Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/s390/linux

Pull s390 updates from Martin Schwidefsky:

 - A rework for the s390 arch random code, the TRNG instruction is
   rather slow and should not be used on the interrupt path

 - A fix for a memory leak in the zcrypt driver

 - Changes to the early boot code to add a compile time check for code
   that may not use the .bss section, with the goal to avoid initrd
   corruptions

 - Add an interface to get the physical network ID (pnetid), this is
   useful to group network devices that are attached to the same network

 - Some cleanup for the linker script

 - Some code improvement for the dasd driver

 - Two fixes for the perf sampling support

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux:
  s390/zcrypt: Fix CCA and EP11 CPRB processing failure memory leak.
  s390/archrandom: Rework arch random implementation.
  s390/net: add pnetid support
  s390/dasd: simplify locking in dasd_times_out
  s390/cio: add test for ccwgroup device
  s390/cio: add helper to query utility strings per given ccw device
  s390: remove no-op macro VMLINUX_SYMBOL()
  s390: remove closung punctuation from spectre messages
  s390: introduce compile time check for empty .bss section
  s390/early: move functions which may not access bss section to extra file
  s390/early: get rid of #ifdef CONFIG_BLK_DEV_INITRD
  s390/early: get rid of memmove_early
  s390/cpum_sf: Add data entry sizes to sampling trailer entry
  perf: fix invalid bit in diagnostic entry

arch/s390/Kconfig

@@ -838,6 +838,10 @@ config CCW
 
 source "drivers/Kconfig"
 
+config HAVE_PNETID
+	tristate
+	default (SMC || CCWGROUP)
+
 source "fs/Kconfig"
 
 source "arch/s390/Kconfig.debug"

arch/s390/crypto/arch_random.c

@@ -2,26 +2,121 @@
 /*
  * s390 arch random implementation.
  *
- * Copyright IBM Corp. 2017
- * Author(s): Harald Freudenberger <[email protected]>
+ * Copyright IBM Corp. 2017, 2018
+ * Author(s): Harald Freudenberger
+ *
+ * The s390_arch_random_generate() function may be called from random.c
+ * in interrupt context. So this implementation does the best to be very
+ * fast. There is a buffer of random data which is asynchronously checked
+ * and filled by a workqueue thread.
+ * If there are enough bytes in the buffer the s390_arch_random_generate()
+ * just delivers these bytes. Otherwise false is returned until the
+ * worker thread refills the buffer.
+ * The worker fills the rng buffer by pulling fresh entropy from the
+ * high quality (but slow) true hardware random generator. This entropy
+ * is then spread over the buffer with an pseudo random generator PRNG.
+ * As the arch_get_random_seed_long() fetches 8 bytes and the calling
+ * function add_interrupt_randomness() counts this as 1 bit entropy the
+ * distribution needs to make sure there is in fact 1 bit entropy contained
+ * in 8 bytes of the buffer. The current values pull 32 byte entropy
+ * and scatter this into a 2048 byte buffer. So 8 byte in the buffer
+ * will contain 1 bit of entropy.
+ * The worker thread is rescheduled based on the charge level of the
+ * buffer but at least with 500 ms delay to avoid too much CPU consumption.
+ * So the max. amount of rng data delivered via arch_get_random_seed is
+ * limited to 4k bytes per second.
  */
 
 #include <linux/kernel.h>
 #include <linux/atomic.h>
 #include <linux/random.h>
+#include <linux/slab.h>
 #include <linux/static_key.h>
+#include <linux/workqueue.h>
 #include <asm/cpacf.h>
 
 DEFINE_STATIC_KEY_FALSE(s390_arch_random_available);
 
 atomic64_t s390_arch_random_counter = ATOMIC64_INIT(0);
 EXPORT_SYMBOL(s390_arch_random_counter);
 
