From bbfed511c262db4d046a35f0389d98645124814f Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Thu, 15 Oct 2015 11:14:19 +0200
Subject: s390/zcore: copy vector registers into the image data

The /sys/kernel/debug/zcore/mem interface delivers the memory of the
old system with the CPU registers stored to the assigned locations in
each prefix page.

For the vector registers the prefix page of each CPU has an address of
a 1024 byte save area at 0x11b0. But the /sys/kernel/debug/zcore/mem
interface fails copy the vector registers saved at boot of the zfcpdump
kernel into the dump image.

Copy the saved vector registers of a CPU to the outout buffer if the
memory area that is read via /sys/kernel/debug/zcore/mem intersects
with the vector register save area of this CPU.

Acked-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/lowcore.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index afe1cfebf1a4..bc618067e725 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -35,6 +35,7 @@ struct save_area {
 struct save_area_ext {
 	struct save_area	sa;
 	__vector128		vx_regs[32];
+	u64			vx_sa_addr;
 };
 
 struct _lowcore {
-- 
cgit 


From ffa52d02c50ea31420dc70869c0b6b439e7cb5ef Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Wed, 28 Oct 2015 09:47:58 +0100
Subject: s390/zcore: remove /sys/kernel/debug/zcore/mem

New versions of the SCSI dumper use the /dev/vmcore interface instead
of zcore mem. Remove the outdated interface.

Acked-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/lowcore.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index bc618067e725..afe1cfebf1a4 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -35,7 +35,6 @@ struct save_area {
 struct save_area_ext {
 	struct save_area	sa;
 	__vector128		vx_regs[32];
-	u64			vx_sa_addr;
 };
 
 struct _lowcore {
-- 
cgit 


From 8a07dd02d7615d91d65d6235f7232e3f9b5d347f Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Wed, 14 Oct 2015 15:53:06 +0200
Subject: s390/kdump: remove code to create ELF notes in the crashed system

The s390 architecture can store the CPU registers of the crashed system
after the kdump kernel has been started and this is the preferred way.
Remove the remaining code fragments that deal with storing CPU registers
while the crashed system is still active.

Acked-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/elf.h      |  2 --
 arch/s390/kernel/crash_dump.c    | 24 +++--------------------
 arch/s390/kernel/machine_kexec.c | 42 +++++++++++++++++-----------------------
 arch/s390/kernel/setup.c         | 15 +++++---------
 arch/s390/kernel/smp.c           |  8 ++------
 5 files changed, 28 insertions(+), 63 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index bab6739a1154..7730e5b9e7e2 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -229,6 +229,4 @@ struct linux_binprm;
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
 int arch_setup_additional_pages(struct linux_binprm *, int);
 
-void *fill_cpu_elf_notes(void *ptr, struct save_area *sa, __vector128 *vxrs);
-
 #endif
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 171e09bb8ea2..07d75b969f59 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -72,11 +72,6 @@ static int copy_from_realmem(void *dest, void *src, size_t count)
 	return 0;
 }
 
-/*
- * Pointer to ELF header in new kernel
- */
-static void *elfcorehdr_newmem;
-
 /*
  * Copy one page from zfcpdump "oldmem"
  *
@@ -390,7 +385,8 @@ static void *nt_s390_vx_low(void *ptr, __vector128 *vx_regs)
 /*
  * Fill ELF notes for one CPU with save area registers
  */
-void *fill_cpu_elf_notes(void *ptr, struct save_area *sa, __vector128 *vx_regs)
+static void *fill_cpu_elf_notes(void *ptr, struct save_area *sa,
+				__vector128 *vx_regs)
 {
 	ptr = nt_prstatus(ptr, sa);
 	ptr = nt_fpregset(ptr, sa);
@@ -573,9 +569,6 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
 	/* If we are not in kdump or zfcpdump mode return */
 	if (!OLDMEM_BASE && ipl_info.type != IPL_TYPE_FCP_DUMP)
 		return 0;
-	/* If elfcorehdr= has been passed via cmdline, we use that one */
-	if (elfcorehdr_addr != ELFCORE_ADDR_MAX)
-		return 0;
 	/* If we cannot get HSA size for zfcpdump return error */
 	if (ipl_info.type == IPL_TYPE_FCP_DUMP && !sclp.hsa_size)
 		return -ENODEV;
@@ -606,7 +599,6 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
 	hdr_off = PTR_DIFF(ptr, hdr);
 	loads_init(phdr_loads, hdr_off);
 	*addr = (unsigned long long) hdr;
-	elfcorehdr_newmem = hdr;
 	*size = (unsigned long long) hdr_off;
 	BUG_ON(elfcorehdr_size > alloc_size);
 	return 0;
@@ -617,8 +609,6 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
  */
 void elfcorehdr_free(unsigned long long addr)
 {
-	if (!elfcorehdr_newmem)
-		return;
 	kfree((void *)(unsigned long)addr);
 }
 
@@ -629,7 +619,6 @@ ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos)
 {
 	void *src = (void *)(unsigned long)*ppos;
 
-	src = elfcorehdr_newmem ? src : src - OLDMEM_BASE;
 	memcpy(buf, src, count);
 	*ppos += count;
 	return count;
@@ -641,15 +630,8 @@ ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos)
 ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos)
 {
 	void *src = (void *)(unsigned long)*ppos;
-	int rc;
 
-	if (elfcorehdr_newmem) {
-		memcpy(buf, src, count);
-	} else {
-		rc = copy_from_oldmem(buf, src, count);
-		if (rc)
-			return rc;
-	}
+	memcpy(buf, src, count);
 	*ppos += count;
 	return count;
 }
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index fb0901ec4306..991b16819b97 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -34,44 +34,38 @@ extern const unsigned long long relocate_kernel_len;
 
 #ifdef CONFIG_CRASH_DUMP
 
-/*
- * Create ELF notes for one CPU
- */
-static void add_elf_notes(int cpu)
-{
-	struct save_area *sa = (void *) 4608 + store_prefix();
-	void *ptr;
-
-	memcpy((void *) (4608UL + sa->pref_reg), sa, sizeof(*sa));
-	ptr = (u64 *) per_cpu_ptr(crash_notes, cpu);
-	ptr = fill_cpu_elf_notes(ptr, sa, NULL);
-	memset(ptr, 0, sizeof(struct elf_note));
-}
-
 /*
  * Initialize CPU ELF notes
  */
 static void setup_regs(void)
 {
-	unsigned long sa = S390_lowcore.prefixreg_save_area + SAVE_AREA_BASE;
-	struct _lowcore *lc;
+	struct save_area *sa, *sa_0;
+	unsigned long prefix;
 	int cpu, this_cpu;
 
-	/* Get lowcore pointer from store status of this CPU (absolute zero) */
-	lc = (struct _lowcore *)(unsigned long)S390_lowcore.prefixreg_save_area;
+	/* setup_regs is called with the prefix register = 0 */
+	sa_0 = (struct save_area *) SAVE_AREA_BASE;
+
+	/* Get status of this CPU out of absolute zero */
+	prefix = (unsigned long) S390_lowcore.prefixreg_save_area;
+	sa = (struct save_area *)(prefix + SAVE_AREA_BASE);
+	memcpy(sa, sa_0, sizeof(struct save_area));
+	if (MACHINE_HAS_VX) {
+		struct _lowcore *lc = (struct _lowcore *) prefix;
+		save_vx_regs_safe((void *) lc->vector_save_area_addr);
+	}
+
+	/* Get status of the other CPUs */
 	this_cpu = smp_find_processor_id(stap());
-	add_elf_notes(this_cpu);
 	for_each_online_cpu(cpu) {
 		if (cpu == this_cpu)
 			continue;
 		if (smp_store_status(cpu))
 			continue;
-		add_elf_notes(cpu);
+		prefix = (unsigned long) S390_lowcore.prefixreg_save_area;
+		sa = (struct save_area *)(prefix + SAVE_AREA_BASE);
+		memcpy(sa, sa_0, sizeof(struct save_area));
 	}
-	if (MACHINE_HAS_VX)
-		save_vx_regs_safe((void *) lc->vector_save_area_addr);
-	/* Copy dump CPU store status info to absolute zero */
-	memcpy((void *) SAVE_AREA_BASE, (void *) sa, sizeof(struct save_area));
 }
 
 /*
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index c837bcacf218..8f5107d6ebb3 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -661,15 +661,6 @@ static void __init reserve_kernel(void)
 #endif
 }
 
-static void __init reserve_elfcorehdr(void)
-{
-#ifdef CONFIG_CRASH_DUMP
-	if (is_kdump_kernel())
-		memblock_reserve(elfcorehdr_addr - OLDMEM_BASE,
-				 PAGE_ALIGN(elfcorehdr_size));
-#endif
-}
-
 static void __init setup_memory(void)
 {
 	struct memblock_region *reg;
@@ -841,6 +832,11 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.brk = (unsigned long) &_end;
 
 	parse_early_param();
+#ifdef CONFIG_CRASH_DUMP
+	/* Deactivate elfcorehdr= kernel parameter */
+	elfcorehdr_addr = ELFCORE_ADDR_MAX;
+#endif
+
 	os_info_init();
 	setup_ipl();
 
@@ -849,7 +845,6 @@ void __init setup_arch(char **cmdline_p)
 	reserve_oldmem();
 	reserve_kernel();
 	reserve_initrd();
-	reserve_elfcorehdr();
 	memblock_allow_resize();
 
 	/* Get information about *all* installed memory */
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 9062df575afe..7ad070e984f2 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -608,9 +608,8 @@ int smp_store_status(int cpu)
  *    stored the registers of the boot CPU in the memory of the old system.
  * 4) kdump and the old kernel stored the CPU state
  *    condition: OLDMEM_BASE != NULL && is_kdump_kernel()
- *    The state of all CPUs is stored in ELF sections in the memory of the
- *    old system. The ELF sections are picked up by the crash_dump code
- *    via elfcorehdr_addr.
+ *    This case does not exist for s390 anymore, setup_arch explicitly
+ *    deactivates the elfcorehdr= kernel parameter
  */
 void __init smp_save_dump_cpus(void)
 {
@@ -619,9 +618,6 @@ void __init smp_save_dump_cpus(void)
 	struct save_area_ext *sa_ext;
 	bool is_boot_cpu;
 
-	if (is_kdump_kernel())
-		/* Previous system stored the CPU states. Nothing to do. */
-		return;
 	if (!(OLDMEM_BASE || ipl_info.type == IPL_TYPE_FCP_DUMP))
 		/* No previous system present, normal boot. */
 		return;
-- 
cgit 


From df9694c7975ff9976368eb381388c61f65352aef Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Mon, 12 Oct 2015 10:43:37 +0200
Subject: s390/dump: streamline oldmem copy functions

Introduce two copy functions for the memory of the dumped system,
copy_oldmem_kernel() to copy to the virtual kernel address space
and copy_oldmem_user() to copy to user space.

Acked-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/os_info.h |   2 +-
 arch/s390/include/asm/sclp.h    |   3 +-
 arch/s390/kernel/crash_dump.c   | 171 +++++++++++++++++++---------------------
 arch/s390/kernel/os_info.c      |   7 +-
 arch/s390/kernel/smp.c          |   4 +-
 5 files changed, 88 insertions(+), 99 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/os_info.h b/arch/s390/include/asm/os_info.h
index 295f2c4f1c96..943475382d51 100644
--- a/arch/s390/include/asm/os_info.h
+++ b/arch/s390/include/asm/os_info.h
@@ -38,7 +38,7 @@ u32 os_info_csum(struct os_info *os_info);
 
 #ifdef CONFIG_CRASH_DUMP
 void *os_info_old_entry(int nr, unsigned long *size);
-int copy_from_oldmem(void *dest, void *src, size_t count);
+int copy_oldmem_kernel(void *dst, void *src, size_t count);
 #else
 static inline void *os_info_old_entry(int nr, unsigned long *size)
 {
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 821dde5f425d..2ca9c7bc50db 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -77,7 +77,8 @@ int sclp_chp_read_info(struct sclp_chp_info *info);
 void sclp_get_ipl_info(struct sclp_ipl_info *info);
 int sclp_pci_configure(u32 fid);
 int sclp_pci_deconfigure(u32 fid);
-int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode);
+int memcpy_hsa_kernel(void *dest, unsigned long src, size_t count);
+int memcpy_hsa_user(void __user *dest, unsigned long src, size_t count);
 void sclp_early_detect(void);
 int _sclp_print_early(const char *);
 
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 07d75b969f59..0d59c0705c4f 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -51,74 +51,85 @@ static inline void *load_real_addr(void *addr)
 }
 
 /*
- * Copy real to virtual or real memory
+ * Copy memory of the old, dumped system to a kernel space virtual address
  */
-static int copy_from_realmem(void *dest, void *src, size_t count)
-{
-	unsigned long size;
-
-	if (!count)
-		return 0;
-	if (!is_vmalloc_or_module_addr(dest))
-		return memcpy_real(dest, src, count);
-	do {
-		size = min(count, PAGE_SIZE - (__pa(dest) & ~PAGE_MASK));
-		if (memcpy_real(load_real_addr(dest), src, size))
-			return -EFAULT;
-		count -= size;
-		dest += size;
-		src += size;
-	} while (count);
-	return 0;
-}
-
-/*
- * Copy one page from zfcpdump "oldmem"
- *
- * For pages below HSA size memory from the HSA is copied. Otherwise
- * real memory copy is used.
- */
-static ssize_t copy_oldmem_page_zfcpdump(char *buf, size_t csize,
-					 unsigned long src, int userbuf)
+int copy_oldmem_kernel(void *dst, void *src, size_t count)
 {
+	unsigned long from, len;
+	void *ra;
 	int rc;
 
-	if (src < sclp.hsa_size) {
-		rc = memcpy_hsa(buf, src, csize, userbuf);
-	} else {
-		if (userbuf)
-			rc = copy_to_user_real((void __force __user *) buf,
-					       (void *) src, csize);
-		else
-			rc = memcpy_real(buf, (void *) src, csize);
+	while (count) {
+		from = __pa(src);
+		if (!OLDMEM_BASE && from < sclp.hsa_size) {
+			/* Copy from zfcpdump HSA area */
+			len = min(count, sclp.hsa_size - from);
+			rc = memcpy_hsa_kernel(dst, from, len);
+			if (rc)
+				return rc;
+		} else {
+			/* Check for swapped kdump oldmem areas */
+			if (OLDMEM_BASE && from - OLDMEM_BASE < OLDMEM_SIZE) {
+				from -= OLDMEM_BASE;
+				len = min(count, OLDMEM_SIZE - from);
+			} else if (OLDMEM_BASE && from < OLDMEM_SIZE) {
+				len = min(count, OLDMEM_SIZE - from);
+				from += OLDMEM_BASE;
+			} else {
+				len = count;
+			}
+			if (is_vmalloc_or_module_addr(dst)) {
+				ra = load_real_addr(dst);
+				len = min(PAGE_SIZE - offset_in_page(ra), len);
+			} else {
+				ra = dst;
+			}
+			if (memcpy_real(ra, (void *) from, len))
+				return -EFAULT;
+		}
+		dst += len;
+		src += len;
+		count -= len;
 	}
-	return rc ? rc : csize;
+	return 0;
 }
 
 /*
- * Copy one page from kdump "oldmem"
- *
- * For the kdump reserved memory this functions performs a swap operation:
- *  - [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] is mapped to [0 - OLDMEM_SIZE].
- *  - [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE]
+ * Copy memory of the old, dumped system to a user space virtual address
  */
-static ssize_t copy_oldmem_page_kdump(char *buf, size_t csize,
-				      unsigned long src, int userbuf)
-
+int copy_oldmem_user(void __user *dst, void *src, size_t count)
 {
+	unsigned long from, len;
 	int rc;
 
-	if (src < OLDMEM_SIZE)
-		src += OLDMEM_BASE;
-	else if (src > OLDMEM_BASE &&
-		 src < OLDMEM_BASE + OLDMEM_SIZE)
-		src -= OLDMEM_BASE;
-	if (userbuf)
-		rc = copy_to_user_real((void __force __user *) buf,
-				       (void *) src, csize);
-	else
-		rc = copy_from_realmem(buf, (void *) src, csize);
-	return (rc == 0) ? rc : csize;
+	while (count) {
+		from = __pa(src);
+		if (!OLDMEM_BASE && from < sclp.hsa_size) {
+			/* Copy from zfcpdump HSA area */
+			len = min(count, sclp.hsa_size - from);
+			rc = memcpy_hsa_user(dst, from, len);
+			if (rc)
+				return rc;
+		} else {
+			/* Check for swapped kdump oldmem areas */
+			if (OLDMEM_BASE && from - OLDMEM_BASE < OLDMEM_SIZE) {
+				from -= OLDMEM_BASE;
+				len = min(count, OLDMEM_SIZE - from);
+			} else if (OLDMEM_BASE && from < OLDMEM_SIZE) {
+				len = min(count, OLDMEM_SIZE - from);
+				from += OLDMEM_BASE;
+			} else {
+				len = count;
+			}
+			rc = copy_to_user_real(dst, (void *) from, count);
+			if (rc)
+				return rc;
+		}
+		dst += len;
+		src += len;
+		count -= len;
+	}
+	return 0;
 }
 
 /*
@@ -127,15 +138,17 @@ static ssize_t copy_oldmem_page_kdump(char *buf, size_t csize,
 ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
 			 unsigned long offset, int userbuf)
 {
-	unsigned long src;
+	void *src;
+	int rc;
 
 	if (!csize)
 		return 0;
-	src = (pfn << PAGE_SHIFT) + offset;
-	if (OLDMEM_BASE)
-		return copy_oldmem_page_kdump(buf, csize, src, userbuf);
+	src = (void *) (pfn << PAGE_SHIFT) + offset;
+	if (userbuf)
+		rc = copy_oldmem_user((void __force __user *) buf, src, csize);
 	else
-		return copy_oldmem_page_zfcpdump(buf, csize, src, userbuf);
+		rc = copy_oldmem_kernel((void *) buf, src, csize);
+	return rc;
 }
 
 /*
@@ -203,33 +216,6 @@ int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from,
 						       prot);
 }
 
-/*
- * Copy memory from old kernel
- */
-int copy_from_oldmem(void *dest, void *src, size_t count)
-{
-	unsigned long copied = 0;
-	int rc;
-
-	if (OLDMEM_BASE) {
-		if ((unsigned long) src < OLDMEM_SIZE) {
-			copied = min(count, OLDMEM_SIZE - (unsigned long) src);
-			rc = copy_from_realmem(dest, src + OLDMEM_BASE, copied);
-			if (rc)
-				return rc;
-		}
-	} else {
-		unsigned long hsa_end = sclp.hsa_size;
-		if ((unsigned long) src < hsa_end) {
-			copied = min(count, hsa_end - (unsigned long) src);
-			rc = memcpy_hsa(dest, (unsigned long) src, copied, 0);
-			if (rc)
-				return rc;
-		}
-	}
-	return copy_from_realmem(dest + copied, src + copied, count - copied);
-}
-
 /*
  * Alloc memory and panic in case of ENOMEM
  */
@@ -425,17 +411,18 @@ static void *get_vmcoreinfo_old(unsigned long *size)
 	Elf64_Nhdr note;
 	void *addr;
 
-	if (copy_from_oldmem(&addr, &S390_lowcore.vmcore_info, sizeof(addr)))
+	if (copy_oldmem_kernel(&addr, &S390_lowcore.vmcore_info, sizeof(addr)))
 		return NULL;
 	memset(nt_name, 0, sizeof(nt_name));
-	if (copy_from_oldmem(&note, addr, sizeof(note)))
+	if (copy_oldmem_kernel(&note, addr, sizeof(note)))
 		return NULL;
-	if (copy_from_oldmem(nt_name, addr + sizeof(note), sizeof(nt_name) - 1))
+	if (copy_oldmem_kernel(nt_name, addr + sizeof(note),
+			       sizeof(nt_name) - 1))
 		return NULL;
 	if (strcmp(nt_name, "VMCOREINFO") != 0)
 		return NULL;
 	vmcoreinfo = kzalloc_panic(note.n_descsz);
-	if (copy_from_oldmem(vmcoreinfo, addr + 24, note.n_descsz))
+	if (copy_oldmem_kernel(vmcoreinfo, addr + 24, note.n_descsz))
 		return NULL;
 	*size = note.n_descsz;
 	return vmcoreinfo;
diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c
index d112fc66f993..87f05e475ae8 100644
--- a/arch/s390/kernel/os_info.c
+++ b/arch/s390/kernel/os_info.c
@@ -89,7 +89,7 @@ static void os_info_old_alloc(int nr, int align)
 		goto fail;
 	}
 	buf_align = PTR_ALIGN(buf, align);
-	if (copy_from_oldmem(buf_align, (void *) addr, size)) {
+	if (copy_oldmem_kernel(buf_align, (void *) addr, size)) {
 		msg = "copy failed";
 		goto fail_free;
 	}
@@ -122,14 +122,15 @@ static void os_info_old_init(void)
 		return;
 	if (!OLDMEM_BASE)
 		goto fail;
-	if (copy_from_oldmem(&addr, &S390_lowcore.os_info, sizeof(addr)))
+	if (copy_oldmem_kernel(&addr, &S390_lowcore.os_info, sizeof(addr)))
 		goto fail;
 	if (addr == 0 || addr % PAGE_SIZE)
 		goto fail;
 	os_info_old = kzalloc(sizeof(*os_info_old), GFP_KERNEL);
 	if (!os_info_old)
 		goto fail;
-	if (copy_from_oldmem(os_info_old, (void *) addr, sizeof(*os_info_old)))
+	if (copy_oldmem_kernel(os_info_old, (void *) addr,
+			       sizeof(*os_info_old)))
 		goto fail_free;
 	if (os_info_old->magic != OS_INFO_MAGIC)
 		goto fail_free;
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 7ad070e984f2..5e04acdc6290 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -546,8 +546,8 @@ static void __init __smp_store_cpu_state(struct save_area_ext *sa_ext,
 
 	if (is_boot_cpu) {
 		/* Copy the registers of the boot CPU. */
-		copy_oldmem_page(1, (void *) &sa_ext->sa, sizeof(sa_ext->sa),
-				 SAVE_AREA_BASE - PAGE_SIZE, 0);
+		copy_oldmem_kernel(&sa_ext->sa, (void *) SAVE_AREA_BASE,
+				   sizeof(sa_ext->sa));
 		if (MACHINE_HAS_VX)
 			save_vx_regs_safe(sa_ext->vx_regs);
 		return;
-- 
cgit 


