7 +59,6 @@ obj-$(CONFIG_COMPAT)		+= compat_linux.o compat_signal.o
 obj-$(CONFIG_COMPAT)		+= $(compat-obj-y)
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
-obj-$(CONFIG_KPROBES)		+= kprobes_insn_page.o
 obj-$(CONFIG_KPROBES)		+= mcount.o
 obj-$(CONFIG_RETHOOK)		+= rethook.o
 obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace.o

arch/s390/kernel/alternative.c

@@ -33,13 +33,6 @@ static void __init_or_module __apply_alternatives(struct alt_instr *start,
 
 		if (!__test_facility(a->facility, alt_stfle_fac_list))
 			continue;
-
-		if (unlikely(a->instrlen % 2)) {
-			WARN_ONCE(1, "cpu alternatives instructions length is "
-				     "odd, skipping patching\n");
-			continue;
-		}
-
 		s390_kernel_write(instr, replacement, a->instrlen);
 	}
 }

arch/s390/kernel/asm-offsets.c

@@ -13,7 +13,6 @@
 #include <linux/purgatory.h>
 #include <linux/pgtable.h>
 #include <linux/ftrace.h>
-#include <asm/idle.h>
 #include <asm/gmap.h>
 #include <asm/stacktrace.h>
 
@@ -66,10 +65,10 @@ int main(void)
 	OFFSET(__SF_SIE_CONTROL_PHYS, stack_frame, sie_control_block_phys);
 	DEFINE(STACK_FRAME_OVERHEAD, sizeof(struct stack_frame));
 	BLANK();
-	/* idle data offsets */
-	OFFSET(__CLOCK_IDLE_ENTER, s390_idle_data, clock_idle_enter);
-	OFFSET(__TIMER_IDLE_ENTER, s390_idle_data, timer_idle_enter);
-	OFFSET(__MT_CYCLES_ENTER, s390_idle_data, mt_cycles_enter);
+	OFFSET(__SFUSER_BACKCHAIN, stack_frame_user, back_chain);
+	DEFINE(STACK_FRAME_USER_OVERHEAD, sizeof(struct stack_frame_user));
+	OFFSET(__SFVDSO_RETURN_ADDRESS, stack_frame_vdso_wrapper, return_address);
+	DEFINE(STACK_FRAME_VDSO_OVERHEAD, sizeof(struct stack_frame_vdso_wrapper));
 	BLANK();
 	/* hardware defined lowcore locations 0x000 - 0x1ff */
 	OFFSET(__LC_EXT_PARAMS, lowcore, ext_params);

arch/s390/kernel/entry.S

@@ -440,29 +440,6 @@ SYM_CODE_END(\name)
 INT_HANDLER ext_int_handler,__LC_EXT_OLD_PSW,do_ext_irq
 INT_HANDLER io_int_handler,__LC_IO_OLD_PSW,do_io_irq
 
-/*
- * Load idle PSW.
- */
-SYM_FUNC_START(psw_idle)
-	stg	%r14,(__SF_GPRS+8*8)(%r15)
-	stg	%r3,__SF_EMPTY(%r15)
-	larl	%r1,psw_idle_exit
-	stg	%r1,__SF_EMPTY+8(%r15)
-	larl	%r1,smp_cpu_mtid
-	llgf	%r1,0(%r1)
-	ltgr	%r1,%r1
-	jz	.Lpsw_idle_stcctm
-	.insn	rsy,0xeb0000000017,%r1,5,__MT_CYCLES_ENTER(%r2)
-.Lpsw_idle_stcctm:
-	oi	__LC_CPU_FLAGS+7,_CIF_ENABLED_WAIT
-	BPON
-	stckf	__CLOCK_IDLE_ENTER(%r2)
-	stpt	__TIMER_IDLE_ENTER(%r2)
-	lpswe	__SF_EMPTY(%r15)
-SYM_INNER_LABEL(psw_idle_exit, SYM_L_GLOBAL)
-	BR_EX	%r14
-SYM_FUNC_END(psw_idle)
-
 /*
  * Machine check handler routines
  */

arch/s390/kernel/idle.c

@@ -57,9 +57,13 @@ void noinstr arch_cpu_idle(void)
 	psw_mask = PSW_KERNEL_BITS | PSW_MASK_WAIT |
 		   PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
 	clear_cpu_flag(CIF_NOHZ_DELAY);
-
-	/* psw_idle() returns with interrupts disabled. */
-	psw_idle(idle, psw_mask);
+	set_cpu_flag(CIF_ENABLED_WAIT);
+	if (smp_cpu_mtid)
+		stcctm(MT_DIAG, smp_cpu_mtid, (u64 *)&idle->mt_cycles_enter);
+	idle->clock_idle_enter = get_tod_clock_fast();
+	idle->timer_idle_enter = get_cpu_timer();
+	bpon();
+	__load_psw_mask(psw_mask);
 }
 
 static ssize_t show_idle_count(struct device *dev,