+#define ARCH_REFILL_TICKS (HZ/2)
+#define ARCH_PRNG_SEED_SIZE 32
+#define ARCH_RNG_BUF_SIZE 2048
+
+static DEFINE_SPINLOCK(arch_rng_lock);
+static u8 *arch_rng_buf;
+static unsigned int arch_rng_buf_idx;
+
+static void arch_rng_refill_buffer(struct work_struct *);
+static DECLARE_DELAYED_WORK(arch_rng_work, arch_rng_refill_buffer);
+
+bool s390_arch_random_generate(u8 *buf, unsigned int nbytes)
+{
+	/* lock rng buffer */
+	if (!spin_trylock(&arch_rng_lock))
+		return false;
+
+	/* try to resolve the requested amount of bytes from the buffer */
+	arch_rng_buf_idx -= nbytes;
+	if (arch_rng_buf_idx < ARCH_RNG_BUF_SIZE) {
+		memcpy(buf, arch_rng_buf + arch_rng_buf_idx, nbytes);
+		atomic64_add(nbytes, &s390_arch_random_counter);
+		spin_unlock(&arch_rng_lock);
+		return true;
+	}
+
+	/* not enough bytes in rng buffer, refill is done asynchronously */
+	spin_unlock(&arch_rng_lock);
+
+	return false;
+}
+EXPORT_SYMBOL(s390_arch_random_generate);
+
+static void arch_rng_refill_buffer(struct work_struct *unused)
+{
+	unsigned int delay = ARCH_REFILL_TICKS;
+
+	spin_lock(&arch_rng_lock);
+	if (arch_rng_buf_idx > ARCH_RNG_BUF_SIZE) {
+		/* buffer is exhausted and needs refill */
+		u8 seed[ARCH_PRNG_SEED_SIZE];
+		u8 prng_wa[240];
+		/* fetch ARCH_PRNG_SEED_SIZE bytes of entropy */
+		cpacf_trng(NULL, 0, seed, sizeof(seed));
+		/* blow this entropy up to ARCH_RNG_BUF_SIZE with PRNG */
+		memset(prng_wa, 0, sizeof(prng_wa));
+		cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED,
+			   &prng_wa, NULL, 0, seed, sizeof(seed));
+		cpacf_prno(CPACF_PRNO_SHA512_DRNG_GEN,
+			   &prng_wa, arch_rng_buf, ARCH_RNG_BUF_SIZE, NULL, 0);
+		arch_rng_buf_idx = ARCH_RNG_BUF_SIZE;
+	}
+	delay += (ARCH_REFILL_TICKS * arch_rng_buf_idx) / ARCH_RNG_BUF_SIZE;
+	spin_unlock(&arch_rng_lock);
+
+	/* kick next check */
+	queue_delayed_work(system_long_wq, &arch_rng_work, delay);
+}
+
 static int __init s390_arch_random_init(void)
 {
-	/* check if subfunction CPACF_PRNO_TRNG is available */
-	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG))
+	/* all the needed PRNO subfunctions available ? */
+	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG) &&
+	    cpacf_query_func(CPACF_PRNO, CPACF_PRNO_SHA512_DRNG_GEN)) {
+
+		/* alloc arch random working buffer */
+		arch_rng_buf = kmalloc(ARCH_RNG_BUF_SIZE, GFP_KERNEL);
+		if (!arch_rng_buf)
+			return -ENOMEM;
+
+		/* kick worker queue job to fill the random buffer */
+		queue_delayed_work(system_long_wq,
+				   &arch_rng_work, ARCH_REFILL_TICKS);
+
+		/* enable arch random to the outside world */
 		static_branch_enable(&s390_arch_random_available);
+	}
 
 	return 0;
 }

arch/s390/include/asm/archrandom.h

@@ -15,16 +15,11 @@
 
 #include <linux/static_key.h>
 #include <linux/atomic.h>
-#include <asm/cpacf.h>
 
 DECLARE_STATIC_KEY_FALSE(s390_arch_random_available);
 extern atomic64_t s390_arch_random_counter;
 
-static void s390_arch_random_generate(u8 *buf, unsigned int nbytes)
-{
-	cpacf_trng(NULL, 0, buf, nbytes);
-	atomic64_add(nbytes, &s390_arch_random_counter);
-}
+bool s390_arch_random_generate(u8 *buf, unsigned int nbytes);
 
 static inline bool arch_has_random(void)
 {
@@ -51,17 +46,15 @@ static inline bool arch_get_random_int(unsigned int *v)
 static inline bool arch_get_random_seed_long(unsigned long *v)
 {
 	if (static_branch_likely(&s390_arch_random_available)) {
-		s390_arch_random_generate((u8 *)v, sizeof(*v));
-		return true;
+		return s390_arch_random_generate((u8 *)v, sizeof(*v));
 	}
 	return false;
 }
 
 static inline bool arch_get_random_seed_int(unsigned int *v)
 {
 	if (static_branch_likely(&s390_arch_random_available)) {
-		s390_arch_random_generate((u8 *)v, sizeof(*v));
-		return true;
+		return s390_arch_random_generate((u8 *)v, sizeof(*v));
 	}
 	return false;
 }

arch/s390/include/asm/ccwdev.h

@@ -231,4 +231,5 @@ int ccw_device_siosl(struct ccw_device *);
 extern void ccw_device_get_schid(struct ccw_device *, struct subchannel_id *);
 
 struct channel_path_desc_fmt0 *ccw_device_get_chp_desc(struct ccw_device *, int);
+u8 *ccw_device_get_util_str(struct ccw_device *cdev, int chp_idx);
 #endif /* _S390_CCWDEV_H_ */

arch/s390/include/asm/ccwgroup.h

@@ -73,4 +73,14 @@ extern void ccwgroup_remove_ccwdev(struct ccw_device *cdev);
 