From d9a3a09af54d01ab8b0c320580f4f95328d4a7ac Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Fri, 23 Oct 2015 09:02:32 +0200
Subject: s390/kvm: remove dependency on struct save_area definition

Replace the offsets based on the struct area_area with the offset
constants from asm-offsets.c based on the struct _lowcore.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/asm-offsets.c |  1 +
 arch/s390/kvm/kvm-s390.c       | 30 +++++++++++++++---------------
 2 files changed, 16 insertions(+), 15 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 9cd248f637c7..dc6c9c604543 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -181,6 +181,7 @@ int main(void)
 	OFFSET(__LC_PSW_SAVE_AREA, _lowcore, psw_save_area);
 	OFFSET(__LC_PREFIX_SAVE_AREA, _lowcore, prefixreg_save_area);
 	OFFSET(__LC_FP_CREG_SAVE_AREA, _lowcore, fpt_creg_save_area);
+	OFFSET(__LC_TOD_PROGREG_SAVE_AREA, _lowcore, tod_progreg_save_area);
 	OFFSET(__LC_CPU_TIMER_SAVE_AREA, _lowcore, cpu_timer_save_area);
 	OFFSET(__LC_CLOCK_COMP_SAVE_AREA, _lowcore, clock_comp_save_area);
 	OFFSET(__LC_AREGS_SAVE_AREA, _lowcore, access_regs_save_area);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 846589281b04..713a91a0622b 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2270,37 +2270,37 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 	u64 clkcomp;
 	int rc;
 
+	px = kvm_s390_get_prefix(vcpu);
 	if (gpa == KVM_S390_STORE_STATUS_NOADDR) {
 		if (write_guest_abs(vcpu, 163, &archmode, 1))
 			return -EFAULT;
-		gpa = SAVE_AREA_BASE;
+		gpa = 0;
 	} else if (gpa == KVM_S390_STORE_STATUS_PREFIXED) {
 		if (write_guest_real(vcpu, 163, &archmode, 1))
 			return -EFAULT;
-		gpa = kvm_s390_real_to_abs(vcpu, SAVE_AREA_BASE);
-	}
-	rc = write_guest_abs(vcpu, gpa + offsetof(struct save_area, fp_regs),
+		gpa = px;
+	} else
+		gpa -= __LC_FPREGS_SAVE_AREA;
+	rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
 			     vcpu->arch.guest_fpregs.fprs, 128);
-	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, gp_regs),
+	rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA,
 			      vcpu->run->s.regs.gprs, 128);
-	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, psw),
+	rc |= write_guest_abs(vcpu, gpa + __LC_PSW_SAVE_AREA,
 			      &vcpu->arch.sie_block->gpsw, 16);
-	px = kvm_s390_get_prefix(vcpu);
-	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, pref_reg),
+	rc |= write_guest_abs(vcpu, gpa + __LC_PREFIX_SAVE_AREA,
 			      &px, 4);
-	rc |= write_guest_abs(vcpu,
-			      gpa + offsetof(struct save_area, fp_ctrl_reg),
+	rc |= write_guest_abs(vcpu, gpa + __LC_FP_CREG_SAVE_AREA,
 			      &vcpu->arch.guest_fpregs.fpc, 4);
-	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, tod_reg),
+	rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA,
 			      &vcpu->arch.sie_block->todpr, 4);
-	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, timer),
+	rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA,
 			      &vcpu->arch.sie_block->cputm, 8);
 	clkcomp = vcpu->arch.sie_block->ckc >> 8;
-	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, clk_cmp),
+	rc |= write_guest_abs(vcpu, gpa + __LC_CLOCK_COMP_SAVE_AREA,
 			      &clkcomp, 8);
-	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, acc_regs),
+	rc |= write_guest_abs(vcpu, gpa + __LC_AREGS_SAVE_AREA,
 			      &vcpu->run->s.regs.acrs, 64);
-	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, ctrl_regs),
+	rc |= write_guest_abs(vcpu, gpa + __LC_CREGS_SAVE_AREA,
 			      &vcpu->arch.sie_block->gcr, 128);
 	return rc ? -EFAULT : 0;
 }
-- 
cgit 


From f08b8414632c9f256e33f0a18104d8d5e103d204 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Fri, 23 Oct 2015 09:05:38 +0200
Subject: s390/dump: remove SAVE_AREA_BASE

Replace the SAVE_AREA_BASE offset calculations in reipl.S with the
assembler constant for the location of each register status area.

Use __LC_FPREGS_SAVE_AREA instead of SAVE_AREA_BASE in the three
remaining code locations and remove the definition of SAVE_AREA_BASE.

Acked-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/asm-offsets.c   |  1 -
 arch/s390/kernel/machine_kexec.c |  6 ++--
 arch/s390/kernel/reipl.S         | 65 ++++++++++++++++++++++------------------
 arch/s390/kernel/smp.c           |  4 +--
 4 files changed, 41 insertions(+), 35 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index dc6c9c604543..ae7b565b6c4c 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -175,7 +175,6 @@ int main(void)
 	/* hardware defined lowcore locations 0x1000 - 0x18ff */
 	OFFSET(__LC_VX_SAVE_AREA_ADDR, _lowcore, vector_save_area_addr);
 	OFFSET(__LC_EXT_PARAMS2, _lowcore, ext_params2);
-	OFFSET(SAVE_AREA_BASE, _lowcore, floating_pt_save_area);
 	OFFSET(__LC_FPREGS_SAVE_AREA, _lowcore, floating_pt_save_area);
 	OFFSET(__LC_GPREGS_SAVE_AREA, _lowcore, gpregs_save_area);
 	OFFSET(__LC_PSW_SAVE_AREA, _lowcore, psw_save_area);
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 991b16819b97..bf2cd699556f 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -44,11 +44,11 @@ static void setup_regs(void)
 	int cpu, this_cpu;
 
 	/* setup_regs is called with the prefix register = 0 */
-	sa_0 = (struct save_area *) SAVE_AREA_BASE;
+	sa_0 = (struct save_area *) __LC_FPREGS_SAVE_AREA;
 
 	/* Get status of this CPU out of absolute zero */
 	prefix = (unsigned long) S390_lowcore.prefixreg_save_area;
-	sa = (struct save_area *)(prefix + SAVE_AREA_BASE);
+	sa = (struct save_area *)(prefix + __LC_FPREGS_SAVE_AREA);
 	memcpy(sa, sa_0, sizeof(struct save_area));
 	if (MACHINE_HAS_VX) {
 		struct _lowcore *lc = (struct _lowcore *) prefix;
@@ -63,7 +63,7 @@ static void setup_regs(void)
 		if (smp_store_status(cpu))
 			continue;
 		prefix = (unsigned long) S390_lowcore.prefixreg_save_area;
-		sa = (struct save_area *)(prefix + SAVE_AREA_BASE);
+		sa = (struct save_area *)(prefix + __LC_FPREGS_SAVE_AREA);
 		memcpy(sa, sa_0, sizeof(struct save_area));
 	}
 }
diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S
index 52aab0bd84f8..b75a521e4fab 100644
--- a/arch/s390/kernel/reipl.S
+++ b/arch/s390/kernel/reipl.S
@@ -19,49 +19,56 @@
 ENTRY(store_status)
 	/* Save register one and load save area base */
 	stg	%r1,__LC_SAVE_AREA_RESTART
-	lghi	%r1,SAVE_AREA_BASE
 	/* General purpose registers */
-	stmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
-	lg	%r2,__LC_SAVE_AREA_RESTART
-	stg	%r2,__LC_GPREGS_SAVE_AREA-SAVE_AREA_BASE+8(%r1)
+	lghi	%r1,__LC_GPREGS_SAVE_AREA
+	stmg	%r0,%r15,0(%r1)
+	mvc	8(8,%r1),__LC_SAVE_AREA_RESTART
 	/* Control registers */
-	stctg	%c0,%c15,__LC_CREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	lghi	%r1,__LC_CREGS_SAVE_AREA
+	stctg	%c0,%c15,0(%r1)
 	/* Access registers */
-	stam	%a0,%a15,__LC_AREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	lghi	%r1,__LC_AREGS_SAVE_AREA
+	stam	%a0,%a15,0(%r1)
 	/* Floating point registers */
-	std	%f0, 0x00 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
-	std	%f1, 0x08 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
-	std	%f2, 0x10 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
-	std	%f3, 0x18 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
-	std	%f4, 0x20 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
-	std	%f5, 0x28 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
-	std	%f6, 0x30 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
-	std	%f7, 0x38 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
-	std	%f8, 0x40 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
-	std	%f9, 0x48 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
-	std	%f10,0x50 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
-	std	%f11,0x58 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
-	std	%f12,0x60 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
-	std	%f13,0x68 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
-	std	%f14,0x70 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
-	std	%f15,0x78 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	lghi	%r1,__LC_FPREGS_SAVE_AREA
+	std	%f0, 0x00(%r1)
+	std	%f1, 0x08(%r1)
+	std	%f2, 0x10(%r1)
+	std	%f3, 0x18(%r1)
+	std	%f4, 0x20(%r1)
+	std	%f5, 0x28(%r1)
+	std	%f6, 0x30(%r1)
+	std	%f7, 0x38(%r1)
+	std	%f8, 0x40(%r1)
+	std	%f9, 0x48(%r1)
+	std	%f10,0x50(%r1)
+	std	%f11,0x58(%r1)
+	std	%f12,0x60(%r1)
+	std	%f13,0x68(%r1)
+	std	%f14,0x70(%r1)
+	std	%f15,0x78(%r1)
 	/* Floating point control register */
-	stfpc	__LC_FP_CREG_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	lghi	%r1,__LC_FP_CREG_SAVE_AREA
+	stfpc	0(%r1)
 	/* CPU timer */
-	stpt	__LC_CPU_TIMER_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	lghi	%r1,__LC_CPU_TIMER_SAVE_AREA
+	stpt	0(%r1)
 	/* Saved prefix register */
+	lghi	%r1,__LC_PREFIX_SAVE_AREA
 	larl	%r2,dump_prefix_page
-	mvc	__LC_PREFIX_SAVE_AREA-SAVE_AREA_BASE(4,%r1),0(%r2)
+	mvc	0(4,%r1),0(%r2)
 	/* Clock comparator - seven bytes */
+	lghi	%r1,__LC_CLOCK_COMP_SAVE_AREA
 	larl	%r2,.Lclkcmp
 	stckc	0(%r2)
-	mvc	__LC_CLOCK_COMP_SAVE_AREA-SAVE_AREA_BASE + 1(7,%r1),1(%r2)
+	mvc	1(7,%r1),1(%r2)
 	/* Program status word */
+	lghi	%r1,__LC_PSW_SAVE_AREA
 	epsw	%r2,%r3
-	st	%r2,__LC_PSW_SAVE_AREA-SAVE_AREA_BASE + 0(%r1)
-	st	%r3,__LC_PSW_SAVE_AREA-SAVE_AREA_BASE + 4(%r1)
+	st	%r2,0(%r1)
+	st	%r3,4(%r1)
 	larl	%r2,store_status
-	stg	%r2,__LC_PSW_SAVE_AREA-SAVE_AREA_BASE + 8(%r1)
+	stg	%r2,8(%r1)
 	br	%r14
 
 	.section .bss
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 5e04acdc6290..d49a8cb404c2 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -546,7 +546,7 @@ static void __init __smp_store_cpu_state(struct save_area_ext *sa_ext,
 
 	if (is_boot_cpu) {
 		/* Copy the registers of the boot CPU. */
-		copy_oldmem_kernel(&sa_ext->sa, (void *) SAVE_AREA_BASE,
+		copy_oldmem_kernel(&sa_ext->sa, (void *) __LC_FPREGS_SAVE_AREA,
 				   sizeof(sa_ext->sa));
 		if (MACHINE_HAS_VX)
 			save_vx_regs_safe(sa_ext->vx_regs);
@@ -554,7 +554,7 @@ static void __init __smp_store_cpu_state(struct save_area_ext *sa_ext,
 	}
 	/* Get the registers of a non-boot cpu. */
 	__pcpu_sigp_relax(address, SIGP_STOP_AND_STORE_STATUS, 0, NULL);
-	memcpy_real(&sa_ext->sa, lc + SAVE_AREA_BASE, sizeof(sa_ext->sa));
+	memcpy_real(&sa_ext->sa, lc + __LC_FPREGS_SAVE_AREA, sizeof(sa_ext->sa));
 	if (!MACHINE_HAS_VX)
 		return;
 	/* Get the VX registers */
-- 
cgit 


From 1a36a39e225d3558fb3776a3d3d7736cf1ec9f60 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Thu, 29 Oct 2015 10:28:26 +0100
Subject: s390/dump: rework CPU register dump code

To collect the CPU registers of the crashed system allocated a single
page with memblock_alloc_base and use it as a copy buffer. Replace the
stop-and-store-status sigp with a store-status-at-address sigp in
smp_save_dump_cpus() and smp_store_status(). In both cases the target
CPU is already stopped and store-status-at-address avoids the detour
via the absolute zero page.

For kexec simplify s390_reset_system and call store_status() before
the prefix register of the boot CPU has been set to zero. Use STPX
to store the prefix register and remove dump_prefix_page.

Acked-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/fpu/internal.h |  10 +---
 arch/s390/include/asm/ipl.h          |   3 +-
 arch/s390/include/asm/reset.h        |   3 +-
 arch/s390/include/asm/smp.h          |   2 +-
 arch/s390/kernel/early.c             |   9 +++
 arch/s390/kernel/ipl.c               |  17 +-----
 arch/s390/kernel/machine_kexec.c     | 104 ++++++++++++++++++--------------
 arch/s390/kernel/reipl.S             |  37 ++++++------
 arch/s390/kernel/setup.c             |   2 +
 arch/s390/kernel/smp.c               | 112 +++++++++++++++++++----------------
 10 files changed, 157 insertions(+), 142 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/fpu/internal.h b/arch/s390/include/asm/fpu/internal.h
index 2559b16da525..ea91ddfe54eb 100644
--- a/arch/s390/include/asm/fpu/internal.h
+++ b/arch/s390/include/asm/fpu/internal.h
@@ -12,21 +12,13 @@
 #include <asm/ctl_reg.h>
 #include <asm/fpu/types.h>
 
-static inline void save_vx_regs_safe(__vector128 *vxrs)
+static inline void save_vx_regs(__vector128 *vxrs)
 {
-	unsigned long cr0, flags;
-
-	flags = arch_local_irq_save();
-	__ctl_store(cr0, 0, 0);
-	__ctl_set_bit(0, 17);
-	__ctl_set_bit(0, 18);
 	asm volatile(
 		"	la	1,%0\n"
 		"	.word	0xe70f,0x1000,0x003e\n"	/* vstm 0,15,0(1) */
 		"	.word	0xe70f,0x1100,0x0c3e\n"	/* vstm 16,31,256(1) */
 		: "=Q" (*(struct vx_array *) vxrs) : : "1");
-	__ctl_load(cr0, 0, 0);
-	arch_local_irq_restore(flags);
 }
 
 static inline void convert_vx_to_fp(freg_t *fprs, __vector128 *vxrs)
diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h
index 86634e71b69f..1dc55db8cd81 100644
--- a/arch/s390/include/asm/ipl.h
+++ b/arch/s390/include/asm/ipl.h
@@ -87,7 +87,6 @@ struct ipl_parameter_block {
  * IPL validity flags
  */
 extern u32 ipl_flags;
-extern u32 dump_prefix_page;
 
 struct dump_save_areas {
 	struct save_area_ext **areas;
@@ -176,7 +175,7 @@ enum diag308_rc {
 
 extern int diag308(unsigned long subcode, void *addr);
 extern void diag308_reset(void);
-extern void store_status(void);
+extern void store_status(void (*fn)(void *), void *data);
 extern void lgr_info_log(void);
 
 #endif /* _ASM_S390_IPL_H */
diff --git a/arch/s390/include/asm/reset.h b/arch/s390/include/asm/reset.h
index 72786067b300..fe11fa88a0e0 100644
--- a/arch/s390/include/asm/reset.h
+++ b/arch/s390/include/asm/reset.h
@@ -15,6 +15,5 @@ struct reset_call {
 
 extern void register_reset_call(struct reset_call *reset);
 extern void unregister_reset_call(struct reset_call *reset);
-extern void s390_reset_system(void (*fn_pre)(void),
-			      void (*fn_post)(void *), void *data);
+extern void s390_reset_system(void);
 #endif /* _ASM_S390_RESET_H */
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index 5df26b11cf47..0cc383b9be7f 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -18,6 +18,7 @@
 extern struct mutex smp_cpu_state_mutex;
 extern unsigned int smp_cpu_mt_shift;
 extern unsigned int smp_cpu_mtid;
+extern __vector128 __initdata boot_cpu_vector_save_area[__NUM_VXRS];
 
 extern int __cpu_up(unsigned int cpu, struct task_struct *tidle);
 
@@ -55,7 +56,6 @@ static inline int smp_store_status(int cpu) { return 0; }
 static inline int smp_vcpu_scheduled(int cpu) { return 1; }
 static inline void smp_yield_cpu(int cpu) { }
 static inline void smp_fill_possible_mask(void) { }
-static inline void smp_save_dump_cpus(void) { }
 
 #endif /* CONFIG_SMP */
 
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 3c31609df959..20a5caf6d981 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -335,6 +335,14 @@ static __init void detect_machine_facilities(void)
 	}
 }
 
+static inline void save_vector_registers(void)
+{
+#ifdef CONFIG_CRASH_DUMP
+	if (test_facility(129))
+		save_vx_regs(boot_cpu_vector_save_area);
+#endif
+}
+
 static int __init disable_vector_extension(char *str)
 {
 	S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX;
@@ -451,6 +459,7 @@ void __init startup_init(void)
 	detect_diag9c();
 	detect_diag44();
 	detect_machine_facilities();
+	save_vector_registers();
 	setup_topology();
 	sclp_early_detect();
 	lockdep_on();
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index b1f0a90f933b..26d58cf72573 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2039,10 +2039,7 @@ static void do_reset_calls(void)
 		reset->fn();
 }
 
-u32 dump_prefix_page;
-
-void s390_reset_system(void (*fn_pre)(void),
-		       void (*fn_post)(void *), void *data)
+void s390_reset_system(void)
 {
 	struct _lowcore *lc;
 
@@ -2051,9 +2048,6 @@ void s390_reset_system(void (*fn_pre)(void),
 	/* Stack for interrupt/machine check handler */
 	lc->panic_stack = S390_lowcore.panic_stack;
 
-	/* Save prefix page address for dump case */
-	dump_prefix_page = (u32)(unsigned long) lc;
-
 	/* Disable prefixing */
 	set_prefix(0);
 
@@ -2077,14 +2071,5 @@ void s390_reset_system(void (*fn_pre)(void),
 	S390_lowcore.subchannel_id = 0;
 	S390_lowcore.subchannel_nr = 0;
 
-	/* Store status at absolute zero */
-	store_status();
-
-	/* Call function before reset */
-	if (fn_pre)
-		fn_pre();
 	do_reset_calls();
-	/* Call function after reset */
-	if (fn_post)
-		fn_post(data);
 }
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index bf2cd699556f..2f1b7217c25c 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -34,40 +34,6 @@ extern const unsigned long long relocate_kernel_len;
 
 #ifdef CONFIG_CRASH_DUMP
 
-/*
- * Initialize CPU ELF notes
- */
-static void setup_regs(void)
-{
-	struct save_area *sa, *sa_0;
-	unsigned long prefix;
-	int cpu, this_cpu;
-
-	/* setup_regs is called with the prefix register = 0 */
-	sa_0 = (struct save_area *) __LC_FPREGS_SAVE_AREA;
-
-	/* Get status of this CPU out of absolute zero */
-	prefix = (unsigned long) S390_lowcore.prefixreg_save_area;
-	sa = (struct save_area *)(prefix + __LC_FPREGS_SAVE_AREA);
-	memcpy(sa, sa_0, sizeof(struct save_area));
-	if (MACHINE_HAS_VX) {
-		struct _lowcore *lc = (struct _lowcore *) prefix;
-		save_vx_regs_safe((void *) lc->vector_save_area_addr);
-	}
-
-	/* Get status of the other CPUs */
-	this_cpu = smp_find_processor_id(stap());
-	for_each_online_cpu(cpu) {
-		if (cpu == this_cpu)
-			continue;
-		if (smp_store_status(cpu))
-			continue;
-		prefix = (unsigned long) S390_lowcore.prefixreg_save_area;
-		sa = (struct save_area *)(prefix + __LC_FPREGS_SAVE_AREA);
-		memcpy(sa, sa_0, sizeof(struct save_area));
-	}
-}
-
 /*
  * PM notifier callback for kdump
  */
@@ -99,14 +65,66 @@ static int __init machine_kdump_pm_init(void)
 arch_initcall(machine_kdump_pm_init);
 
 /*
- * Start kdump: We expect here that a store status has been done on our CPU
+ * Reset the system, copy boot CPU registers to absolute zero,
+ * and jump to the kdump image
  */
 static void __do_machine_kdump(void *image)
 {
-	int (*start_kdump)(int) = (void *)((struct kimage *) image)->start;
+	int (*start_kdump)(int);
+	unsigned long prefix;
+
+	/* store_status() saved the prefix register to lowcore */
+	prefix = (unsigned long) S390_lowcore.prefixreg_save_area;
+
+	/* Now do the reset  */
+	s390_reset_system();
+
+	/*
+	 * Copy dump CPU store status info to absolute zero.
+	 * This need to be done *after* s390_reset_system set the
+	 * prefix register of this CPU to zero
+	 */
+	memcpy((void *) __LC_FPREGS_SAVE_AREA,
+	       (void *)(prefix + __LC_FPREGS_SAVE_AREA), 512);
 
 	__load_psw_mask(PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA);
+	start_kdump = (void *)((struct kimage *) image)->start;
 	start_kdump(1);
+
+	/* Die if start_kdump returns */
+	disabled_wait((unsigned long) __builtin_return_address(0));
+}
+
+/*
+ * Start kdump: create a LGR log entry, store status of all CPUs and
+ * branch to __do_machine_kdump.
+ */
+static noinline void __machine_kdump(void *image)
+{
+	int this_cpu, cpu;
+
+	lgr_info_log();
+	/* Get status of the other CPUs */
+	this_cpu = smp_find_processor_id(stap());
+	for_each_online_cpu(cpu) {
+		if (cpu == this_cpu)
+			continue;
+		if (smp_store_status(cpu))
+			continue;
+	}
+	/* Store status of the boot CPU */
+	if (MACHINE_HAS_VX)
+		save_vx_regs((void *) &S390_lowcore.vector_save_area);
+	/*
+	 * To create a good backchain for this CPU in the dump store_status
+	 * is passed the address of a function. The address is saved into
+	 * the PSW save area of the boot CPU and the function is invoked as
+	 * a tail call of store_status. The backchain in the dump will look
+	 * like this:
+	 *   restart_int_handler ->  __machine_kexec -> __do_machine_kdump
+	 * The call to store_status() will not return.
+	 */
+	store_status(__do_machine_kdump, image);
 }
 #endif
 
@@ -229,10 +247,14 @@ static void __do_machine_kexec(void *data)
 	relocate_kernel_t data_mover;
 	struct kimage *image = data;
 
+	s390_reset_system();
 	data_mover = (relocate_kernel_t) page_to_phys(image->control_code_page);
 
 	/* Call the moving routine */
 	(*data_mover)(&image->head, image->start);
+
+	/* Die if kexec returns */
+	disabled_wait((unsigned long) __builtin_return_address(0));
 }
 
 /*
@@ -245,14 +267,10 @@ static void __machine_kexec(void *data)
 	tracing_off();
 	debug_locks_off();
 #ifdef CONFIG_CRASH_DUMP
-	if (((struct kimage *) data)->type == KEXEC_TYPE_CRASH) {
-
-		lgr_info_log();
-		s390_reset_system(setup_regs, __do_machine_kdump, data);
-	} else
+	if (((struct kimage *) data)->type == KEXEC_TYPE_CRASH)
+		__machine_kdump(data);
 #endif
-		s390_reset_system(NULL, __do_machine_kexec, data);
-	disabled_wait((unsigned long) __builtin_return_address(0));
+	__do_machine_kexec(data);
 }
 
 /*
diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S
index b75a521e4fab..89ea8c213d82 100644
--- a/arch/s390/kernel/reipl.S
+++ b/arch/s390/kernel/reipl.S
@@ -9,12 +9,11 @@
 #include <asm/sigp.h>
 
 #
-# store_status
+# Issue "store status" for the current CPU to its prefix page
+# and call passed function afterwards
 #
-# Prerequisites to run this function:
-# - Prefix register is set to zero
-# - Original prefix register is stored in "dump_prefix_page"
-# - Lowcore protection is off
+# r2 = Function to be called after store status
+# r3 = Parameter for function
 #
 ENTRY(store_status)
 	/* Save register one and load save area base */
@@ -53,23 +52,23 @@ ENTRY(store_status)
 	/* CPU timer */
 	lghi	%r1,__LC_CPU_TIMER_SAVE_AREA
 	stpt	0(%r1)
-	/* Saved prefix register */
+	/* Store prefix register */
 	lghi	%r1,__LC_PREFIX_SAVE_AREA
-	larl	%r2,dump_prefix_page
-	mvc	0(4,%r1),0(%r2)
+	stpx	0(%r1)
 	/* Clock comparator - seven bytes */
 	lghi	%r1,__LC_CLOCK_COMP_SAVE_AREA
-	larl	%r2,.Lclkcmp
-	stckc	0(%r2)
-	mvc	1(7,%r1),1(%r2)
+	larl	%r4,.Lclkcmp
+	stckc	0(%r4)
+	mvc	1(7,%r1),1(%r4)
 	/* Program status word */
 	lghi	%r1,__LC_PSW_SAVE_AREA
-	epsw	%r2,%r3
-	st	%r2,0(%r1)
-	st	%r3,4(%r1)
-	larl	%r2,store_status
+	epsw	%r4,%r5
+	st	%r4,0(%r1)
+	st	%r5,4(%r1)
 	stg	%r2,8(%r1)
-	br	%r14
+	lgr	%r1,%r2
+	lgr	%r2,%r3
+	br	%r1
 
 	.section .bss
 	.align	8
@@ -84,9 +83,11 @@ ENTRY(store_status)
 ENTRY(do_reipl_asm)
 		basr	%r13,0
 .Lpg0:		lpswe	.Lnewpsw-.Lpg0(%r13)
-.Lpg1:		brasl	%r14,store_status
+.Lpg1:		lgr	%r3,%r2
+		larl	%r2,.Lstatus
+		brasl	%r14,store_status
 
-		lctlg	%c6,%c6,.Lall-.Lpg0(%r13)
+.Lstatus:	lctlg	%c6,%c6,.Lall-.Lpg0(%r13)
 		lgr	%r1,%r2
 		mvc	__LC_PGM_NEW_PSW(16),.Lpcnew-.Lpg0(%r13)
 		stsch	.Lschib-.Lpg0(%r13)
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 8f5107d6ebb3..22756bb0819e 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -865,11 +865,13 @@ void __init setup_arch(char **cmdline_p)
 
 	check_initrd();
 	reserve_crashkernel();
+#ifdef CONFIG_CRASH_DUMP
 	/*
 	 * Be aware that smp_save_dump_cpus() triggers a system reset.
 	 * Therefore CPU and device initialization should be done afterwards.
 	 */
 	smp_save_dump_cpus();
+#endif
 
 	setup_resources();
 	setup_vmcoreinfo();
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index d49a8cb404c2..2a69077d482c 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -80,6 +80,10 @@ EXPORT_SYMBOL(smp_cpu_mt_shift);
 unsigned int smp_cpu_mtid;
 EXPORT_SYMBOL(smp_cpu_mtid);
 
+#ifdef CONFIG_CRASH_DUMP
+__vector128 __initdata boot_cpu_vector_save_area[__NUM_VXRS];
+#endif
+
 static unsigned int smp_max_threads __initdata = -1U;
 
 static int __init early_nosmt(char *s)
@@ -105,8 +109,7 @@ DEFINE_MUTEX(smp_cpu_state_mutex);
 /*
  * Signal processor helper functions.
  */
-static inline int __pcpu_sigp_relax(u16 addr, u8 order, unsigned long parm,
-				    u32 *status)
+static inline int __pcpu_sigp_relax(u16 addr, u8 order, unsigned long parm)
 {
 	int cc;
 
@@ -538,53 +541,24 @@ EXPORT_SYMBOL(smp_ctl_clear_bit);
 
 #ifdef CONFIG_CRASH_DUMP
 
-static void __init __smp_store_cpu_state(struct save_area_ext *sa_ext,
-					 u16 address, int is_boot_cpu)
-{
-	void *lc = (void *)(unsigned long) store_prefix();
-	unsigned long vx_sa;
-
-	if (is_boot_cpu) {
-		/* Copy the registers of the boot CPU. */
-		copy_oldmem_kernel(&sa_ext->sa, (void *) __LC_FPREGS_SAVE_AREA,
-				   sizeof(sa_ext->sa));
-		if (MACHINE_HAS_VX)
-			save_vx_regs_safe(sa_ext->vx_regs);
-		return;
-	}
-	/* Get the registers of a non-boot cpu. */
-	__pcpu_sigp_relax(address, SIGP_STOP_AND_STORE_STATUS, 0, NULL);
-	memcpy_real(&sa_ext->sa, lc + __LC_FPREGS_SAVE_AREA, sizeof(sa_ext->sa));
-	if (!MACHINE_HAS_VX)
-		return;
-	/* Get the VX registers */
-	vx_sa = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-	if (!vx_sa)
-		panic("could not allocate memory for VX save area\n");
-	__pcpu_sigp_relax(address, SIGP_STORE_ADDITIONAL_STATUS, vx_sa, NULL);
-	memcpy(sa_ext->vx_regs, (void *) vx_sa, sizeof(sa_ext->vx_regs));
-	memblock_free(vx_sa, PAGE_SIZE);
-}
-
 int smp_store_status(int cpu)
 {
-	unsigned long vx_sa;
-	struct pcpu *pcpu;
+	struct pcpu *pcpu = pcpu_devices + cpu;
+	unsigned long pa;
 
-	pcpu = pcpu_devices + cpu;
-	if (__pcpu_sigp_relax(pcpu->address, SIGP_STOP_AND_STORE_STATUS,
-			      0, NULL) != SIGP_CC_ORDER_CODE_ACCEPTED)
+	pa = __pa(&pcpu->lowcore->floating_pt_save_area);
+	if (__pcpu_sigp_relax(pcpu->address, SIGP_STORE_STATUS_AT_ADDRESS,
+			      pa) != SIGP_CC_ORDER_CODE_ACCEPTED)
 		return -EIO;
 	if (!MACHINE_HAS_VX)
 		return 0;
-	vx_sa = __pa(pcpu->lowcore->vector_save_area_addr);
-	__pcpu_sigp_relax(pcpu->address, SIGP_STORE_ADDITIONAL_STATUS,
-			  vx_sa, NULL);
+	pa = __pa(pcpu->lowcore->vector_save_area_addr);
+	if (__pcpu_sigp_relax(pcpu->address, SIGP_STORE_ADDITIONAL_STATUS,
+			      pa) != SIGP_CC_ORDER_CODE_ACCEPTED)
+		return -EIO;
 	return 0;
 }
 
-#endif /* CONFIG_CRASH_DUMP */
-
 /*
  * Collect CPU state of the previous, crashed system.
  * There are four cases:
@@ -593,7 +567,7 @@ int smp_store_status(int cpu)
  *    The state for all CPUs except the boot CPU needs to be collected
  *    with sigp stop-and-store-status. The boot CPU state is located in
  *    the absolute lowcore of the memory stored in the HSA. The zcore code
- *    will allocate the save area and copy the boot CPU state from the HSA.
+ *    will copy the boot CPU state from the HSA.
  * 2) stand-alone kdump for SCSI (zfcp dump with swapped memory)
  *    condition: OLDMEM_BASE != NULL && ipl_info.type == IPL_TYPE_FCP_DUMP
  *    The state for all CPUs except the boot CPU needs to be collected
@@ -611,21 +585,49 @@ int smp_store_status(int cpu)
  *    This case does not exist for s390 anymore, setup_arch explicitly
  *    deactivates the elfcorehdr= kernel parameter
  */
+static __init void smp_save_cpu_vxrs(struct save_area_ext *sa_ext, u16 addr,
+				     bool is_boot_cpu, unsigned long page)
+{
+	__vector128 *vxrs = (__vector128 *) page;
+
+	if (is_boot_cpu)
+		vxrs = boot_cpu_vector_save_area;
+	else
+		__pcpu_sigp_relax(addr, SIGP_STORE_ADDITIONAL_STATUS, page);
+	memcpy(&sa_ext->vx_regs, vxrs, sizeof(sa_ext->vx_regs));
+}
+
+static __init void smp_save_cpu_regs(struct save_area_ext *sa_ext, u16 addr,
+				     bool is_boot_cpu, unsigned long page)
+{
+	void *regs = (void *) page;
+
+	if (is_boot_cpu)
+		copy_oldmem_kernel(regs, (void *) __LC_FPREGS_SAVE_AREA, 512);
+	else
+		__pcpu_sigp_relax(addr, SIGP_STORE_STATUS_AT_ADDRESS, page);
+	memcpy(&sa_ext->sa, regs, sizeof(sa_ext->sa));
+}
+
 void __init smp_save_dump_cpus(void)
 {
-#ifdef CONFIG_CRASH_DUMP
 	int addr, cpu, boot_cpu_addr, max_cpu_addr;
 	struct save_area_ext *sa_ext;
+	unsigned long page;
 	bool is_boot_cpu;
 
 	if (!(OLDMEM_BASE || ipl_info.type == IPL_TYPE_FCP_DUMP))
 		/* No previous system present, normal boot. */
 		return;
+	/* Allocate a page as dumping area for the store status sigps */
+	page = memblock_alloc_base(PAGE_SIZE, PAGE_SIZE, 1UL << 31);
+	if (!page)
+		panic("could not allocate memory for save area\n");
 	/* Set multi-threading state to the previous system. */
 	pcpu_set_smt(sclp.mtid_prev);
 	max_cpu_addr = SCLP_MAX_CORES << sclp.mtid_prev;
 	for (cpu = 0, addr = 0; addr <= max_cpu_addr; addr++) {
-		if (__pcpu_sigp_relax(addr, SIGP_SENSE, 0, NULL) ==
+		if (__pcpu_sigp_relax(addr, SIGP_SENSE, 0) ==
 		    SIGP_CC_NOT_OPERATIONAL)
 			continue;
 		cpu += 1;
@@ -634,7 +636,7 @@ void __init smp_save_dump_cpus(void)
 	dump_save_areas.count = cpu;
 	boot_cpu_addr = stap();
 	for (cpu = 0, addr = 0; addr <= max_cpu_addr; addr++) {
-		if (__pcpu_sigp_relax(addr, SIGP_SENSE, 0, NULL) ==
+		if (__pcpu_sigp_relax(addr, SIGP_SENSE, 0) ==
 		    SIGP_CC_NOT_OPERATIONAL)
 			continue;
 		sa_ext = (void *) memblock_alloc(sizeof(*sa_ext), 8);
@@ -643,16 +645,24 @@ void __init smp_save_dump_cpus(void)
 			panic("could not allocate memory for save area\n");
 		is_boot_cpu = (addr == boot_cpu_addr);
 		cpu += 1;
-		if (is_boot_cpu && !OLDMEM_BASE)
-			/* Skip boot CPU for standard zfcp dump. */
-			continue;
-		/* Get state for this CPU. */
-		__smp_store_cpu_state(sa_ext, addr, is_boot_cpu);
+		if (MACHINE_HAS_VX)
+			/* Get the vector registers */
+			smp_save_cpu_vxrs(sa_ext, addr, is_boot_cpu, page);
+		/*
+		 * For a zfcp dump OLDMEM_BASE == NULL and the registers
+		 * of the boot CPU are stored in the HSA. To retrieve
+		 * these registers an SCLP request is required which is
+		 * done by drivers/s390/char/zcore.c:init_cpu_info()
+		 */
+		if (!is_boot_cpu || OLDMEM_BASE)
+			/* Get the CPU registers */
+			smp_save_cpu_regs(sa_ext, addr, is_boot_cpu, page);
 	}
+	memblock_free(page, PAGE_SIZE);
 	diag308_reset();
 	pcpu_set_smt(0);
-#endif /* CONFIG_CRASH_DUMP */
 }
+#endif /* CONFIG_CRASH_DUMP */
 
 void smp_cpu_set_polarization(int cpu, int val)
 {
@@ -676,7 +686,7 @@ static struct sclp_core_info *smp_get_core_info(void)
 		for (address = 0;
 		     address < (SCLP_MAX_CORES << smp_cpu_mt_shift);
 		     address += (1U << smp_cpu_mt_shift)) {
-			if (__pcpu_sigp_relax(address, SIGP_SENSE, 0, NULL) ==
+			if (__pcpu_sigp_relax(address, SIGP_SENSE, 0) ==
 			    SIGP_CC_NOT_OPERATIONAL)
 				continue;
 			info->core[info->configured].core_id =
-- 
cgit 


From 1a2c5840acf9f657c9b580d4ee12a4c9db3429cb Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Thu, 29 Oct 2015 10:59:15 +0100
Subject: s390/dump: cleanup CPU save area handling

Introduce save_area_alloc(), save_area_boot_cpu(), save_area_add_regs()
and save_area_add_vxrs to deal with storing the CPU state in case of a
system dump. Remove struct save_area and save_area_ext, and create a new
struct save_area as a local definition to arch/s390/kernel/crash_dump.c.
Copy each individual field from the hardware status area to the save area,
storing the minimum of required data.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/ipl.h     |  11 +-
 arch/s390/include/asm/lowcore.h |  21 ----
 arch/s390/kernel/crash_dump.c   | 263 ++++++++++++++++++----------------------
 arch/s390/kernel/smp.c          |  37 +++---
 4 files changed, 140 insertions(+), 192 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h
index 1dc55db8cd81..6fc44dca193e 100644
--- a/arch/s390/include/asm/ipl.h
+++ b/arch/s390/include/asm/ipl.h
@@ -88,12 +88,11 @@ struct ipl_parameter_block {
  */
 extern u32 ipl_flags;
 
-struct dump_save_areas {
-	struct save_area_ext **areas;
-	int count;
-};
-
-extern struct dump_save_areas dump_save_areas;
+struct save_area;
+struct save_area * __init save_area_alloc(bool is_boot_cpu);
+struct save_area * __init save_area_boot_cpu(void);
+void __init save_area_add_regs(struct save_area *, void *regs);
+void __init save_area_add_vxrs(struct save_area *, __vector128 *vxrs);
 
 extern void do_reipl(void);
 extern void do_halt(void);
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index afe1cfebf1a4..5dbbf199ba2e 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -16,27 +16,6 @@
 #define LC_ORDER 1
 #define LC_PAGES 2
 
-struct save_area {
-	u64	fp_regs[16];
-	u64	gp_regs[16];
-	u8	psw[16];
-	u8	pad1[8];
-	u32	pref_reg;
-	u32	fp_ctrl_reg;
-	u8	pad2[4];
-	u32	tod_reg;
-	u64	timer;
-	u64	clk_cmp;
-	u8	pad3[8];
-	u32	acc_regs[16];
-	u64	ctrl_regs[16];
-} __packed;
-
-struct save_area_ext {
-	struct save_area	sa;
-	__vector128		vx_regs[32];
-};
-
 struct _lowcore {
 	__u8	pad_0x0000[0x0014-0x0000];	/* 0x0000 */
 	__u32	ipl_parmblock_ptr;		/* 0x0014 */
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 0d59c0705c4f..823ed6ab53c8 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/bootmem.h>
 #include <linux/elf.h>
+#include <asm/asm-offsets.h>
 #include <linux/memblock.h>
 #include <asm/os_info.h>
 #include <asm/elf.h>
@@ -32,7 +33,84 @@ static struct memblock_type oldmem_type = {
 	.regions = &oldmem_region,
 };
 
-struct dump_save_areas dump_save_areas;
+struct save_area {
+	struct list_head list;
+	u64 psw[2];
+	u64 ctrs[16];
+	u64 gprs[16];
+	u32 acrs[16];
+	u64 fprs[16];
+	u32 fpc;
+	u32 prefix;
+	u64 todpreg;
+	u64 timer;
+	u64 todcmp;
+	u64 vxrs_low[16];
+	__vector128 vxrs_high[16];
+};
+
+static LIST_HEAD(dump_save_areas);
+
+/*
+ * Allocate a save area
+ */
+struct save_area * __init save_area_alloc(bool is_boot_cpu)
+{
+	struct save_area *sa;
+
+	sa = (void *) memblock_alloc(sizeof(*sa), 8);
+	if (!sa)
+		return NULL;
+	if (is_boot_cpu)
+		list_add(&sa->list, &dump_save_areas);
+	else
+		list_add_tail(&sa->list, &dump_save_areas);
+	return sa;
+}
+
+/*
+ * Return the address of the save area for the boot CPU
+ */
+struct save_area * __init save_area_boot_cpu(void)
+{
+	if (list_empty(&dump_save_areas))
+		return NULL;
+	return list_first_entry(&dump_save_areas, struct save_area, list);
+}
+
+/*
+ * Copy CPU registers into the save area
+ */
+void __init save_area_add_regs(struct save_area *sa, void *regs)
+{
+	struct _lowcore *lc;
+
+	lc = (struct _lowcore *)(regs - __LC_FPREGS_SAVE_AREA);
+	memcpy(&sa->psw, &lc->psw_save_area, sizeof(sa->psw));
+	memcpy(&sa->ctrs, &lc->cregs_save_area, sizeof(sa->ctrs));
+	memcpy(&sa->gprs, &lc->gpregs_save_area, sizeof(sa->gprs));
+	memcpy(&sa->acrs, &lc->access_regs_save_area, sizeof(sa->acrs));
+	memcpy(&sa->fprs, &lc->floating_pt_save_area, sizeof(sa->fprs));
+	memcpy(&sa->fpc, &lc->fpt_creg_save_area, sizeof(sa->fpc));
+	memcpy(&sa->prefix, &lc->prefixreg_save_area, sizeof(sa->prefix));
+	memcpy(&sa->todpreg, &lc->tod_progreg_save_area, sizeof(sa->todpreg));
+	memcpy(&sa->timer, &lc->cpu_timer_save_area, sizeof(sa->timer));
+	memcpy(&sa->todcmp, &lc->clock_comp_save_area, sizeof(sa->todcmp));
+}
+
+/*
+ * Copy vector registers into the save area
+ */
+void __init save_area_add_vxrs(struct save_area *sa, __vector128 *vxrs)
+{
+	int i;
+
+	/* Copy lower halves of vector registers 0-15 */
+	for (i = 0; i < 16; i++)
+		memcpy(&sa->vxrs_low[i], &vxrs[i].u[2], 8);
+	/* Copy vector registers 16-31 */
+	memcpy(sa->vxrs_high, vxrs + 16, 16 * sizeof(__vector128));
+}
 