 #define to_ccwgroupdev(x) container_of((x), struct ccwgroup_device, dev)
 #define to_ccwgroupdrv(x) container_of((x), struct ccwgroup_driver, driver)
+
+#if IS_ENABLED(CONFIG_CCWGROUP)
+bool dev_is_ccwgroup(struct device *dev);
+#else /* CONFIG_CCWGROUP */
+static inline bool dev_is_ccwgroup(struct device *dev)
+{
+	return false;
+}
+#endif /* CONFIG_CCWGROUP */
+
 #endif

arch/s390/include/asm/cpu_mf.h

@@ -113,7 +113,7 @@ struct hws_basic_entry {
 
 struct hws_diag_entry {
 	unsigned int def:16;	    /* 0-15  Data Entry Format		 */
-	unsigned int R:14;	    /* 16-19 and 20-30 reserved		 */
+	unsigned int R:15;	    /* 16-19 and 20-30 reserved		 */
 	unsigned int I:1;	    /* 31 entry valid or invalid	 */
 	u8	     data[];	    /* Machine-dependent sample data	 */
 } __packed;
@@ -129,7 +129,9 @@ struct hws_trailer_entry {
 			unsigned int f:1;	/* 0 - Block Full Indicator   */
 			unsigned int a:1;	/* 1 - Alert request control  */
 			unsigned int t:1;	/* 2 - Timestamp format	      */
-			unsigned long long:61;	/* 3 - 63: Reserved	      */
+			unsigned int :29;	/* 3 - 31: Reserved	      */
+			unsigned int bsdes:16;	/* 32-47: size of basic SDE   */
+			unsigned int dsdes:16;	/* 48-63: size of diagnostic SDE */
 		};
 		unsigned long long flags;	/* 0 - 63: All indicators     */
 	};

arch/s390/include/asm/pnet.h

@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  IBM System z PNET ID Support
+ *
+ *    Copyright IBM Corp. 2018
+ */
+
+#ifndef _ASM_S390_PNET_H
+#define _ASM_S390_PNET_H
+
+#include <linux/device.h>
+#include <linux/types.h>
+
+#define PNETIDS_LEN		64	/* Total utility string length in bytes
+					 * to cover up to 4 PNETIDs of 16 bytes
+					 * for up to 4 device ports
+					 */
+#define MAX_PNETID_LEN		16	/* Max.length of a single port PNETID */
+#define MAX_PNETID_PORTS	(PNETIDS_LEN / MAX_PNETID_LEN)
+					/* Max. # of ports with a PNETID */
+
+int pnet_id_by_dev_port(struct device *dev, unsigned short port, u8 *pnetid);
+#endif /* _ASM_S390_PNET_H */

arch/s390/kernel/Makefile

@@ -6,22 +6,26 @@
 ifdef CONFIG_FUNCTION_TRACER
 
 # Do not trace tracer code
-CFLAGS_REMOVE_ftrace.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_ftrace.o		= $(CC_FLAGS_FTRACE)
 
 # Do not trace early setup code
-CFLAGS_REMOVE_als.o	= $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_early.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_als.o		= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_early.o		= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_early_nobss.o	= $(CC_FLAGS_FTRACE)
 
 endif
 
-GCOV_PROFILE_als.o	:= n
-GCOV_PROFILE_early.o	:= n
+GCOV_PROFILE_als.o		:= n
+GCOV_PROFILE_early.o		:= n
+GCOV_PROFILE_early_nobss.o	:= n
 
-KCOV_INSTRUMENT_als.o	:= n
-KCOV_INSTRUMENT_early.o	:= n
+KCOV_INSTRUMENT_als.o		:= n
+KCOV_INSTRUMENT_early.o		:= n
+KCOV_INSTRUMENT_early_nobss.o	:= n
 