 /*
  * Return physical address for virtual address
@@ -232,8 +310,8 @@ static void *kzalloc_panic(int len)
 /*
  * Initialize ELF note
  */
-static void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len,
-		     const char *name)
+static void *nt_init_name(void *buf, Elf64_Word type, void *desc, int d_len,
+			  const char *name)
 {
 	Elf64_Nhdr *note;
 	u64 len;
@@ -253,137 +331,42 @@ static void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len,
 	return PTR_ADD(buf, len);
 }
 
-/*
- * Initialize prstatus note
- */
-static void *nt_prstatus(void *ptr, struct save_area *sa)
+static inline void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len)
 {
-	struct elf_prstatus nt_prstatus;
-	static int cpu_nr = 1;
-
-	memset(&nt_prstatus, 0, sizeof(nt_prstatus));
-	memcpy(&nt_prstatus.pr_reg.gprs, sa->gp_regs, sizeof(sa->gp_regs));
-	memcpy(&nt_prstatus.pr_reg.psw, sa->psw, sizeof(sa->psw));
-	memcpy(&nt_prstatus.pr_reg.acrs, sa->acc_regs, sizeof(sa->acc_regs));
-	nt_prstatus.pr_pid = cpu_nr;
-	cpu_nr++;
-
-	return nt_init(ptr, NT_PRSTATUS, &nt_prstatus, sizeof(nt_prstatus),
-			 "CORE");
+	return nt_init_name(buf, type, desc, d_len, KEXEC_CORE_NOTE_NAME);
 }
 
 /*
- * Initialize fpregset (floating point) note
+ * Fill ELF notes for one CPU with save area registers
  */
-static void *nt_fpregset(void *ptr, struct save_area *sa)
+static void *fill_cpu_elf_notes(void *ptr, int cpu, struct save_area *sa)
 {
+	struct elf_prstatus nt_prstatus;
 	elf_fpregset_t nt_fpregset;
 
+	/* Prepare prstatus note */
+	memset(&nt_prstatus, 0, sizeof(nt_prstatus));
+	memcpy(&nt_prstatus.pr_reg.gprs, sa->gprs, sizeof(sa->gprs));
+	memcpy(&nt_prstatus.pr_reg.psw, sa->psw, sizeof(sa->psw));
+	memcpy(&nt_prstatus.pr_reg.acrs, sa->acrs, sizeof(sa->acrs));
+	nt_prstatus.pr_pid = cpu;
+	/* Prepare fpregset (floating point) note */
 	memset(&nt_fpregset, 0, sizeof(nt_fpregset));
-	memcpy(&nt_fpregset.fpc, &sa->fp_ctrl_reg, sizeof(sa->fp_ctrl_reg));
-	memcpy(&nt_fpregset.fprs, &sa->fp_regs, sizeof(sa->fp_regs));
-
-	return nt_init(ptr, NT_PRFPREG, &nt_fpregset, sizeof(nt_fpregset),
-		       "CORE");
-}
-
-/*
- * Initialize timer note
- */
-static void *nt_s390_timer(void *ptr, struct save_area *sa)
-{
-	return nt_init(ptr, NT_S390_TIMER, &sa->timer, sizeof(sa->timer),
-			 KEXEC_CORE_NOTE_NAME);
-}
-
-/*
- * Initialize TOD clock comparator note
- */
-static void *nt_s390_tod_cmp(void *ptr, struct save_area *sa)
-{
-	return nt_init(ptr, NT_S390_TODCMP, &sa->clk_cmp,
-		       sizeof(sa->clk_cmp), KEXEC_CORE_NOTE_NAME);
-}
-
-/*
- * Initialize TOD programmable register note
- */
-static void *nt_s390_tod_preg(void *ptr, struct save_area *sa)
-{
-	return nt_init(ptr, NT_S390_TODPREG, &sa->tod_reg,
-		       sizeof(sa->tod_reg), KEXEC_CORE_NOTE_NAME);
-}
-
-/*
- * Initialize control register note
- */
-static void *nt_s390_ctrs(void *ptr, struct save_area *sa)
-{
-	return nt_init(ptr, NT_S390_CTRS, &sa->ctrl_regs,
-		       sizeof(sa->ctrl_regs), KEXEC_CORE_NOTE_NAME);
-}
-
-/*
- * Initialize prefix register note
- */
-static void *nt_s390_prefix(void *ptr, struct save_area *sa)
-{
-	return nt_init(ptr, NT_S390_PREFIX, &sa->pref_reg,
-			 sizeof(sa->pref_reg), KEXEC_CORE_NOTE_NAME);
-}
-
-/*
- * Initialize vxrs high note (full 128 bit VX registers 16-31)
- */
-static void *nt_s390_vx_high(void *ptr, __vector128 *vx_regs)
-{
-	return nt_init(ptr, NT_S390_VXRS_HIGH, &vx_regs[16],
-		       16 * sizeof(__vector128), KEXEC_CORE_NOTE_NAME);
-}
-
-/*
- * Initialize vxrs low note (lower halves of VX registers 0-15)
- */
-static void *nt_s390_vx_low(void *ptr, __vector128 *vx_regs)
-{
-	Elf64_Nhdr *note;
-	u64 len;
-	int i;
-
-	note = (Elf64_Nhdr *)ptr;
-	note->n_namesz = strlen(KEXEC_CORE_NOTE_NAME) + 1;
-	note->n_descsz = 16 * 8;
-	note->n_type = NT_S390_VXRS_LOW;
-	len = sizeof(Elf64_Nhdr);
-
-	memcpy(ptr + len, KEXEC_CORE_NOTE_NAME, note->n_namesz);
-	len = roundup(len + note->n_namesz, 4);
-
-	ptr += len;
-	/* Copy lower halves of SIMD registers 0-15 */
-	for (i = 0; i < 16; i++) {
-		memcpy(ptr, &vx_regs[i].u[2], 8);
-		ptr += 8;
-	}
-	return ptr;
-}
-
-/*
- * Fill ELF notes for one CPU with save area registers
- */
-static void *fill_cpu_elf_notes(void *ptr, struct save_area *sa,
-				__vector128 *vx_regs)
-{
-	ptr = nt_prstatus(ptr, sa);
-	ptr = nt_fpregset(ptr, sa);
-	ptr = nt_s390_timer(ptr, sa);
-	ptr = nt_s390_tod_cmp(ptr, sa);
-	ptr = nt_s390_tod_preg(ptr, sa);
-	ptr = nt_s390_ctrs(ptr, sa);
-	ptr = nt_s390_prefix(ptr, sa);
-	if (MACHINE_HAS_VX && vx_regs) {
-		ptr = nt_s390_vx_low(ptr, vx_regs);
-		ptr = nt_s390_vx_high(ptr, vx_regs);
+	memcpy(&nt_fpregset.fpc, &sa->fpc, sizeof(sa->fpc));
+	memcpy(&nt_fpregset.fprs, &sa->fprs, sizeof(sa->fprs));
+	/* Create ELF notes for the CPU */
+	ptr = nt_init(ptr, NT_PRSTATUS, &nt_prstatus, sizeof(nt_prstatus));
+	ptr = nt_init(ptr, NT_PRFPREG, &nt_fpregset, sizeof(nt_fpregset));
+	ptr = nt_init(ptr, NT_S390_TIMER, &sa->timer, sizeof(sa->timer));
+	ptr = nt_init(ptr, NT_S390_TODCMP, &sa->todcmp, sizeof(sa->todcmp));
+	ptr = nt_init(ptr, NT_S390_TODPREG, &sa->todpreg, sizeof(sa->todpreg));
+	ptr = nt_init(ptr, NT_S390_CTRS, &sa->ctrs, sizeof(sa->ctrs));
+	ptr = nt_init(ptr, NT_S390_PREFIX, &sa->prefix, sizeof(sa->prefix));
+	if (MACHINE_HAS_VX) {
+		ptr = nt_init(ptr, NT_S390_VXRS_HIGH,
+			      &sa->vxrs_high, sizeof(sa->vxrs_high));
+		ptr = nt_init(ptr, NT_S390_VXRS_LOW,
+			      &sa->vxrs_low, sizeof(sa->vxrs_low));
 	}
 	return ptr;
 }
@@ -398,8 +381,7 @@ static void *nt_prpsinfo(void *ptr)
 	memset(&prpsinfo, 0, sizeof(prpsinfo));
 	prpsinfo.pr_sname = 'R';
 	strcpy(prpsinfo.pr_fname, "vmlinux");
-	return nt_init(ptr, NT_PRPSINFO, &prpsinfo, sizeof(prpsinfo),
-		       KEXEC_CORE_NOTE_NAME);
+	return nt_init(ptr, NT_PRPSINFO, &prpsinfo, sizeof(prpsinfo));
 }
 
 /*
@@ -441,7 +423,7 @@ static void *nt_vmcoreinfo(void *ptr)
 		vmcoreinfo = get_vmcoreinfo_old(&size);
 	if (!vmcoreinfo)
 		return ptr;
-	return nt_init(ptr, 0, vmcoreinfo, size, "VMCOREINFO");
+	return nt_init_name(ptr, 0, vmcoreinfo, size, "VMCOREINFO");
 }
 
 /*
@@ -470,13 +452,12 @@ static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt)
  */
 static int get_cpu_cnt(void)
 {
-	int i, cpus = 0;
+	struct save_area *sa;
+	int cpus = 0;
 
-	for (i = 0; i < dump_save_areas.count; i++) {
-		if (dump_save_areas.areas[i]->sa.pref_reg == 0)
-			continue;
-		cpus++;
-	}
+	list_for_each_entry(sa, &dump_save_areas, list)
+		if (sa->prefix != 0)
+			cpus++;
 	return cpus;
 }
 
@@ -521,18 +502,16 @@ static void loads_init(Elf64_Phdr *phdr, u64 loads_offset)
  */
 static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
 {
-	struct save_area_ext *sa_ext;
+	struct save_area *sa;
 	void *ptr_start = ptr;
-	int i;
+	int cpu;
 
 	ptr = nt_prpsinfo(ptr);
 
-	for (i = 0; i < dump_save_areas.count; i++) {
-		sa_ext = dump_save_areas.areas[i];
-		if (sa_ext->sa.pref_reg == 0)
-			continue;
-		ptr = fill_cpu_elf_notes(ptr, &sa_ext->sa, sa_ext->vx_regs);
-	}
+	cpu = 1;
+	list_for_each_entry(sa, &dump_save_areas, list)
+		if (sa->prefix != 0)
+			ptr = fill_cpu_elf_notes(ptr, cpu++, sa);
 	ptr = nt_vmcoreinfo(ptr);
 	memset(phdr, 0, sizeof(*phdr));
 	phdr->p_type = PT_NOTE;
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 2a69077d482c..9da95d8dfc62 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -585,7 +585,7 @@ int smp_store_status(int cpu)
  *    This case does not exist for s390 anymore, setup_arch explicitly
  *    deactivates the elfcorehdr= kernel parameter
  */
-static __init void smp_save_cpu_vxrs(struct save_area_ext *sa_ext, u16 addr,
+static __init void smp_save_cpu_vxrs(struct save_area *sa, u16 addr,
 				     bool is_boot_cpu, unsigned long page)
 {
 	__vector128 *vxrs = (__vector128 *) page;
@@ -594,10 +594,10 @@ static __init void smp_save_cpu_vxrs(struct save_area_ext *sa_ext, u16 addr,
 		vxrs = boot_cpu_vector_save_area;
 	else
 		__pcpu_sigp_relax(addr, SIGP_STORE_ADDITIONAL_STATUS, page);
-	memcpy(&sa_ext->vx_regs, vxrs, sizeof(sa_ext->vx_regs));
+	save_area_add_vxrs(sa, vxrs);
 }
 
-static __init void smp_save_cpu_regs(struct save_area_ext *sa_ext, u16 addr,
+static __init void smp_save_cpu_regs(struct save_area *sa, u16 addr,
 				     bool is_boot_cpu, unsigned long page)
 {
 	void *regs = (void *) page;
@@ -606,13 +606,13 @@ static __init void smp_save_cpu_regs(struct save_area_ext *sa_ext, u16 addr,
 		copy_oldmem_kernel(regs, (void *) __LC_FPREGS_SAVE_AREA, 512);
 	else
 		__pcpu_sigp_relax(addr, SIGP_STORE_STATUS_AT_ADDRESS, page);
-	memcpy(&sa_ext->sa, regs, sizeof(sa_ext->sa));
+	save_area_add_regs(sa, regs);
 }
 
 void __init smp_save_dump_cpus(void)
 {
-	int addr, cpu, boot_cpu_addr, max_cpu_addr;
-	struct save_area_ext *sa_ext;
+	int addr, boot_cpu_addr, max_cpu_addr;
+	struct save_area *sa;
 	unsigned long page;
 	bool is_boot_cpu;
 
@@ -625,29 +625,20 @@ void __init smp_save_dump_cpus(void)
 		panic("could not allocate memory for save area\n");
 	/* Set multi-threading state to the previous system. */
 	pcpu_set_smt(sclp.mtid_prev);
-	max_cpu_addr = SCLP_MAX_CORES << sclp.mtid_prev;
-	for (cpu = 0, addr = 0; addr <= max_cpu_addr; addr++) {
-		if (__pcpu_sigp_relax(addr, SIGP_SENSE, 0) ==
-		    SIGP_CC_NOT_OPERATIONAL)
-			continue;
-		cpu += 1;
-	}
-	dump_save_areas.areas = (void *)memblock_alloc(sizeof(void *) * cpu, 8);
-	dump_save_areas.count = cpu;
 	boot_cpu_addr = stap();
-	for (cpu = 0, addr = 0; addr <= max_cpu_addr; addr++) {
+	max_cpu_addr = SCLP_MAX_CORES << sclp.mtid_prev;
+	for (addr = 0; addr <= max_cpu_addr; addr++) {
 		if (__pcpu_sigp_relax(addr, SIGP_SENSE, 0) ==
 		    SIGP_CC_NOT_OPERATIONAL)
 			continue;
-		sa_ext = (void *) memblock_alloc(sizeof(*sa_ext), 8);
-		dump_save_areas.areas[cpu] = sa_ext;
-		if (!sa_ext)
-			panic("could not allocate memory for save area\n");
 		is_boot_cpu = (addr == boot_cpu_addr);
-		cpu += 1;
+		/* Allocate save area */
+		sa = save_area_alloc(is_boot_cpu);
+		if (!sa)
+			panic("could not allocate memory for save area\n");
 		if (MACHINE_HAS_VX)
 			/* Get the vector registers */
-			smp_save_cpu_vxrs(sa_ext, addr, is_boot_cpu, page);
+			smp_save_cpu_vxrs(sa, addr, is_boot_cpu, page);
 		/*
 		 * For a zfcp dump OLDMEM_BASE == NULL and the registers
 		 * of the boot CPU are stored in the HSA. To retrieve
@@ -656,7 +647,7 @@ void __init smp_save_dump_cpus(void)
 		 */
 		if (!is_boot_cpu || OLDMEM_BASE)
 			/* Get the CPU registers */
-			smp_save_cpu_regs(sa_ext, addr, is_boot_cpu, page);
+			smp_save_cpu_regs(sa, addr, is_boot_cpu, page);
 	}
 	memblock_free(page, PAGE_SIZE);
 	diag308_reset();
-- 
cgit 


From db1c45154a82195ad0b4d45d0e330ebac6883b70 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Thu, 12 Nov 2015 12:51:17 +0100
Subject: s390/spinlock: avoid diagnose loop

The spinlock implementation calls the diagnose 0x9c / 0x44 immediately
if the SIGP sense running reported the target CPU as not running.

The diagnose 0x9c is a hint to the hypervisor to schedule the target
CPU in preference to the source CPU that issued the diagnose. It can
happen that on return from the diagnose the target CPU has not been
scheduled yet, e.g. if the target logical CPU is on another physical
CPU and the hypervisor did not want to migrate the logical CPU.

Avoid the immediate repeat of the diagnose instruction, instead do
the retry loop before the next invocation of diagnose 0x9c.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/lib/spinlock.c | 28 +++++++++++++++++++---------
 1 file changed, 19 insertions(+), 9 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c
index 427aa44b3505..0a68fe04a9e1 100644
--- a/arch/s390/lib/spinlock.c
+++ b/arch/s390/lib/spinlock.c
@@ -41,8 +41,9 @@ void arch_spin_lock_wait(arch_spinlock_t *lp)
 {
 	unsigned int cpu = SPINLOCK_LOCKVAL;
 	unsigned int owner;
-	int count;
+	int count, first_diag;
 
+	first_diag = 1;
 	while (1) {
 		owner = ACCESS_ONCE(lp->lock);
 		/* Try to get the lock if it is free. */
@@ -51,9 +52,10 @@ void arch_spin_lock_wait(arch_spinlock_t *lp)
 				return;
 			continue;
 		}
-		/* Check if the lock owner is running. */
-		if (!smp_vcpu_scheduled(~owner)) {
+		/* First iteration: check if the lock owner is running. */
+		if (first_diag && !smp_vcpu_scheduled(~owner)) {
 			smp_yield_cpu(~owner);
+			first_diag = 0;
 			continue;
 		}
 		/* Loop for a while on the lock value. */
@@ -67,10 +69,13 @@ void arch_spin_lock_wait(arch_spinlock_t *lp)
 			continue;
 		/*
 		 * For multiple layers of hypervisors, e.g. z/VM + LPAR
-		 * yield the CPU if the lock is still unavailable.
+		 * yield the CPU unconditionally. For LPAR rely on the
+		 * sense running status.
 		 */
-		if (!MACHINE_IS_LPAR)
+		if (!MACHINE_IS_LPAR || !smp_vcpu_scheduled(~owner)) {
 			smp_yield_cpu(~owner);
+			first_diag = 0;
+		}
 	}
 }
 EXPORT_SYMBOL(arch_spin_lock_wait);
@@ -79,9 +84,10 @@ void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags)
 {
 	unsigned int cpu = SPINLOCK_LOCKVAL;
 	unsigned int owner;
-	int count;
+	int count, first_diag;
 
 	local_irq_restore(flags);
+	first_diag = 1;
 	while (1) {
 		owner = ACCESS_ONCE(lp->lock);
 		/* Try to get the lock if it is free. */
@@ -92,8 +98,9 @@ void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags)
 			local_irq_restore(flags);
 		}
 		/* Check if the lock owner is running. */
-		if (!smp_vcpu_scheduled(~owner)) {
+		if (first_diag && !smp_vcpu_scheduled(~owner)) {
 			smp_yield_cpu(~owner);
+			first_diag = 0;
 			continue;
 		}
 		/* Loop for a while on the lock value. */
@@ -107,10 +114,13 @@ void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags)
 			continue;
 		/*
 		 * For multiple layers of hypervisors, e.g. z/VM + LPAR
-		 * yield the CPU if the lock is still unavailable.
+		 * yield the CPU unconditionally. For LPAR rely on the
+		 * sense running status.
 		 */
-		if (!MACHINE_IS_LPAR)
+		if (!MACHINE_IS_LPAR || !smp_vcpu_scheduled(~owner)) {
 			smp_yield_cpu(~owner);
+			first_diag = 0;
+		}
 	}
 }
 EXPORT_SYMBOL(arch_spin_lock_wait_flags);
-- 
cgit 


From 406123517b5b3cd5855774f80d685cf393c950f6 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <dahi@linux.vnet.ibm.com>
Date: Thu, 15 Oct 2015 10:47:18 +0200
Subject: s390: get_user_pages_fast() might sleep

Let's annotate it correctly, so we directly get a warning if
we ever were to use it in atomic/preempt_disable/spinlock environment.

Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/mm/gup.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/s390')

diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 12bbf0e8478f..21c74a71e2ab 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -233,6 +233,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	struct mm_struct *mm = current->mm;
 	int nr, ret;
 
+	might_sleep();
 	start &= PAGE_MASK;
 	nr = __get_user_pages_fast(start, nr_pages, write, pages);
 	if (nr == nr_pages)
-- 
cgit 


From 69eea95c48857c9dfcac120d6acea43027627b28 Mon Sep 17 00:00:00 2001
From: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Date: Mon, 16 Nov 2015 14:35:48 +0100
Subject: s390/pci_dma: fix DMA table corruption with > 4 TB main memory

DMA addresses returned from map_page() are calculated by using an iommu
bitmap plus a start_dma offset. The size of this bitmap is based on the main
memory size. If we have more than (4 TB - start_dma) main memory, the DMA
address calculation will also produce addresses > 4 TB. Such addresses
cannot be inserted in the 3-level DMA page table, instead the entries
modulo 4 TB will be overwritten.

Fix this by restricting the iommu bitmap size to (4 TB - start_dma).
Also set zdev->end_dma to the actual end address of the usable
range, instead of the theoretical maximum as reported by the hardware,
which fixes a sanity check in dma_map() and also the IOMMU API domain
geometry aperture calculation.

Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Reviewed-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/pci_dma.h |  2 ++
 arch/s390/pci/pci.c             |  3 +--
 arch/s390/pci/pci_dma.c         | 19 ++++++++++++++-----
 3 files changed, 17 insertions(+), 7 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h
index 1aac41e83ea1..92df3eb8d14e 100644
--- a/arch/s390/include/asm/pci_dma.h
+++ b/arch/s390/include/asm/pci_dma.h
@@ -23,6 +23,8 @@ enum zpci_ioat_dtype {
 #define ZPCI_IOTA_FS_2G			2
 #define ZPCI_KEY			(PAGE_DEFAULT_KEY << 5)
 
+#define ZPCI_TABLE_SIZE_RT	(1UL << 42)
+
 #define ZPCI_IOTA_STO_FLAG	(ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_ST)
 #define ZPCI_IOTA_RTTO_FLAG	(ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RT)
 #define ZPCI_IOTA_RSTO_FLAG	(ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RS)
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 7ef12a3ace3a..11d4f277e9f6 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -701,8 +701,7 @@ static int zpci_restore(struct device *dev)
 		goto out;
 
 	zpci_map_resources(pdev);
-	zpci_register_ioat(zdev, 0, zdev->start_dma + PAGE_OFFSET,
-			   zdev->start_dma + zdev->iommu_size - 1,
+	zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
 			   (u64) zdev->dma_table);
 
 out:
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index d348f2c09a1e..3a40f718baef 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -458,7 +458,19 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 		goto out_clean;
 	}
 
-	zdev->iommu_size = (unsigned long) high_memory - PAGE_OFFSET;
+	/*
+	 * Restrict the iommu bitmap size to the minimum of the following:
+	 * - main memory size
+	 * - 3-level pagetable address limit minus start_dma offset
+	 * - DMA address range allowed by the hardware (clp query pci fn)
+	 *
+	 * Also set zdev->end_dma to the actual end address of the usable
+	 * range, instead of the theoretical maximum as reported by hardware.
+	 */
+	zdev->iommu_size = min3((u64) high_memory,
+				ZPCI_TABLE_SIZE_RT - zdev->start_dma,
+				zdev->end_dma - zdev->start_dma + 1);
+	zdev->end_dma = zdev->start_dma + zdev->iommu_size - 1;
 	zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT;
 	zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8);
 	if (!zdev->iommu_bitmap) {
@@ -466,10 +478,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 		goto out_reg;
 	}
 
-	rc = zpci_register_ioat(zdev,
-				0,
-				zdev->start_dma + PAGE_OFFSET,
-				zdev->start_dma + zdev->iommu_size - 1,
+	rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
 				(u64) zdev->dma_table);
 	if (rc)
 		goto out_reg;
-- 
cgit 


From 561e103002696a17907ac5bbccec551e32de3b7f Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Wed, 18 Nov 2015 17:00:10 +0100
Subject: s390/dis: Fix printing of the register numbers

Since commit b006f19b055f ("lib/vsprintf.c: handle invalid format
specifiers more robustly") I get errors like
[...]
Krnl Code: 00000000004e2410: c00400000000        brcl 0,4e2410
Please remove unsupported %r in format string
[    8.179483] ------------[ cut here ]------------
[    8.179484] WARNING: at lib/vsprintf.c:1781

Turns out that our disassembler relied on %r not being used as format
string. Let's do the proper escaping of our decode buffers.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/dis.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 8140d10c6785..8cb9bfdd3ea8 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -2015,7 +2015,7 @@ void show_code(struct pt_regs *regs)
 			*ptr++ = '\t';
 		ptr += print_insn(ptr, code + start, addr);
 		start += opsize;
-		printk(buffer);
+		printk("%s", buffer);
 		ptr = buffer;
 		ptr += sprintf(ptr, "\n          ");
 		hops++;
@@ -2042,7 +2042,7 @@ void print_fn_code(unsigned char *code, unsigned long len)
 		ptr += print_insn(ptr, code, (unsigned long) code);
 		*ptr++ = '\n';
 		*ptr++ = 0;
-		printk(buffer);
+		printk("%s", buffer);
 		code += opsize;
 		len -= opsize;
 	}
-- 
cgit 


From 3f975df69dba78834471b7133dcb8c8ddf7f986a Mon Sep 17 00:00:00 2001
From: Sascha Silbe <silbe@linux.vnet.ibm.com>
Date: Tue, 24 Nov 2015 16:28:55 +0100
Subject: s390/sclp: Add VT220 support to early sclp console

When running under qemu with the default configuration (-nographic),
there is only a VT220 SCLP console, no line-mode SCLP console. Add
VT220 support to the early SCLP console so the user has a chance to
see critical error messages during early boot.

None of the existing users of _sclp_print_early() check the return
code. Instead of trying to come up with return code semantics when
printing to multiple consoles (any or all of which may fail), we just
drop the return code entirely.

Tested on z/VM (line mode console) and LPAR (VT220 and line mode
console). Tested on qemu/KVM with VT220 console and / or line mode
console.

Signed-off-by: Sascha Silbe <silbe@linux.vnet.ibm.com>
Reviewed-by: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/sclp.h |  2 +-
 arch/s390/kernel/sclp.c      | 65 ++++++++++++++++++++++++++++++++++----------
 2 files changed, 51 insertions(+), 16 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 2ca9c7bc50db..cb691602f295 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -80,6 +80,6 @@ int sclp_pci_deconfigure(u32 fid);
 int memcpy_hsa_kernel(void *dest, unsigned long src, size_t count);
 int memcpy_hsa_user(void __user *dest, unsigned long src, size_t count);
 void sclp_early_detect(void);
-int _sclp_print_early(const char *);
+void _sclp_print_early(const char *);
 
 #endif /* _ASM_S390_SCLP_H */
diff --git a/arch/s390/kernel/sclp.c b/arch/s390/kernel/sclp.c
index 9fe7781a45cd..d88db40bdf15 100644
--- a/arch/s390/kernel/sclp.c
+++ b/arch/s390/kernel/sclp.c
@@ -9,7 +9,11 @@
 #include <asm/processor.h>
 #include <asm/sclp.h>
 
+#define EVTYP_VT220MSG_MASK	0x00000040
+#define EVTYP_MSG_MASK		0x40000000
+
 static char _sclp_work_area[4096] __aligned(PAGE_SIZE);
+static bool have_vt220, have_linemode;
 
 static void _sclp_wait_int(void)
 {
@@ -68,7 +72,7 @@ static int _sclp_setup(int disable)
 		0x00, 0x1c,
 		0x00, 0x00, 0x00, 0x00,	0x00, 0x00, 0x00, 0x00,
 		0x00, 0x04,
-		0x80, 0x00, 0x00, 0x00,	0x40, 0x00, 0x00, 0x00,
+		0x80, 0x00, 0x00, 0x00,	0x40, 0x00, 0x00, 0x40,
 		0x00, 0x00, 0x00, 0x00,	0x00, 0x00, 0x00, 0x00
 	};
 	unsigned int *masks;
@@ -82,13 +86,13 @@ static int _sclp_setup(int disable)
 	rc = _sclp_servc(0x00780005, _sclp_work_area);
 	if (rc)
 		return rc;
-	if ((masks[0] & masks[3]) != masks[0] ||
-	    (masks[1] & masks[2]) != masks[1])
-		return -EIO;
+	have_vt220 = masks[2] & EVTYP_VT220MSG_MASK;
+	have_linemode = masks[2] & EVTYP_MSG_MASK;
 	return 0;
 }
 
-static int _sclp_print(const char *str)
+/* Output multi-line text using SCLP Message interface. */
+static void _sclp_print_lm(const char *str)
 {
 	static unsigned char write_head[] = {
 		/* sccb header */
@@ -143,18 +147,49 @@ static int _sclp_print(const char *str)
 	} while (ch != 0);
 
 	/* SCLP write data */
-	return _sclp_servc(0x00760005, _sclp_work_area);
+	_sclp_servc(0x00760005, _sclp_work_area);
 }
 
-int _sclp_print_early(const char *str)
+/* Output multi-line text (plus a newline) using SCLP VT220
+ * interface.
+ */
+static void _sclp_print_vt220(const char *str)
 {
-	int rc;
+	static unsigned char const write_head[] = {
+		/* sccb header */
+		0x00, 0x0e,
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		/* evbuf header */
+		0x00, 0x06,
+		0x1a, 0x00, 0x00, 0x00,
+	};
+	size_t len = strlen(str);
 
-	rc = _sclp_setup(0);
-	if (rc)
-		return rc;
-	rc = _sclp_print(str);
-	if (rc)
-		return rc;
-	return _sclp_setup(1);
+	if (sizeof(write_head) + len >= sizeof(_sclp_work_area))
+		len = sizeof(_sclp_work_area) - sizeof(write_head) - 1;
+
+	memcpy(_sclp_work_area, write_head, sizeof(write_head));
+	memcpy(_sclp_work_area + sizeof(write_head), str, len);
+	_sclp_work_area[sizeof(write_head) + len] = '\n';
+
+	/* Update length fields in evbuf and sccb headers */
+	*(unsigned short *)(_sclp_work_area + 8) += len + 1;
+	*(unsigned short *)(_sclp_work_area + 0) += len + 1;
+
+	/* SCLP write data */
+	(void)_sclp_servc(0x00760005, _sclp_work_area);
+}
+
+/* Output one or more lines of text on the SCLP console (VT220 and /
+ * or line-mode). All lines get terminated; no need for a trailing LF.
+ */
+void _sclp_print_early(const char *str)
+{
+	if (_sclp_setup(0) != 0)
+		return;
+	if (have_linemode)
+		_sclp_print_lm(str);
+	if (have_vt220)
+		_sclp_print_vt220(str);
+	_sclp_setup(1);
 }
-- 
cgit 


From b8eecf36a47bc5e9569f513a3888d03d82985fbb Mon Sep 17 00:00:00 2001
From: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Date: Wed, 25 Nov 2015 11:54:36 +0100
Subject: s390: add 'install' target to 'make help'

Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Makefile | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'arch/s390')

diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index e8d4423e4f85..647bd14b223e 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -129,4 +129,8 @@ archclean:
 define archhelp
   echo  '* image           - Kernel image for IPL ($(boot)/image)'
   echo	'* bzImage         - Compressed kernel image for IPL ($(boot)/bzImage)'
+  echo	'  install         - Install kernel using'
+  echo	'                    (your) ~/bin/$(INSTALLKERNEL) or'
+  echo	'                    (distribution) /sbin/$(INSTALLKERNEL) or'
+  echo	'                    install to $$(INSTALL_PATH)'
 endef
-- 
cgit 


From 9eb31be33cf84266abd61de0f6d3d1fe609587cf Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Thu, 26 Nov 2015 09:25:35 +0100
Subject: s390: remove is_32bit_task() helper

is_32bit_task() used to be helpful when we still had CONFIG_32BIT.
Since that is gone, it is nowadays identical to is_compat_task().
So remove it.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/compat.h      | 2 +-
 arch/s390/include/asm/elf.h         | 9 +++++----
 arch/s390/include/asm/thread_info.h | 2 --
 3 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index d350ed9d0fbb..352f7bdaf11f 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -284,7 +284,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
 
 static inline int is_compat_task(void)
 {
-	return is_32bit_task();
+	return test_thread_flag(TIF_31BIT);
 }
 
 static inline void __user *arch_compat_alloc_user_space(long len)
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 7730e5b9e7e2..fabebe1e45d9 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -126,6 +126,7 @@ typedef s390_regs elf_gregset_t;
 typedef s390_fp_regs compat_elf_fpregset_t;
 typedef s390_compat_regs compat_elf_gregset_t;
 
+#include <linux/compat.h>
 #include <linux/sched.h>	/* for task_struct */
 #include <asm/mmu_context.h>
 
@@ -159,7 +160,7 @@ extern unsigned int vdso_enabled;
    the loader.  We need to make sure that it is out of the way of the program
    that it will "exec", and that there is sufficient room for the brk. 64-bit
    tasks are aligned to 4GB. */
-#define ELF_ET_DYN_BASE (is_32bit_task() ? \
+#define ELF_ET_DYN_BASE (is_compat_task() ? \
 				(STACK_TOP / 3 * 2) : \
 				(STACK_TOP / 3 * 2) & ~((1UL << 32) - 1))
 
@@ -212,9 +213,9 @@ do {								\
  * of up to 1GB. For 31-bit processes the virtual address space is limited,
  * use no alignment and limit the randomization to 8MB.
  */
-#define BRK_RND_MASK	(is_32bit_task() ? 0x7ffUL : 0x3ffffUL)
-#define MMAP_RND_MASK	(is_32bit_task() ? 0x7ffUL : 0x3ff80UL)
-#define MMAP_ALIGN_MASK	(is_32bit_task() ? 0 : 0x7fUL)
+#define BRK_RND_MASK	(is_compat_task() ? 0x7ffUL : 0x3ffffUL)
+#define MMAP_RND_MASK	(is_compat_task() ? 0x7ffUL : 0x3ff80UL)
+#define MMAP_ALIGN_MASK	(is_compat_task() ? 0 : 0x7fUL)
 #define STACK_RND_MASK	MMAP_RND_MASK
 
 #define ARCH_DLINFO							    \
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 692b9247c019..2fffc2c27581 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -96,6 +96,4 @@ void arch_release_task_struct(struct task_struct *tsk);
 #define _TIF_31BIT		_BITUL(TIF_31BIT)
 #define _TIF_SINGLE_STEP	_BITUL(TIF_SINGLE_STEP)
 
-#define is_32bit_task()		(test_thread_flag(TIF_31BIT))
-
 #endif /* _ASM_THREAD_INFO_H */
-- 
cgit 


From 419123f900dac58fb27ce5285b21074f5300095a Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Thu, 19 Nov 2015 11:09:45 +0100
Subject: s390/spinlock: do not yield to a CPU in udelay/mdelay

It does not make sense to try to relinquish the time slice with diag 0x9c
to a CPU in a state that does not allow to schedule the CPU. The scenario
where this can happen is a CPU waiting in udelay/mdelay while holding a
spin-lock.

Add a CIF bit to tag a CPU in enabled wait and use it to detect that the
yield of a CPU will not be successful and skip the diagnose call.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/processor.h | 12 ++++++++++++
 arch/s390/kernel/entry.S          |  2 ++
 arch/s390/lib/spinlock.c          | 25 +++++++++++++++++--------
 3 files changed, 31 insertions(+), 8 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index b16c3d0a1b9f..5592c94ebe31 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -18,12 +18,14 @@
 #define CIF_NOHZ_DELAY		2	/* delay HZ disable for a tick */
 #define CIF_FPU			3	/* restore FPU registers */
 #define CIF_IGNORE_IRQ		4	/* ignore interrupt (for udelay) */
+#define CIF_ENABLED_WAIT	5	/* in enabled wait state */
 
 #define _CIF_MCCK_PENDING	_BITUL(CIF_MCCK_PENDING)
 #define _CIF_ASCE		_BITUL(CIF_ASCE)
 #define _CIF_NOHZ_DELAY		_BITUL(CIF_NOHZ_DELAY)
 #define _CIF_FPU		_BITUL(CIF_FPU)
 #define _CIF_IGNORE_IRQ		_BITUL(CIF_IGNORE_IRQ)
+#define _CIF_ENABLED_WAIT	_BITUL(CIF_ENABLED_WAIT)
 
 #ifndef __ASSEMBLY__
 
@@ -52,6 +54,16 @@ static inline int test_cpu_flag(int flag)
 	return !!(S390_lowcore.cpu_flags & (1UL << flag));
 }
 
+/*
+ * Test CIF flag of another CPU. The caller needs to ensure that
+ * CPU hotplug can not happen, e.g. by disabling preemption.
+ */
+static inline int test_cpu_flag_of(int flag, int cpu)
+{
+	struct _lowcore *lc = lowcore_ptr[cpu];
+	return !!(lc->cpu_flags & (1UL << flag));
+}
+
 #define arch_needs_cpu() test_cpu_flag(CIF_NOHZ_DELAY)
 
 /*
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 857b6526d298..cd5a191381b9 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -764,6 +764,7 @@ ENTRY(psw_idle)
 	.insn	rsy,0xeb0000000017,%r1,5,__SF_EMPTY+16(%r15)
 .Lpsw_idle_stcctm:
 #endif
+	oi	__LC_CPU_FLAGS+7,_CIF_ENABLED_WAIT
 	STCK	__CLOCK_IDLE_ENTER(%r2)
 	stpt	__TIMER_IDLE_ENTER(%r2)
 .Lpsw_idle_lpsw:
@@ -1146,6 +1147,7 @@ cleanup_critical:
 	.quad	.Lio_done - 4
 
 .Lcleanup_idle:
+	ni	__LC_CPU_FLAGS+7,255-_CIF_ENABLED_WAIT
 	# copy interrupt clock & cpu timer
 	mvc	__CLOCK_IDLE_EXIT(8,%r2),__LC_INT_CLOCK
 	mvc	__TIMER_IDLE_EXIT(8,%r2),__LC_ASYNC_ENTER_TIMER
diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c
index 0a68fe04a9e1..d4549c964589 100644
--- a/arch/s390/lib/spinlock.c
+++ b/arch/s390/lib/spinlock.c
@@ -37,6 +37,15 @@ static inline void _raw_compare_and_delay(unsigned int *lock, unsigned int old)
 	asm(".insn rsy,0xeb0000000022,%0,0,%1" : : "d" (old), "Q" (*lock));
 }
 
+static inline int cpu_is_preempted(int cpu)
+{
+	if (test_cpu_flag_of(CIF_ENABLED_WAIT, cpu))
+		return 0;
+	if (smp_vcpu_scheduled(cpu))
+		return 0;
+	return 1;
+}
+
 void arch_spin_lock_wait(arch_spinlock_t *lp)
 {
 	unsigned int cpu = SPINLOCK_LOCKVAL;
@@ -53,7 +62,7 @@ void arch_spin_lock_wait(arch_spinlock_t *lp)
 			continue;
 		}
 		/* First iteration: check if the lock owner is running. */
-		if (first_diag && !smp_vcpu_scheduled(~owner)) {
+		if (first_diag && cpu_is_preempted(~owner)) {
 			smp_yield_cpu(~owner);
 			first_diag = 0;
 			continue;
@@ -72,7 +81,7 @@ void arch_spin_lock_wait(arch_spinlock_t *lp)
 		 * yield the CPU unconditionally. For LPAR rely on the
 		 * sense running status.
 		 */
-		if (!MACHINE_IS_LPAR || !smp_vcpu_scheduled(~owner)) {
+		if (!MACHINE_IS_LPAR || cpu_is_preempted(~owner)) {
 			smp_yield_cpu(~owner);
 			first_diag = 0;
 		}
@@ -98,7 +107,7 @@ void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags)
 			local_irq_restore(flags);
 		}
 		/* Check if the lock owner is running. */
-		if (first_diag && !smp_vcpu_scheduled(~owner)) {
+		if (first_diag && cpu_is_preempted(~owner)) {
 			smp_yield_cpu(~owner);
 			first_diag = 0;
 			continue;
@@ -117,7 +126,7 @@ void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags)
 		 * yield the CPU unconditionally. For LPAR rely on the
 		 * sense running status.
 		 */
-		if (!MACHINE_IS_LPAR || !smp_vcpu_scheduled(~owner)) {
+		if (!MACHINE_IS_LPAR || cpu_is_preempted(~owner)) {
 			smp_yield_cpu(~owner);
 			first_diag = 0;
 		}
@@ -155,7 +164,7 @@ void _raw_read_lock_wait(arch_rwlock_t *rw)
 	owner = 0;
 	while (1) {
 		if (count-- <= 0) {
-			if (owner && !smp_vcpu_scheduled(~owner))
+			if (owner && cpu_is_preempted(~owner))
 				smp_yield_cpu(~owner);
 			count = spin_retry;
 		}
@@ -201,7 +210,7 @@ void _raw_write_lock_wait(arch_rwlock_t *rw, unsigned int prev)
 	owner = 0;
 	while (1) {
 		if (count-- <= 0) {
-			if (owner && !smp_vcpu_scheduled(~owner))
+			if (owner && cpu_is_preempted(~owner))
 				smp_yield_cpu(~owner);
 			count = spin_retry;
 		}
@@ -231,7 +240,7 @@ void _raw_write_lock_wait(arch_rwlock_t *rw)
 	owner = 0;
 	while (1) {
 		if (count-- <= 0) {
-			if (owner && !smp_vcpu_scheduled(~owner))
+			if (owner && cpu_is_preempted(~owner))
 				smp_yield_cpu(~owner);
 			count = spin_retry;
 		}
@@ -275,7 +284,7 @@ void arch_lock_relax(unsigned int cpu)
 {
 	if (!cpu)
 		return;
-	if (MACHINE_IS_LPAR && smp_vcpu_scheduled(~cpu))
+	if (MACHINE_IS_LPAR && !cpu_is_preempted(~cpu))
 		return;
 	smp_yield_cpu(~cpu);
 }
-- 
cgit 


From e09fefdeeb517ff653516dea8a882ce001e99237 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <dahi@linux.vnet.ibm.com>
Date: Thu, 5 Nov 2015 09:03:50 +0100
Subject: KVM: Use common function for VCPU lookup by id

Let's reuse the new common function for VPCU lookup by id.

Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: Dominik Dingel <dingel@linux.vnet.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
[split out the new function into a separate patch]
---
 arch/s390/kvm/diag.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 5fbfb88f8477..05f7de9869a9 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -155,10 +155,8 @@ static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
 
 static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
 {
-	struct kvm *kvm = vcpu->kvm;
 	struct kvm_vcpu *tcpu;
 	int tid;
-	int i;
 
 	tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
 	vcpu->stat.diagnose_9c++;
@@ -167,12 +165,9 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
 	if (tid == vcpu->vcpu_id)
 		return 0;
 
-	kvm_for_each_vcpu(i, tcpu, kvm)
-		if (tcpu->vcpu_id == tid) {
-			kvm_vcpu_yield_to(tcpu);
-			break;
-		}
-
+	tcpu = kvm_get_vcpu_by_id(vcpu->kvm, tid);
+	if (tcpu)
+		kvm_vcpu_yield_to(tcpu);
 	return 0;
 }
 
-- 
cgit 


From 71f116bfedfdd6763f2caf842bf40a6506759029 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <dahi@linux.vnet.ibm.com>
Date: Mon, 19 Oct 2015 16:24:28 +0200
Subject: KVM: s390: rewrite vcpu_post_run and drop out early

Let's rewrite this function to better reflect how we actually handle
exit_code. By dropping out early we can save a few cycles. This
especially speeds up sie exits caused by host irqs.

Also, let's move the special -EOPNOTSUPP for intercepts to
the place where it belongs and convert it to -EREMOTE.

Reviewed-by: Dominik Dingel <dingel@linux.vnet.ibm.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/kvm/intercept.c |  7 +++---
 arch/s390/kvm/kvm-s390.c  | 59 +++++++++++++++++------------------------------
 2 files changed, 24 insertions(+), 42 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index b4a5aa110cec..d53c10753c46 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -54,9 +54,6 @@ void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc)
 static int handle_noop(struct kvm_vcpu *vcpu)
 {
 	switch (vcpu->arch.sie_block->icptcode) {
-	case 0x0:
-		vcpu->stat.exit_null++;
-		break;
 	case 0x10:
 		vcpu->stat.exit_external_request++;
 		break;
@@ -338,8 +335,10 @@ static int handle_partial_execution(struct kvm_vcpu *vcpu)
 
 int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
 {
+	if (kvm_is_ucontrol(vcpu->kvm))
+		return -EOPNOTSUPP;
+
 	switch (vcpu->arch.sie_block->icptcode) {
-	case 0x00:
 	case 0x10:
 	case 0x18:
 		return handle_noop(vcpu);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 846589281b04..5c36c8e7e937 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2071,8 +2071,6 @@ static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
 
 static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
 {
-	int rc = -1;
-
 	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
 		   vcpu->arch.sie_block->icptcode);
 	trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
@@ -2080,40 +2078,35 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
 	if (guestdbg_enabled(vcpu))
 		kvm_s390_restore_guest_per_regs(vcpu);
 
-	if (exit_reason >= 0) {
-		rc = 0;
+	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
+
+	if (vcpu->arch.sie_block->icptcode > 0) {
+		int rc = kvm_handle_sie_intercept(vcpu);
+
+		if (rc != -EOPNOTSUPP)
+			return rc;
+		vcpu->run->exit_reason = KVM_EXIT_S390_SIEIC;
+		vcpu->run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
+		vcpu->run->s390_sieic.ipa = vcpu->arch.sie_block->ipa;
+		vcpu->run->s390_sieic.ipb = vcpu->arch.sie_block->ipb;
+		return -EREMOTE;
+	} else if (exit_reason != -EFAULT) {
+		vcpu->stat.exit_null++;
+		return 0;
 	} else if (kvm_is_ucontrol(vcpu->kvm)) {
 		vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
 		vcpu->run->s390_ucontrol.trans_exc_code =
 						current->thread.gmap_addr;
 		vcpu->run->s390_ucontrol.pgm_code = 0x10;
-		rc = -EREMOTE;
-
+		return -EREMOTE;
 	} else if (current->thread.gmap_pfault) {
 		trace_kvm_s390_major_guest_pfault(vcpu);
 		current->thread.gmap_pfault = 0;
-		if (kvm_arch_setup_async_pf(vcpu)) {
-			rc = 0;
-		} else {
-			gpa_t gpa = current->thread.gmap_addr;
-			rc = kvm_arch_fault_in_page(vcpu, gpa, 1);
-		}
-	}
-
-	if (rc == -1)
-		rc = vcpu_post_run_fault_in_sie(vcpu);
-
-	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
-
-	if (rc == 0) {
-		if (kvm_is_ucontrol(vcpu->kvm))
-			/* Don't exit for host interrupts. */
-			rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0;
-		else
-			rc = kvm_handle_sie_intercept(vcpu);
+		if (kvm_arch_setup_async_pf(vcpu))
+			return 0;
+		return kvm_arch_fault_in_page(vcpu, current->thread.gmap_addr, 1);
 	}
-
-	return rc;
+	return vcpu_post_run_fault_in_sie(vcpu);
 }
 
 static int __vcpu_run(struct kvm_vcpu *vcpu)
@@ -2233,18 +2226,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		rc = 0;
 	}
 
-	if (rc == -EOPNOTSUPP) {
-		/* intercept cannot be handled in-kernel, prepare kvm-run */
-		kvm_run->exit_reason         = KVM_EXIT_S390_SIEIC;
-		kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
-		kvm_run->s390_sieic.ipa      = vcpu->arch.sie_block->ipa;
-		kvm_run->s390_sieic.ipb      = vcpu->arch.sie_block->ipb;
-		rc = 0;
-	}
-
 	if (rc == -EREMOTE) {
-		/* intercept was handled, but userspace support is needed
-		 * kvm_run has been prepared by the handler */
+		/* userspace support is needed, kvm_run has been prepared */
 		rc = 0;
 	}
 
-- 
cgit 


From f7ba1d34263e333e82aa8879028ddd06d6d5f9ac Mon Sep 17 00:00:00 2001
From: "Eugene (jno) Dvurechenski" <jno@linux.vnet.ibm.com>
Date: Thu, 9 Oct 2014 16:04:48 +0200
Subject: s390/sclp: introduce checks for ESCA and HVS

Introduce sclp.has_hvs and sclp.has_esca to provide a way for kvm to check
whether the extended-SCA and the home-virtual-SCA facilities are available.

Signed-off-by: Eugene (jno) Dvurechenski <jno@linux.vnet.ibm.com>
Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/include/asm/sclp.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 821dde5f425d..8324abbdaeaf 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -53,6 +53,8 @@ struct sclp_info {
 	unsigned char has_sigpif : 1;
 	unsigned char has_core_type : 1;
 	unsigned char has_sprp : 1;
+	unsigned char has_hvs : 1;
+	unsigned char has_esca : 1;
 	unsigned int ibc;
 	unsigned int mtid;
 	unsigned int mtid_cp;
-- 
cgit 


From 605145103abb21c555d5982073bee29269aaad51 Mon Sep 17 00:00:00 2001
From: "Eugene (jno) Dvurechenski" <jno@linux.vnet.ibm.com>
Date: Tue, 21 Apr 2015 14:44:54 +0200
Subject: KVM: s390: Generalize access to IPTE controls

This patch generalizes access to the IPTE controls, which is a part of SCA.
This is to prepare for upcoming introduction of Extended SCA support.

Signed-off-by: Eugene (jno) Dvurechenski <jno@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/kvm/gaccess.c  | 10 +++++-----
 arch/s390/kvm/kvm-s390.h |  5 +++++
 2 files changed, 10 insertions(+), 5 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index a7559f7207df..06f7edb3770d 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -259,7 +259,7 @@ struct aste {
 
 int ipte_lock_held(struct kvm_vcpu *vcpu)
 {
-	union ipte_control *ic = &vcpu->kvm->arch.sca->ipte_control;
+	union ipte_control *ic = kvm_s390_get_ipte_control(vcpu->kvm);
 
 	if (vcpu->arch.sie_block->eca & 1)
 		return ic->kh != 0;
@@ -274,7 +274,7 @@ static void ipte_lock_simple(struct kvm_vcpu *vcpu)
 	vcpu->kvm->arch.ipte_lock_count++;
 	if (vcpu->kvm->arch.ipte_lock_count > 1)
 		goto out;
-	ic = &vcpu->kvm->arch.sca->ipte_control;
+	ic = kvm_s390_get_ipte_control(vcpu->kvm);
 	do {
 		old = READ_ONCE(*ic);
 		while (old.k) {
@@ -296,7 +296,7 @@ static void ipte_unlock_simple(struct kvm_vcpu *vcpu)
 	vcpu->kvm->arch.ipte_lock_count--;
 	if (vcpu->kvm->arch.ipte_lock_count)
 		goto out;
-	ic = &vcpu->kvm->arch.sca->ipte_control;
+	ic = kvm_s390_get_ipte_control(vcpu->kvm);
 	do {
 		old = READ_ONCE(*ic);
 		new = old;
@@ -311,7 +311,7 @@ static void ipte_lock_siif(struct kvm_vcpu *vcpu)
 {
 	union ipte_control old, new, *ic;
 
-	ic = &vcpu->kvm->arch.sca->ipte_control;
+	ic = kvm_s390_get_ipte_control(vcpu->kvm);
 	do {
 		old = READ_ONCE(*ic);
 		while (old.kg) {
@@ -328,7 +328,7 @@ static void ipte_unlock_siif(struct kvm_vcpu *vcpu)
 {
 	union ipte_control old, new, *ic;
 
-	ic = &vcpu->kvm->arch.sca->ipte_control;
+	ic = kvm_s390_get_ipte_control(vcpu->kvm);
 	do {
 		old = READ_ONCE(*ic);
 		new = old;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 1e70e00d3c5e..844f711972f9 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -340,4 +340,9 @@ void kvm_s390_clear_bp_data(struct kvm_vcpu *vcpu);
 void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu);
 void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu);
 
+/* support for Basic/Extended SCA handling */
+static inline union ipte_control *kvm_s390_get_ipte_control(struct kvm *kvm)
+{
+	return &kvm->arch.sca->ipte_control;
+}
 #endif
-- 
cgit 


From a5bd764734838da64b37d771e5b7814eb1f61ffd Mon Sep 17 00:00:00 2001
From: "Eugene (jno) Dvurechenski" <jno@linux.vnet.ibm.com>
Date: Tue, 21 Apr 2015 15:10:10 +0200
Subject: KVM: s390: Generalize access to SIGP controls

This patch generalizes access to the SIGP controls, which is a part of SCA.
This is to prepare for upcoming introduction of Extended SCA support.

Signed-off-by: Eugene (jno) Dvurechenski <jno@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/kvm/interrupt.c | 72 +++++++++++++++++++++++++++++------------------
 1 file changed, 45 insertions(+), 27 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 6a75352f453c..2a4718af9dcf 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -34,6 +34,45 @@
 #define PFAULT_DONE 0x0680
 #define VIRTIO_PARAM 0x0d00
 
+/* handle external calls via sigp interpretation facility */
+static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
+{
+	struct sca_block *sca = vcpu->kvm->arch.sca;
+	uint8_t sigp_ctrl = sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+
+	if (src_id)
+		*src_id = sigp_ctrl & SIGP_CTRL_SCN_MASK;
+
+	return sigp_ctrl & SIGP_CTRL_C &&
+		atomic_read(&vcpu->arch.sie_block->cpuflags) &
+			CPUSTAT_ECALL_PEND;
+}
+
+static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
+{
+	struct sca_block *sca = vcpu->kvm->arch.sca;
+	uint8_t *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+	uint8_t new_val = SIGP_CTRL_C | (src_id & SIGP_CTRL_SCN_MASK);
+	uint8_t old_val = *sigp_ctrl & ~SIGP_CTRL_C;
+
+	if (cmpxchg(sigp_ctrl, old_val, new_val) != old_val) {
+		/* another external call is pending */
+		return -EBUSY;
+	}
+	atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
+	return 0;
+}
+
+static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
+{
+	struct sca_block *sca = vcpu->kvm->arch.sca;
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+	uint8_t *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+
+	atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
+	*sigp_ctrl = 0;
+}
+
 int psw_extint_disabled(struct kvm_vcpu *vcpu)
 {
 	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
@@ -792,13 +831,11 @@ static const deliver_irq_t deliver_irq_funcs[] = {
 int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
-	uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
 
 	if (!sclp.has_sigpif)
 		return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
 
-	return (sigp_ctrl & SIGP_CTRL_C) &&
-	       (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND);
+	return sca_ext_call_pending(vcpu, NULL);
 }
 
 int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop)
@@ -909,9 +946,7 @@ void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
 	memset(&li->irq, 0, sizeof(li->irq));
 	spin_unlock(&li->lock);
 
-	/* clear pending external calls set by sigp interpretation facility */
-	atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
-	vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl = 0;
+	sca_clear_ext_call(vcpu);
 }
 
 int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
@@ -1003,21 +1038,6 @@ static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	return 0;
 }
 
-static int __inject_extcall_sigpif(struct kvm_vcpu *vcpu, uint16_t src_id)
-{
-	unsigned char new_val, old_val;
-	uint8_t *sigp_ctrl = &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
-
-	new_val = SIGP_CTRL_C | (src_id & SIGP_CTRL_SCN_MASK);
-	old_val = *sigp_ctrl & ~SIGP_CTRL_C;
-	if (cmpxchg(sigp_ctrl, old_val, new_val) != old_val) {
-		/* another external call is pending */
-		return -EBUSY;
-	}
-	atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
-	return 0;
-}
-
 static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -1034,7 +1054,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 		return -EINVAL;
 
 	if (sclp.has_sigpif)
-		return __inject_extcall_sigpif(vcpu, src_id);
+		return sca_inject_ext_call(vcpu, src_id);
 
 	if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
 		return -EBUSY;
@@ -2203,7 +2223,7 @@ static void store_local_irq(struct kvm_s390_local_interrupt *li,
 
 int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len)
 {
-	uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+	int scn;
 	unsigned long sigp_emerg_pending[BITS_TO_LONGS(KVM_MAX_VCPUS)];
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	unsigned long pending_irqs;
@@ -2243,14 +2263,12 @@ int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len)
 		}
 	}
 
-	if ((sigp_ctrl & SIGP_CTRL_C) &&
-	    (atomic_read(&vcpu->arch.sie_block->cpuflags) &
-	     CPUSTAT_ECALL_PEND)) {
+	if (sca_ext_call_pending(vcpu, &scn)) {
 		if (n + sizeof(irq) > len)
 			return -ENOBUFS;
 		memset(&irq, 0, sizeof(irq));
 		irq.type = KVM_S390_INT_EXTERNAL_CALL;
-		irq.u.extcall.code = sigp_ctrl & SIGP_CTRL_SCN_MASK;
+		irq.u.extcall.code = scn;
 		if (copy_to_user(&buf[n], &irq, sizeof(irq)))
 			return -EFAULT;
 		n += sizeof(irq);
-- 
cgit 


From a6e2f683e7691949d33ca9392e7807cfa9aca34e Mon Sep 17 00:00:00 2001
From: "Eugene (jno) Dvurechenski" <jno@linux.vnet.ibm.com>
Date: Tue, 21 Apr 2015 15:31:59 +0200
Subject: KVM: s390: Provide SCA-aware helpers for VCPU add/del

This patch provides SCA-aware helpers to create/delete a VCPU.
This is to prepare for upcoming introduction of Extended SCA support.

Signed-off-by: Eugene (jno) Dvurechenski <jno@linux.vnet.ibm.com>
Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/kvm/kvm-s390.c | 44 +++++++++++++++++++++++++++++++-------------
 1 file changed, 31 insertions(+), 13 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 5c36c8e7e937..8ddd48848a83 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -283,6 +283,8 @@ static void kvm_s390_sync_dirty_log(struct kvm *kvm,
 }
 
 /* Section: vm related */
+static void sca_del_vcpu(struct kvm_vcpu *vcpu);
+
 /*
  * Get (and clear) the dirty memory log for a memory slot.
  */
@@ -1189,11 +1191,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kvm_s390_clear_local_irqs(vcpu);
 	kvm_clear_async_pf_completion_queue(vcpu);
 	if (!kvm_is_ucontrol(vcpu->kvm)) {
-		clear_bit(63 - vcpu->vcpu_id,
-			  (unsigned long *) &vcpu->kvm->arch.sca->mcn);
-		if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda ==
-		    (__u64) vcpu->arch.sie_block)
-			vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
+		sca_del_vcpu(vcpu);
 	}
 	smp_mb();
 
@@ -1249,6 +1247,32 @@ static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static void sca_del_vcpu(struct kvm_vcpu *vcpu)
+{
+	struct sca_block *sca = vcpu->kvm->arch.sca;
+
+	clear_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
+	if (sca->cpu[vcpu->vcpu_id].sda == (__u64) vcpu->arch.sie_block)
+		sca->cpu[vcpu->vcpu_id].sda = 0;
+}
+
+static void sca_add_vcpu(struct kvm_vcpu *vcpu, struct kvm *kvm,
+			unsigned int id)
+{
+	struct sca_block *sca = kvm->arch.sca;
+
+	if (!sca->cpu[id].sda)
+		sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
+	vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
+	vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
+	set_bit_inv(id, (unsigned long *) &sca->mcn);
+}
+
+static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id)
+{
+	return id < KVM_MAX_VCPUS;
+}
+
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
@@ -1465,7 +1489,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	struct sie_page *sie_page;
 	int rc = -EINVAL;
 
-	if (id >= KVM_MAX_VCPUS)
+	if (!sca_can_add_vcpu(kvm, id))
 		goto out;
 
 	rc = -ENOMEM;
@@ -1487,13 +1511,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 			WARN_ON_ONCE(1);
 			goto out_free_cpu;
 		}
-		if (!kvm->arch.sca->cpu[id].sda)
-			kvm->arch.sca->cpu[id].sda =
-				(__u64) vcpu->arch.sie_block;
-		vcpu->arch.sie_block->scaoh =
-			(__u32)(((__u64)kvm->arch.sca) >> 32);
-		vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
-		set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
+		sca_add_vcpu(vcpu, kvm, id);
 	}
 
 	spin_lock_init(&vcpu->arch.local_int.lock);
-- 
cgit 


From bc784ccee5eb9ae1e737927eb9d8a0fbf7601abc Mon Sep 17 00:00:00 2001
From: "Eugene (jno) Dvurechenski" <jno@linux.vnet.ibm.com>
Date: Thu, 23 Apr 2015 16:09:06 +0200
Subject: KVM: s390: Introduce new structures

This patch adds new structures and updates some existing ones to
provide the base for Extended SCA functionality.

The old sca_* structures were renamed to bsca_* to keep things uniform.

The access to fields of SIGP controls were turned into bitfields instead
of hardcoded bitmasks.

Signed-off-by: Eugene (jno) Dvurechenski <jno@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/include/asm/kvm_host.h | 47 +++++++++++++++++++++++++++++++++++-----
 arch/s390/kvm/interrupt.c        | 31 ++++++++++++++++----------
 arch/s390/kvm/kvm-s390.c         | 14 ++++++------
 arch/s390/kvm/kvm-s390.h         |  4 +++-
 4 files changed, 70 insertions(+), 26 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index efaac2c3bb77..923b13df43a7 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -25,7 +25,9 @@
 #include <asm/fpu/api.h>
 #include <asm/isc.h>
 
-#define KVM_MAX_VCPUS 64
+#define KVM_S390_BSCA_CPU_SLOTS 64
+#define KVM_S390_ESCA_CPU_SLOTS 248
+#define KVM_MAX_VCPUS KVM_S390_BSCA_CPU_SLOTS
 #define KVM_USER_MEM_SLOTS 32
 
 /*
@@ -40,9 +42,34 @@
 #define SIGP_CTRL_C		0x80
 #define SIGP_CTRL_SCN_MASK	0x3f
 
-struct sca_entry {
+union bsca_sigp_ctrl {
+	__u8 value;
+	struct {
+		__u8 c : 1;
+		__u8 r : 1;
+		__u8 scn : 6;
+	};
+} __packed;
+
+union esca_sigp_ctrl {
+	__u16 value;
+	struct {
+		__u8 c : 1;
+		__u8 reserved: 7;
+		__u8 scn;
+	};
+} __packed;
+
+struct esca_entry {
+	union esca_sigp_ctrl sigp_ctrl;
+	__u16   reserved1[3];
+	__u64   sda;
+	__u64   reserved2[6];
+} __packed;
+
+struct bsca_entry {
 	__u8	reserved0;
-	__u8	sigp_ctrl;
+	union bsca_sigp_ctrl	sigp_ctrl;
 	__u16	reserved[3];
 	__u64	sda;
 	__u64	reserved2[2];
@@ -57,14 +84,22 @@ union ipte_control {
 	};
 };
 
-struct sca_block {
+struct bsca_block {
 	union ipte_control ipte_control;
 	__u64	reserved[5];
 	__u64	mcn;
 	__u64	reserved2;
-	struct sca_entry cpu[64];
+	struct bsca_entry cpu[KVM_S390_BSCA_CPU_SLOTS];
 } __attribute__((packed));
 
+struct esca_block {
+	union ipte_control ipte_control;
+	__u64   reserved1[7];
+	__u64   mcn[4];
+	__u64   reserved2[20];
+	struct esca_entry cpu[KVM_S390_ESCA_CPU_SLOTS];
+} __packed;
+
 #define CPUSTAT_STOPPED    0x80000000
 #define CPUSTAT_WAIT       0x10000000
 #define CPUSTAT_ECALL_PEND 0x08000000
@@ -585,7 +620,7 @@ struct kvm_s390_crypto_cb {
 };
 
 struct kvm_arch{
-	struct sca_block *sca;
+	struct bsca_block *sca;
 	debug_info_t *dbf;
 	struct kvm_s390_float_interrupt float_int;
 	struct kvm_device *flic;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 2a4718af9dcf..aa221a48cc7c 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -37,25 +37,32 @@
 /* handle external calls via sigp interpretation facility */
 static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
 {
-	struct sca_block *sca = vcpu->kvm->arch.sca;
-	uint8_t sigp_ctrl = sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+	struct bsca_block *sca = vcpu->kvm->arch.sca;
+	union bsca_sigp_ctrl sigp_ctrl = sca->cpu[vcpu->vcpu_id].sigp_ctrl;
 
 	if (src_id)
-		*src_id = sigp_ctrl & SIGP_CTRL_SCN_MASK;
+		*src_id = sigp_ctrl.scn;
 
-	return sigp_ctrl & SIGP_CTRL_C &&
+	return sigp_ctrl.c &&
 		atomic_read(&vcpu->arch.sie_block->cpuflags) &
 			CPUSTAT_ECALL_PEND;
 }
 
 static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
 {
-	struct sca_block *sca = vcpu->kvm->arch.sca;
-	uint8_t *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
-	uint8_t new_val = SIGP_CTRL_C | (src_id & SIGP_CTRL_SCN_MASK);
-	uint8_t old_val = *sigp_ctrl & ~SIGP_CTRL_C;
+	int expect, rc;
+	struct bsca_block *sca = vcpu->kvm->arch.sca;
+	union bsca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+	union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
 
-	if (cmpxchg(sigp_ctrl, old_val, new_val) != old_val) {
+	new_val.scn = src_id;
+	new_val.c = 1;
+	old_val.c = 0;
+
+	expect = old_val.value;
+	rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
+
+	if (rc != expect) {
 		/* another external call is pending */
 		return -EBUSY;
 	}
@@ -65,12 +72,12 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
 
 static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
 {
-	struct sca_block *sca = vcpu->kvm->arch.sca;
+	struct bsca_block *sca = vcpu->kvm->arch.sca;
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
-	uint8_t *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+	union bsca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
 
 	atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
-	*sigp_ctrl = 0;
+	sigp_ctrl->value = 0;
 }
 
 int psw_extint_disabled(struct kvm_vcpu *vcpu)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 8ddd48848a83..c2683529b25c 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1100,14 +1100,15 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	rc = -ENOMEM;
 