-UBSAN_SANITIZE_als.o	:= n
-UBSAN_SANITIZE_early.o	:= n
+UBSAN_SANITIZE_als.o		:= n
+UBSAN_SANITIZE_early.o		:= n
+UBSAN_SANITIZE_early_nobss.o	:= n
 
 #
 # Use -march=z900 for als.c to be able to print an error
@@ -57,7 +61,7 @@ CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
 obj-y	:= traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
 obj-y	+= processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
-obj-y	+= debug.o irq.o ipl.o dis.o diag.o vdso.o als.o
+obj-y	+= debug.o irq.o ipl.o dis.o diag.o vdso.o als.o early_nobss.o
 obj-y	+= sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
 obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
 obj-y	+= entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o
@@ -94,3 +98,6 @@ obj-$(CONFIG_TRACEPOINTS)	+= trace.o
 # vdso
 obj-y				+= vdso64/
 obj-$(CONFIG_COMPAT)		+= vdso32/
+
+chkbss := head.o head64.o als.o early_nobss.o
+include $(srctree)/arch/s390/scripts/Makefile.chkbss

arch/s390/kernel/early.c

@@ -33,32 +33,6 @@
 
 static void __init setup_boot_command_line(void);
 
-/*
- * Get the TOD clock running.
- */
-static void __init reset_tod_clock(void)
-{
-	u64 time;
-
-	if (store_tod_clock(&time) == 0)
-		return;
-	/* TOD clock not running. Set the clock to Unix Epoch. */
-	if (set_tod_clock(TOD_UNIX_EPOCH) != 0 || store_tod_clock(&time) != 0)
-		disabled_wait(0);
-
-	memset(tod_clock_base, 0, 16);
-	*(__u64 *) &tod_clock_base[1] = TOD_UNIX_EPOCH;
-	S390_lowcore.last_update_clock = TOD_UNIX_EPOCH;
-}
-
-/*
- * Clear bss memory
- */
-static noinline __init void clear_bss_section(void)
-{
-	memset(__bss_start, 0, __bss_stop - __bss_start);
-}
-
 /*
  * Initialize storage key for kernel pages
  */
@@ -310,57 +284,6 @@ static int __init cad_setup(char *str)
 }
 early_param("cad", cad_setup);
 
-static __init void memmove_early(void *dst, const void *src, size_t n)
-{
-	unsigned long addr;
-	long incr;
-	psw_t old;
-
-	if (!n)
-		return;
-	incr = 1;
-	if (dst > src) {
-		incr = -incr;
-		dst += n - 1;
-		src += n - 1;
-	}
-	old = S390_lowcore.program_new_psw;
-	S390_lowcore.program_new_psw.mask = __extract_psw();
-	asm volatile(
-		"	larl	%[addr],1f\n"
-		"	stg	%[addr],%[psw_pgm_addr]\n"
-		"0:     mvc	0(1,%[dst]),0(%[src])\n"
-		"	agr	%[dst],%[incr]\n"
-		"	agr	%[src],%[incr]\n"
-		"	brctg	%[n],0b\n"
-		"1:\n"
-		: [addr] "=&d" (addr),
-		  [psw_pgm_addr] "=Q" (S390_lowcore.program_new_psw.addr),
-		  [dst] "+&a" (dst), [src] "+&a" (src),  [n] "+d" (n)
-		: [incr] "d" (incr)
-		: "cc", "memory");
-	S390_lowcore.program_new_psw = old;
-}
-
-static __init noinline void rescue_initrd(void)
-{
-#ifdef CONFIG_BLK_DEV_INITRD
-	unsigned long min_initrd_addr = (unsigned long) _end + (4UL << 20);
-	/*
-	 * Just like in case of IPL from VM reader we make sure there is a
-	 * gap of 4MB between end of kernel and start of initrd.
-	 * That way we can also be sure that saving an NSS will succeed,
-	 * which however only requires different segments.
-	 */
-	if (!INITRD_START || !INITRD_SIZE)
-		return;
-	if (INITRD_START >= min_initrd_addr)
-		return;
-	memmove_early((void *) min_initrd_addr, (void *) INITRD_START, INITRD_SIZE);
-	INITRD_START = min_initrd_addr;
-#endif
-}
-
 /* Set up boot command line */
 static void __init append_to_cmdline(size_t (*ipl_data)(char *, size_t))
 {
@@ -410,9 +333,6 @@ static void __init setup_boot_command_line(void)
 
 void __init startup_init(void)
 {
-	reset_tod_clock();
-	rescue_initrd();
-	clear_bss_section();
 	time_early_init();
 	init_kernel_storage_key();
 	lockdep_off();