-	kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
+	kvm->arch.sca = (struct bsca_block *) get_zeroed_page(GFP_KERNEL);
 	if (!kvm->arch.sca)
 		goto out_err;
 	spin_lock(&kvm_lock);
 	sca_offset += 16;
-	if (sca_offset + sizeof(struct sca_block) > PAGE_SIZE)
+	if (sca_offset + sizeof(struct bsca_block) > PAGE_SIZE)
 		sca_offset = 0;
-	kvm->arch.sca = (struct sca_block *) ((char *) kvm->arch.sca + sca_offset);
+	kvm->arch.sca = (struct bsca_block *)
+			((char *) kvm->arch.sca + sca_offset);
 	spin_unlock(&kvm_lock);
 
 	sprintf(debug_name, "kvm-%u", current->pid);
@@ -1190,9 +1191,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
 	kvm_s390_clear_local_irqs(vcpu);
 	kvm_clear_async_pf_completion_queue(vcpu);
-	if (!kvm_is_ucontrol(vcpu->kvm)) {
+	if (!kvm_is_ucontrol(vcpu->kvm))
 		sca_del_vcpu(vcpu);
-	}
 	smp_mb();
 
 	if (kvm_is_ucontrol(vcpu->kvm))
@@ -1249,7 +1249,7 @@ static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu)
 
 static void sca_del_vcpu(struct kvm_vcpu *vcpu)
 {
-	struct sca_block *sca = vcpu->kvm->arch.sca;
+	struct bsca_block *sca = vcpu->kvm->arch.sca;
 
 	clear_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
 	if (sca->cpu[vcpu->vcpu_id].sda == (__u64) vcpu->arch.sie_block)
@@ -1259,7 +1259,7 @@ static void sca_del_vcpu(struct kvm_vcpu *vcpu)
 static void sca_add_vcpu(struct kvm_vcpu *vcpu, struct kvm *kvm,
 			unsigned int id)
 {
-	struct sca_block *sca = kvm->arch.sca;
+	struct bsca_block *sca = kvm->arch.sca;
 
 	if (!sca->cpu[id].sda)
 		sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 844f711972f9..df1abada1f36 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -343,6 +343,8 @@ void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu);
 /* support for Basic/Extended SCA handling */
 static inline union ipte_control *kvm_s390_get_ipte_control(struct kvm *kvm)
 {
-	return &kvm->arch.sca->ipte_control;
+	struct bsca_block *sca = kvm->arch.sca; /* SCA version doesn't matter */
+
+	return &sca->ipte_control;
 }
 #endif
-- 
cgit 


From 7d43bafcff17c7fb07270999d3cf002f1ed6bd3f Mon Sep 17 00:00:00 2001
From: "Eugene (jno) Dvurechenski" <jno@linux.vnet.ibm.com>
Date: Wed, 22 Apr 2015 17:09:44 +0200
Subject: KVM: s390: Make provisions for ESCA utilization

This patch updates the routines (sca_*) to provide transparent access
to and manipulation on the data for both Basic and Extended SCA in use.
The kvm.arch.sca is generalized to (void *) to handle BSCA/ESCA cases.
Also the kvm.arch.use_esca flag is provided.
The actual functionality is kept the same.

Signed-off-by: Eugene (jno) Dvurechenski <jno@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/include/asm/kvm_host.h |  3 +-
 arch/s390/kvm/interrupt.c        | 78 +++++++++++++++++++++++++++++++---------
 arch/s390/kvm/kvm-s390.c         | 54 +++++++++++++++++++++-------
 3 files changed, 106 insertions(+), 29 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 923b13df43a7..25fdbf808693 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -620,7 +620,8 @@ struct kvm_s390_crypto_cb {
 };
 
 struct kvm_arch{
-	struct bsca_block *sca;
+	void *sca;
+	int use_esca;
 	debug_info_t *dbf;
 	struct kvm_s390_float_interrupt float_int;
 	struct kvm_device *flic;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index aa221a48cc7c..60b36b0e2125 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -37,30 +37,60 @@
 /* handle external calls via sigp interpretation facility */
 static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
 {
-	struct bsca_block *sca = vcpu->kvm->arch.sca;
-	union bsca_sigp_ctrl sigp_ctrl = sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+	int c, scn;
+
+	if (vcpu->kvm->arch.use_esca) {
+		struct esca_block *sca = vcpu->kvm->arch.sca;
+		union esca_sigp_ctrl sigp_ctrl =
+			sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+
+		c = sigp_ctrl.c;
+		scn = sigp_ctrl.scn;
+	} else {
+		struct bsca_block *sca = vcpu->kvm->arch.sca;
+		union bsca_sigp_ctrl sigp_ctrl =
+			sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+
+		c = sigp_ctrl.c;
+		scn = sigp_ctrl.scn;
+	}
 
 	if (src_id)
-		*src_id = sigp_ctrl.scn;
+		*src_id = scn;
 
-	return sigp_ctrl.c &&
-		atomic_read(&vcpu->arch.sie_block->cpuflags) &
+	return c && atomic_read(&vcpu->arch.sie_block->cpuflags) &
 			CPUSTAT_ECALL_PEND;
 }
 
 static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
 {
 	int expect, rc;
-	struct bsca_block *sca = vcpu->kvm->arch.sca;
-	union bsca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
-	union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
 
-	new_val.scn = src_id;
-	new_val.c = 1;
-	old_val.c = 0;
+	if (vcpu->kvm->arch.use_esca) {
+		struct esca_block *sca = vcpu->kvm->arch.sca;
+		union esca_sigp_ctrl *sigp_ctrl =
+			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+		union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
+
+		new_val.scn = src_id;
+		new_val.c = 1;
+		old_val.c = 0;
 
-	expect = old_val.value;
-	rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
+		expect = old_val.value;
+		rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
+	} else {
+		struct bsca_block *sca = vcpu->kvm->arch.sca;
+		union bsca_sigp_ctrl *sigp_ctrl =
+			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+		union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
+
+		new_val.scn = src_id;
+		new_val.c = 1;
+		old_val.c = 0;
+
+		expect = old_val.value;
+		rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
+	}
 
 	if (rc != expect) {
 		/* another external call is pending */
@@ -72,12 +102,28 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
 
 static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
 {
-	struct bsca_block *sca = vcpu->kvm->arch.sca;
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
-	union bsca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+	int rc, expect;
 
 	atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
-	sigp_ctrl->value = 0;
+	if (vcpu->kvm->arch.use_esca) {
+		struct esca_block *sca = vcpu->kvm->arch.sca;
+		union esca_sigp_ctrl *sigp_ctrl =
+			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+		union esca_sigp_ctrl old = *sigp_ctrl;
+
+		expect = old.value;
+		rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
+	} else {
+		struct bsca_block *sca = vcpu->kvm->arch.sca;
+		union bsca_sigp_ctrl *sigp_ctrl =
+			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+		union bsca_sigp_ctrl old = *sigp_ctrl;
+
+		expect = old.value;
+		rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
+	}
+	WARN_ON(rc != expect); /* cannot clear? */
 }
 
 int psw_extint_disabled(struct kvm_vcpu *vcpu)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index c2683529b25c..41b3fed51591 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1077,6 +1077,15 @@ static int kvm_s390_crypto_init(struct kvm *kvm)
 	return 0;
 }
 
+static void sca_dispose(struct kvm *kvm)
+{
+	if (kvm->arch.use_esca)
+		BUG(); /* not implemented yet */
+	else
+		free_page((unsigned long)(kvm->arch.sca));
+	kvm->arch.sca = NULL;
+}
+
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	int i, rc;
@@ -1100,6 +1109,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	rc = -ENOMEM;
 
+	kvm->arch.use_esca = 0; /* start with basic SCA */
 	kvm->arch.sca = (struct bsca_block *) get_zeroed_page(GFP_KERNEL);
 	if (!kvm->arch.sca)
 		goto out_err;
@@ -1180,7 +1190,7 @@ out_err:
 	kfree(kvm->arch.crypto.crycb);
 	free_page((unsigned long)kvm->arch.model.fac);
 	debug_unregister(kvm->arch.dbf);
-	free_page((unsigned long)(kvm->arch.sca));
+	sca_dispose(kvm);
 	KVM_EVENT(3, "creation of vm failed: %d", rc);
 	return rc;
 }
@@ -1226,7 +1236,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	kvm_free_vcpus(kvm);
 	free_page((unsigned long)kvm->arch.model.fac);
-	free_page((unsigned long)(kvm->arch.sca));
+	sca_dispose(kvm);
 	debug_unregister(kvm->arch.dbf);
 	kfree(kvm->arch.crypto.crycb);
 	if (!kvm_is_ucontrol(kvm))
@@ -1249,23 +1259,41 @@ static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu)
 
 static void sca_del_vcpu(struct kvm_vcpu *vcpu)
 {
-	struct bsca_block *sca = vcpu->kvm->arch.sca;
+	if (vcpu->kvm->arch.use_esca) {
+		struct esca_block *sca = vcpu->kvm->arch.sca;
+
+		clear_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
+		if (sca->cpu[vcpu->vcpu_id].sda == (__u64) vcpu->arch.sie_block)
+			sca->cpu[vcpu->vcpu_id].sda = 0;
+	} else {
+		struct bsca_block *sca = vcpu->kvm->arch.sca;
 
-	clear_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
-	if (sca->cpu[vcpu->vcpu_id].sda == (__u64) vcpu->arch.sie_block)
-		sca->cpu[vcpu->vcpu_id].sda = 0;
+		clear_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
+		if (sca->cpu[vcpu->vcpu_id].sda == (__u64) vcpu->arch.sie_block)
+			sca->cpu[vcpu->vcpu_id].sda = 0;
+	}
 }
 
 static void sca_add_vcpu(struct kvm_vcpu *vcpu, struct kvm *kvm,
 			unsigned int id)
 {
-	struct bsca_block *sca = kvm->arch.sca;
+	if (kvm->arch.use_esca) {
+		struct esca_block *sca = kvm->arch.sca;
 
-	if (!sca->cpu[id].sda)
-		sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
-	vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
-	vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
-	set_bit_inv(id, (unsigned long *) &sca->mcn);
+		if (!sca->cpu[id].sda)
+			sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
+		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
+		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca & ~0x3fU;
+		set_bit_inv(id, (unsigned long *) sca->mcn);
+	} else {
+		struct bsca_block *sca = kvm->arch.sca;
+
+		if (!sca->cpu[id].sda)
+			sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
+		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
+		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
+		set_bit_inv(id, (unsigned long *) &sca->mcn);
+	}
 }
 
 static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id)
@@ -1458,6 +1486,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 		vcpu->arch.sie_block->ecb |= 0x10;
 
 	vcpu->arch.sie_block->ecb2  = 8;
+	if (vcpu->kvm->arch.use_esca)
+		vcpu->arch.sie_block->ecb2 |= 4;
 	vcpu->arch.sie_block->eca   = 0xC1002000U;
 	if (sclp.has_siif)
 		vcpu->arch.sie_block->eca |= 1;
-- 
cgit 


From 5e0443152367ab9fef597a41a4e09a32df2bf887 Mon Sep 17 00:00:00 2001
From: "Eugene (jno) Dvurechenski" <jno@linux.vnet.ibm.com>
Date: Wed, 22 Apr 2015 18:08:39 +0200
Subject: KVM: s390: Introduce switching code

This patch adds code that performs transparent switch to Extended
SCA on addition of 65th VCPU in a VM. Disposal of ESCA is added too.
The entier ESCA functionality, however, is still not enabled.
The enablement will be provided in a separate patch.

This patch also uses read/write lock protection of SCA and its subfields for
possible disposal at the BSCA-to-ESCA transition. While only Basic SCA needs such
a protection (for the swap), any SCA access is now guarded.

Signed-off-by: Eugene (jno) Dvurechenski <jno@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/include/asm/kvm_host.h |  1 +
 arch/s390/kvm/gaccess.c          | 30 ++++++++++++----
 arch/s390/kvm/interrupt.c        |  6 ++++
 arch/s390/kvm/kvm-s390.c         | 75 ++++++++++++++++++++++++++++++++++++++--
 4 files changed, 103 insertions(+), 9 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 25fdbf808693..86c33863a0ad 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -622,6 +622,7 @@ struct kvm_s390_crypto_cb {
 struct kvm_arch{
 	void *sca;
 	int use_esca;
+	rwlock_t sca_lock;
 	debug_info_t *dbf;
 	struct kvm_s390_float_interrupt float_int;
 	struct kvm_device *flic;
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 06f7edb3770d..d30db40437dc 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -259,10 +259,14 @@ struct aste {
 
 int ipte_lock_held(struct kvm_vcpu *vcpu)
 {
-	union ipte_control *ic = kvm_s390_get_ipte_control(vcpu->kvm);
+	if (vcpu->arch.sie_block->eca & 1) {
+		int rc;
 
-	if (vcpu->arch.sie_block->eca & 1)
-		return ic->kh != 0;
+		read_lock(&vcpu->kvm->arch.sca_lock);
+		rc = kvm_s390_get_ipte_control(vcpu->kvm)->kh != 0;
+		read_unlock(&vcpu->kvm->arch.sca_lock);
+		return rc;
+	}
 	return vcpu->kvm->arch.ipte_lock_count != 0;
 }
 
@@ -274,16 +278,20 @@ static void ipte_lock_simple(struct kvm_vcpu *vcpu)
 	vcpu->kvm->arch.ipte_lock_count++;
 	if (vcpu->kvm->arch.ipte_lock_count > 1)
 		goto out;
+retry:
+	read_lock(&vcpu->kvm->arch.sca_lock);
 	ic = kvm_s390_get_ipte_control(vcpu->kvm);
 	do {
 		old = READ_ONCE(*ic);
-		while (old.k) {
+		if (old.k) {
+			read_unlock(&vcpu->kvm->arch.sca_lock);
 			cond_resched();
-			old = READ_ONCE(*ic);
+			goto retry;
 		}
 		new = old;
 		new.k = 1;
 	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	read_unlock(&vcpu->kvm->arch.sca_lock);
 out:
 	mutex_unlock(&vcpu->kvm->arch.ipte_mutex);
 }
@@ -296,12 +304,14 @@ static void ipte_unlock_simple(struct kvm_vcpu *vcpu)
 	vcpu->kvm->arch.ipte_lock_count--;
 	if (vcpu->kvm->arch.ipte_lock_count)
 		goto out;
+	read_lock(&vcpu->kvm->arch.sca_lock);
 	ic = kvm_s390_get_ipte_control(vcpu->kvm);
 	do {
 		old = READ_ONCE(*ic);
 		new = old;
 		new.k = 0;
 	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	read_unlock(&vcpu->kvm->arch.sca_lock);
 	wake_up(&vcpu->kvm->arch.ipte_wq);
 out:
 	mutex_unlock(&vcpu->kvm->arch.ipte_mutex);
@@ -311,23 +321,28 @@ static void ipte_lock_siif(struct kvm_vcpu *vcpu)
 {
 	union ipte_control old, new, *ic;
 
+retry:
+	read_lock(&vcpu->kvm->arch.sca_lock);
 	ic = kvm_s390_get_ipte_control(vcpu->kvm);
 	do {
 		old = READ_ONCE(*ic);
-		while (old.kg) {
+		if (old.kg) {
+			read_unlock(&vcpu->kvm->arch.sca_lock);
 			cond_resched();
-			old = READ_ONCE(*ic);
+			goto retry;
 		}
 		new = old;
 		new.k = 1;
 		new.kh++;
 	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	read_unlock(&vcpu->kvm->arch.sca_lock);
 }
 
 static void ipte_unlock_siif(struct kvm_vcpu *vcpu)
 {
 	union ipte_control old, new, *ic;
 
+	read_lock(&vcpu->kvm->arch.sca_lock);
 	ic = kvm_s390_get_ipte_control(vcpu->kvm);
 	do {
 		old = READ_ONCE(*ic);
@@ -336,6 +351,7 @@ static void ipte_unlock_siif(struct kvm_vcpu *vcpu)
 		if (!new.kh)
 			new.k = 0;
 	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	read_unlock(&vcpu->kvm->arch.sca_lock);
 	if (!new.kh)
 		wake_up(&vcpu->kvm->arch.ipte_wq);
 }
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 60b36b0e2125..831c9ac728ec 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -39,6 +39,7 @@ static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
 {
 	int c, scn;
 
+	read_lock(&vcpu->kvm->arch.sca_lock);
 	if (vcpu->kvm->arch.use_esca) {
 		struct esca_block *sca = vcpu->kvm->arch.sca;
 		union esca_sigp_ctrl sigp_ctrl =
@@ -54,6 +55,7 @@ static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
 		c = sigp_ctrl.c;
 		scn = sigp_ctrl.scn;
 	}
+	read_unlock(&vcpu->kvm->arch.sca_lock);
 
 	if (src_id)
 		*src_id = scn;
@@ -66,6 +68,7 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
 {
 	int expect, rc;
 
+	read_lock(&vcpu->kvm->arch.sca_lock);
 	if (vcpu->kvm->arch.use_esca) {
 		struct esca_block *sca = vcpu->kvm->arch.sca;
 		union esca_sigp_ctrl *sigp_ctrl =
@@ -91,6 +94,7 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
 		expect = old_val.value;
 		rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
 	}
+	read_unlock(&vcpu->kvm->arch.sca_lock);
 
 	if (rc != expect) {
 		/* another external call is pending */
@@ -106,6 +110,7 @@ static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
 	int rc, expect;
 
 	atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
+	read_lock(&vcpu->kvm->arch.sca_lock);
 	if (vcpu->kvm->arch.use_esca) {
 		struct esca_block *sca = vcpu->kvm->arch.sca;
 		union esca_sigp_ctrl *sigp_ctrl =
@@ -123,6 +128,7 @@ static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
 		expect = old.value;
 		rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
 	}
+	read_unlock(&vcpu->kvm->arch.sca_lock);
 	WARN_ON(rc != expect); /* cannot clear? */
 }
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 41b3fed51591..5e884aa890cb 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1080,7 +1080,7 @@ static int kvm_s390_crypto_init(struct kvm *kvm)
 static void sca_dispose(struct kvm *kvm)
 {
 	if (kvm->arch.use_esca)
-		BUG(); /* not implemented yet */
+		free_pages_exact(kvm->arch.sca, sizeof(struct esca_block));
 	else
 		free_page((unsigned long)(kvm->arch.sca));
 	kvm->arch.sca = NULL;
@@ -1110,6 +1110,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	rc = -ENOMEM;
 
 	kvm->arch.use_esca = 0; /* start with basic SCA */
+	rwlock_init(&kvm->arch.sca_lock);
 	kvm->arch.sca = (struct bsca_block *) get_zeroed_page(GFP_KERNEL);
 	if (!kvm->arch.sca)
 		goto out_err;
@@ -1259,6 +1260,7 @@ static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu)
 
 static void sca_del_vcpu(struct kvm_vcpu *vcpu)
 {
+	read_lock(&vcpu->kvm->arch.sca_lock);
 	if (vcpu->kvm->arch.use_esca) {
 		struct esca_block *sca = vcpu->kvm->arch.sca;
 
@@ -1272,11 +1274,13 @@ static void sca_del_vcpu(struct kvm_vcpu *vcpu)
 		if (sca->cpu[vcpu->vcpu_id].sda == (__u64) vcpu->arch.sie_block)
 			sca->cpu[vcpu->vcpu_id].sda = 0;
 	}
+	read_unlock(&vcpu->kvm->arch.sca_lock);
 }
 
 static void sca_add_vcpu(struct kvm_vcpu *vcpu, struct kvm *kvm,
 			unsigned int id)
 {
+	read_lock(&kvm->arch.sca_lock);
 	if (kvm->arch.use_esca) {
 		struct esca_block *sca = kvm->arch.sca;
 
@@ -1294,11 +1298,78 @@ static void sca_add_vcpu(struct kvm_vcpu *vcpu, struct kvm *kvm,
 		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
 		set_bit_inv(id, (unsigned long *) &sca->mcn);
 	}
+	read_unlock(&kvm->arch.sca_lock);
+}
+
+/* Basic SCA to Extended SCA data copy routines */
+static inline void sca_copy_entry(struct esca_entry *d, struct bsca_entry *s)
+{
+	d->sda = s->sda;
+	d->sigp_ctrl.c = s->sigp_ctrl.c;
+	d->sigp_ctrl.scn = s->sigp_ctrl.scn;
+}
+
+static void sca_copy_b_to_e(struct esca_block *d, struct bsca_block *s)
+{
+	int i;
+
+	d->ipte_control = s->ipte_control;
+	d->mcn[0] = s->mcn;
+	for (i = 0; i < KVM_S390_BSCA_CPU_SLOTS; i++)
+		sca_copy_entry(&d->cpu[i], &s->cpu[i]);
+}
+
+static int sca_switch_to_extended(struct kvm *kvm)
+{
+	struct bsca_block *old_sca = kvm->arch.sca;
+	struct esca_block *new_sca;
+	struct kvm_vcpu *vcpu;
+	unsigned int vcpu_idx;
+	u32 scaol, scaoh;
+
+	new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL|__GFP_ZERO);
+	if (!new_sca)
+		return -ENOMEM;
+
+	scaoh = (u32)((u64)(new_sca) >> 32);
+	scaol = (u32)(u64)(new_sca) & ~0x3fU;
+
+	kvm_s390_vcpu_block_all(kvm);
+	write_lock(&kvm->arch.sca_lock);
+
+	sca_copy_b_to_e(new_sca, old_sca);
+
+	kvm_for_each_vcpu(vcpu_idx, vcpu, kvm) {
+		vcpu->arch.sie_block->scaoh = scaoh;
+		vcpu->arch.sie_block->scaol = scaol;
+		vcpu->arch.sie_block->ecb2 |= 0x04U;
+	}
+	kvm->arch.sca = new_sca;
+	kvm->arch.use_esca = 1;
+
+	write_unlock(&kvm->arch.sca_lock);
+	kvm_s390_vcpu_unblock_all(kvm);
+
+	free_page((unsigned long)old_sca);
+
+	VM_EVENT(kvm, 2, "Switched to ESCA (%p -> %p)", old_sca, kvm->arch.sca);
+	return 0;
 }
 
 static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id)
 {
-	return id < KVM_MAX_VCPUS;
+	int rc;
+
+	if (id < KVM_S390_BSCA_CPU_SLOTS)
+		return true;
+	if (!sclp.has_esca)
+		return false;
+
+	mutex_lock(&kvm->lock);
+	rc = kvm->arch.use_esca ? 0 : sca_switch_to_extended(kvm);
+	mutex_unlock(&kvm->lock);
+
+	return rc == 0 && id < KVM_S390_ESCA_CPU_SLOTS;
 }
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
-- 
cgit 


From fe0edcb7311e80a349ad5f2b15f2d91a5606ed7f Mon Sep 17 00:00:00 2001
From: "Eugene (jno) Dvurechenski" <jno@linux.vnet.ibm.com>
Date: Wed, 22 Apr 2015 18:37:40 +0200
Subject: KVM: s390: Enable up to 248 VCPUs per VM

This patch allows s390 to have more than 64 VCPUs for a guest (up to
248 for memory usage considerations), if supported by the underlaying
hardware (sclp.has_esca).

Signed-off-by: Eugene (jno) Dvurechenski <jno@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/include/asm/kvm_host.h | 2 +-
 arch/s390/kvm/kvm-s390.c         | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 86c33863a0ad..12e9291da267 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -27,7 +27,7 @@
 
 #define KVM_S390_BSCA_CPU_SLOTS 64
 #define KVM_S390_ESCA_CPU_SLOTS 248
-#define KVM_MAX_VCPUS KVM_S390_BSCA_CPU_SLOTS
+#define KVM_MAX_VCPUS KVM_S390_ESCA_CPU_SLOTS
 #define KVM_USER_MEM_SLOTS 32
 
 /*
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 5e884aa890cb..16c19fb0af8d 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -246,7 +246,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 	case KVM_CAP_NR_VCPUS:
 	case KVM_CAP_MAX_VCPUS:
-		r = KVM_MAX_VCPUS;
+		r = sclp.has_esca ? KVM_S390_ESCA_CPU_SLOTS
+				  : KVM_S390_BSCA_CPU_SLOTS;
 		break;
 	case KVM_CAP_NR_MEMSLOTS:
 		r = KVM_USER_MEM_SLOTS;
-- 
cgit 


From 2c1bb2be986c56848ce92ba41ba32fc62ab3165f Mon Sep 17 00:00:00 2001
From: David Hildenbrand <dahi@linux.vnet.ibm.com>
Date: Wed, 23 Sep 2015 09:45:50 +0200
Subject: KVM: s390: fast path for sca_ext_call_pending

If CPUSTAT_ECALL_PEND isn't set, we can't have an external call pending,
so we can directly avoid taking the lock.

Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/kvm/interrupt.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 831c9ac728ec..62ec925aa196 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -39,6 +39,9 @@ static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
 {
 	int c, scn;
 
+	if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND))
+		return 0;
+
 	read_lock(&vcpu->kvm->arch.sca_lock);
 	if (vcpu->kvm->arch.use_esca) {
 		struct esca_block *sca = vcpu->kvm->arch.sca;
@@ -60,8 +63,7 @@ static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
 	if (src_id)
 		*src_id = scn;
 
-	return c && atomic_read(&vcpu->arch.sie_block->cpuflags) &
-			CPUSTAT_ECALL_PEND;
+	return c;
 }
 
 static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
-- 
cgit 


From 5f3fe620a56f2f5c79e89522107f2476a45ed6ce Mon Sep 17 00:00:00 2001
From: David Hildenbrand <dahi@linux.vnet.ibm.com>
Date: Mon, 12 Oct 2015 12:34:19 +0200
Subject: KVM: s390: we always have a SCA

Having no sca can never happen, even when something goes wrong when
switching to ESCA. Otherwise we would have a serious bug.
Let's remove this superfluous check.

Acked-by: Dominik Dingel <dingel@linux.vnet.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/kvm/kvm-s390.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 16c19fb0af8d..5c58127b7527 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1608,13 +1608,8 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;
 
 	vcpu->arch.sie_block->icpua = id;
-	if (!kvm_is_ucontrol(kvm)) {
-		if (!kvm->arch.sca) {
-			WARN_ON_ONCE(1);
-			goto out_free_cpu;
-		}
+	if (!kvm_is_ucontrol(kvm))
 		sca_add_vcpu(vcpu, kvm, id);
-	}
 
 	spin_lock_init(&vcpu->arch.local_int.lock);
 	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
-- 
cgit 


From 2550882449299fd55c8214529cc0777b789db0f7 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <dahi@linux.vnet.ibm.com>
Date: Mon, 12 Oct 2015 16:27:23 +0200
Subject: KVM: s390: fix SCA related races and double use

If something goes wrong in kvm_arch_vcpu_create, the VCPU has already
been added to the sca but will never be removed. Trying to create VCPUs
with duplicate ids (e.g. after a failed attempt) is problematic.

Also, when creating multiple VCPUs in parallel, we could theoretically
forget to set the correct SCA when the switch to ESCA happens just
before the VCPU is registered.

Let's add the VCPU to the SCA in kvm_arch_vcpu_postcreate, where we can
be sure that no duplicate VCPU with the same id is around and the VCPU
has already been registered at the VM. We also have to make sure to update
ECB at that point.

Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/kvm/kvm-s390.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 5c58127b7527..2ba5978829f6 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1289,6 +1289,7 @@ static void sca_add_vcpu(struct kvm_vcpu *vcpu, struct kvm *kvm,
 			sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
 		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
 		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca & ~0x3fU;
+		vcpu->arch.sie_block->ecb2 |= 0x04U;
 		set_bit_inv(id, (unsigned long *) sca->mcn);
 	} else {
 		struct bsca_block *sca = kvm->arch.sca;
@@ -1493,8 +1494,11 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 	vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch;
 	preempt_enable();
 	mutex_unlock(&vcpu->kvm->lock);
-	if (!kvm_is_ucontrol(vcpu->kvm))
+	if (!kvm_is_ucontrol(vcpu->kvm)) {
 		vcpu->arch.gmap = vcpu->kvm->arch.gmap;
+		sca_add_vcpu(vcpu, vcpu->kvm, vcpu->vcpu_id);
+	}
+
 }
 
 static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
@@ -1558,8 +1562,6 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 		vcpu->arch.sie_block->ecb |= 0x10;
 
 	vcpu->arch.sie_block->ecb2  = 8;
-	if (vcpu->kvm->arch.use_esca)
-		vcpu->arch.sie_block->ecb2 |= 4;
 	vcpu->arch.sie_block->eca   = 0xC1002000U;
 	if (sclp.has_siif)
 		vcpu->arch.sie_block->eca |= 1;
@@ -1608,9 +1610,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;
 
 	vcpu->arch.sie_block->icpua = id;
-	if (!kvm_is_ucontrol(kvm))
-		sca_add_vcpu(vcpu, kvm, id);
-
 	spin_lock_init(&vcpu->arch.local_int.lock);
 	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
 	vcpu->arch.local_int.wq = &vcpu->wq;
-- 
cgit 


From 10ce32d5b07470c5eb0fa821000c789073128b3f Mon Sep 17 00:00:00 2001
From: David Hildenbrand <dahi@linux.vnet.ibm.com>
Date: Mon, 12 Oct 2015 12:41:41 +0200
Subject: KVM: s390: always set/clear the SCA sda field

Let's always set and clear the sda when enabling/disabling a VCPU.
Dealing with sda being set to something else makes no sense anymore
as we enable a VCPU in the SCA now after it has been registered at
the VM.

Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/kvm/kvm-s390.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2ba5978829f6..7e0092bea6e9 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1266,14 +1266,12 @@ static void sca_del_vcpu(struct kvm_vcpu *vcpu)
 		struct esca_block *sca = vcpu->kvm->arch.sca;
 
 		clear_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
-		if (sca->cpu[vcpu->vcpu_id].sda == (__u64) vcpu->arch.sie_block)
-			sca->cpu[vcpu->vcpu_id].sda = 0;
+		sca->cpu[vcpu->vcpu_id].sda = 0;
 	} else {
 		struct bsca_block *sca = vcpu->kvm->arch.sca;
 
 		clear_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
-		if (sca->cpu[vcpu->vcpu_id].sda == (__u64) vcpu->arch.sie_block)
-			sca->cpu[vcpu->vcpu_id].sda = 0;
+		sca->cpu[vcpu->vcpu_id].sda = 0;
 	}
 	read_unlock(&vcpu->kvm->arch.sca_lock);
 }
@@ -1285,8 +1283,7 @@ static void sca_add_vcpu(struct kvm_vcpu *vcpu, struct kvm *kvm,
 	if (kvm->arch.use_esca) {
 		struct esca_block *sca = kvm->arch.sca;
 
-		if (!sca->cpu[id].sda)
-			sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
+		sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
 		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
 		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca & ~0x3fU;
 		vcpu->arch.sie_block->ecb2 |= 0x04U;
@@ -1294,8 +1291,7 @@ static void sca_add_vcpu(struct kvm_vcpu *vcpu, struct kvm *kvm,
 	} else {
 		struct bsca_block *sca = kvm->arch.sca;
 
-		if (!sca->cpu[id].sda)
-			sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
+		sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
 		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
 		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
 		set_bit_inv(id, (unsigned long *) &sca->mcn);
-- 
cgit 


From eaa78f343255dabac963ab8c7644367844d18e00 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <dahi@linux.vnet.ibm.com>
Date: Mon, 12 Oct 2015 16:29:01 +0200
Subject: KVM: s390: cleanup sca_add_vcpu

Now that we already have kvm and the VCPU id set for the VCPU, we can
convert sda_add_vcpu to look much more like sda_del_vcpu.

Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/kvm/kvm-s390.c | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 7e0092bea6e9..d9d71bb91404 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1276,27 +1276,26 @@ static void sca_del_vcpu(struct kvm_vcpu *vcpu)
 	read_unlock(&vcpu->kvm->arch.sca_lock);
 }
 
-static void sca_add_vcpu(struct kvm_vcpu *vcpu, struct kvm *kvm,
-			unsigned int id)
+static void sca_add_vcpu(struct kvm_vcpu *vcpu)
 {
-	read_lock(&kvm->arch.sca_lock);
-	if (kvm->arch.use_esca) {
-		struct esca_block *sca = kvm->arch.sca;
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	if (vcpu->kvm->arch.use_esca) {
+		struct esca_block *sca = vcpu->kvm->arch.sca;
 
-		sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
+		sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block;
 		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
 		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca & ~0x3fU;
 		vcpu->arch.sie_block->ecb2 |= 0x04U;
-		set_bit_inv(id, (unsigned long *) sca->mcn);
+		set_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
 	} else {
-		struct bsca_block *sca = kvm->arch.sca;
+		struct bsca_block *sca = vcpu->kvm->arch.sca;
 
-		sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
+		sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block;
 		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
 		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
-		set_bit_inv(id, (unsigned long *) &sca->mcn);
+		set_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
 	}
-	read_unlock(&kvm->arch.sca_lock);
+	read_unlock(&vcpu->kvm->arch.sca_lock);
 }
 
 /* Basic SCA to Extended SCA data copy routines */
@@ -1492,7 +1491,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 	mutex_unlock(&vcpu->kvm->lock);
 	if (!kvm_is_ucontrol(vcpu->kvm)) {
 		vcpu->arch.gmap = vcpu->kvm->arch.gmap;
-		sca_add_vcpu(vcpu, vcpu->kvm, vcpu->vcpu_id);
+		sca_add_vcpu(vcpu);
 	}
 
 }
-- 
cgit 


From 4215825eeb1f704d1bd327ca01fb753b53ea34d3 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <dahi@linux.vnet.ibm.com>
Date: Mon, 12 Oct 2015 12:57:22 +0200
Subject: KVM: s390: don't switch to ESCA for ucontrol

sca_add_vpcu is not called for ucontrol guests. We must also not
apply the sca checking for sca_can_add_vcpu as ucontrol guests
do not have to follow the sca limits.

As common code already checks that id < KVM_MAX_VCPUS all other
data structures are safe as well.

Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/kvm/kvm-s390.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index d9d71bb91404..539d3857a59a 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1588,7 +1588,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	struct sie_page *sie_page;
 	int rc = -EINVAL;
 
-	if (!sca_can_add_vcpu(kvm, id))
+	if (!kvm_is_ucontrol(kvm) && !sca_can_add_vcpu(kvm, id))
 		goto out;
 
 	rc = -ENOMEM;
-- 
cgit 


From 8dfd523f8523779210038264259546299a8398e9 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <dahi@linux.vnet.ibm.com>
Date: Tue, 24 Feb 2015 15:51:55 +0100
Subject: s390/sclp: introduce check for SIE

This patch adds a way to check if the SIE with zArchitecture support is
available.

Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/include/asm/sclp.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 8324abbdaeaf..dea883f85d66 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -29,7 +29,10 @@ struct sclp_ipl_info {
 
 struct sclp_core_entry {
 	u8 core_id;
-	u8 reserved0[2];
+	u8 reserved0;
+	u8 : 4;
+	u8 sief2 : 1;
+	u8 : 3;
 	u8 : 3;
 	u8 siif : 1;
 	u8 sigpif : 1;
@@ -55,6 +58,7 @@ struct sclp_info {
 	unsigned char has_sprp : 1;
 	unsigned char has_hvs : 1;
 	unsigned char has_esca : 1;
+	unsigned char has_sief2 : 1;
 	unsigned int ibc;
 	unsigned int mtid;
 	unsigned int mtid_cp;
-- 
cgit 


From 7f16d7e787b731d9db273b822b4b8069102e57a6 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <dahi@linux.vnet.ibm.com>
Date: Tue, 24 Feb 2015 15:54:47 +0100
Subject: s390: show virtualization support in /proc/cpuinfo

This patch exposes the SIE capability (aka virtualization support) via
/proc/cpuinfo -> "features" as "sie".

As we don't want to expose this hwcap via elf, let's add a second,
"internal"/non-elf capability list. The content is simply concatenated
to the existing features when printing /proc/cpuinfo.

We also add the defines to elf.h to keep the hwcap stuff at a common
place.

Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/include/asm/elf.h  | 7 +++++++
 arch/s390/kernel/processor.c | 6 ++++++
 arch/s390/kernel/setup.c     | 9 +++++++++
 3 files changed, 22 insertions(+)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index bab6739a1154..08e34a5dc909 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -104,6 +104,9 @@
 #define HWCAP_S390_TE		1024
 #define HWCAP_S390_VXRS		2048
 
+/* Internal bits, not exposed via elf */
+#define HWCAP_INT_SIE		1UL
+
 /*
  * These are used to set parameters in the core dumps.
  */
@@ -169,6 +172,10 @@ extern unsigned int vdso_enabled;
 extern unsigned long elf_hwcap;
 #define ELF_HWCAP (elf_hwcap)
 
+/* Internal hardware capabilities, not exposed via elf */
+
+extern unsigned long int_hwcap;
+
 /* This yields a string that ld.so will use to load implementation
    specific libraries for optimization.  This is more specific in
    intent than poking at uname or /proc/cpuinfo.
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 7ce00e7a709a..647128d5b983 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -61,6 +61,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
 		"edat", "etf3eh", "highgprs", "te", "vx"
 	};
+	static const char * const int_hwcap_str[] = {
+		"sie"
+	};
 	unsigned long n = (unsigned long) v - 1;
 	int i;
 
@@ -75,6 +78,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		for (i = 0; i < ARRAY_SIZE(hwcap_str); i++)
 			if (hwcap_str[i] && (elf_hwcap & (1UL << i)))
 				seq_printf(m, "%s ", hwcap_str[i]);
+		for (i = 0; i < ARRAY_SIZE(int_hwcap_str); i++)
+			if (int_hwcap_str[i] && (int_hwcap & (1UL << i)))
+				seq_printf(m, "%s ", int_hwcap_str[i]);
 		seq_puts(m, "\n");
 		show_cacheinfo(m);
 	}
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index c837bcacf218..dc83ae66a730 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -80,6 +80,8 @@ EXPORT_SYMBOL(console_irq);
 unsigned long elf_hwcap __read_mostly = 0;
 char elf_platform[ELF_PLATFORM_SIZE];
 
+unsigned long int_hwcap = 0;
+
 int __initdata memory_end_set;
 unsigned long __initdata memory_end;
 unsigned long __initdata max_physmem_end;
@@ -793,6 +795,13 @@ static int __init setup_hwcaps(void)
 		strcpy(elf_platform, "z13");
 		break;
 	}
+
+	/*
+	 * Virtualization support HWCAP_INT_SIE is bit 0.
+	 */
+	if (sclp.has_sief2)
+		int_hwcap |= HWCAP_INT_SIE;
+
 	return 0;
 }
 arch_initcall(setup_hwcaps);
-- 
cgit 


From 07197fd05fa3eb2e8a5aae92938ca5d07bcac9fc Mon Sep 17 00:00:00 2001
From: David Hildenbrand <dahi@linux.vnet.ibm.com>
Date: Fri, 30 Jan 2015 16:01:38 +0100
Subject: KVM: s390: don't load kvm without virtualization support

If we don't have support for virtualization (SIE), e.g. when running under
a hypervisor not supporting execution of the SIE instruction, we should
immediately abort loading the kvm module, as the SIE instruction cannot
be enabled dynamically.

Currently, the SIE instructions fails with an exception on a non-SIE
host, resulting in the guest making no progress, instead of failing hard.

Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/kvm/kvm-s390.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 539d3857a59a..49d33190bd98 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2859,6 +2859,11 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 
 static int __init kvm_s390_init(void)
 {
+	if (!sclp.has_sief2) {
+		pr_info("SIE not available\n");
+		return -ENODEV;
+	}
+
 	return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
 }
 
-- 
cgit 


From a6aacc3f87dfd44425fc17ea9875a5c2ad917227 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Tue, 24 Nov 2015 14:28:12 +0100
Subject: KVM: s390: remove pointless test_facility(2) check

This evaluates always to 'true'.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/kvm/kvm-s390.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 49d33190bd98..77724ce0cb82 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1027,7 +1027,7 @@ static int kvm_s390_apxa_installed(void)
 	u8 config[128];
 	int cc;
 
-	if (test_facility(2) && test_facility(12)) {
+	if (test_facility(12)) {
 		cc = kvm_s390_query_ap_config(config);
 
 		if (cc)
-- 
cgit 


From 2f8a43d45d14ad62b105ed99151b453c12df7149 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Fri, 27 Nov 2015 11:00:54 +0100
Subject: KVM: s390: remove redudant assigment of error code

rc already contains -ENOMEM, no need to assign it twice.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
---
 arch/s390/kvm/kvm-s390.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 77724ce0cb82..6857262eb7ae 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1618,10 +1618,8 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	 */
 	vcpu->arch.guest_fpregs.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS,
 					       GFP_KERNEL);
-	if (!vcpu->arch.guest_fpregs.fprs) {
-		rc = -ENOMEM;
+	if (!vcpu->arch.guest_fpregs.fprs)
 		goto out_free_sie_block;
-	}
 
 	rc = kvm_vcpu_init(vcpu, kvm, id);
 	if (rc)
-- 
cgit 


From d5a73cadf3fdec95e9518ee5bb91bd0747c42b30 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Tue, 27 Oct 2015 12:53:49 -0700
Subject: lcoking/barriers, arch: Use smp barriers in smp_store_release()

With commit b92b8b35a2e ("locking/arch: Rename set_mb() to smp_store_mb()")
it was made clear that the context of this call (and thus set_mb)
is strictly for CPU ordering, as opposed to IO. As such all archs
should use the smp variant of mb(), respecting the semantics and
saving a mandatory barrier on UP.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <linux-arch@vger.kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: dave@stgolabs.net
Link: http://lkml.kernel.org/r/1445975631-17047-3-git-send-email-dave@stgolabs.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/s390/include/asm/barrier.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index d68e11e0df5e..7ffd0b19135c 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -36,7 +36,7 @@
 #define smp_mb__before_atomic()		smp_mb()
 #define smp_mb__after_atomic()		smp_mb()
 
-#define smp_store_mb(var, value)		do { WRITE_ONCE(var, value); mb(); } while (0)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 
 #define smp_store_release(p, v)						\
 do {									\
-- 
cgit 


From 7523e4dc5057e157212b4741abd6256e03404cf1 Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Thu, 26 Nov 2015 09:44:08 +1030
Subject: module: use a structure to encapsulate layout.

Makes it easier to handle init vs core cleanly, though the change is
fairly invasive across random architectures.

It simplifies the rbtree code immediately, however, while keeping the
core data together in the same cachline (now iff the rbtree code is
enabled).

Acked-by: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 arch/s390/kernel/module.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index 0c1a679314dd..7873e171457c 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -159,11 +159,11 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 
 	/* Increase core size by size of got & plt and set start
 	   offsets for got and plt. */
-	me->core_size = ALIGN(me->core_size, 4);
-	me->arch.got_offset = me->core_size;
-	me->core_size += me->arch.got_size;
-	me->arch.plt_offset = me->core_size;
-	me->core_size += me->arch.plt_size;
+	me->core_layout.size = ALIGN(me->core_layout.size, 4);
+	me->arch.got_offset = me->core_layout.size;
+	me->core_layout.size += me->arch.got_size;
+	me->arch.plt_offset = me->core_layout.size;
+	me->core_layout.size += me->arch.plt_size;
 	return 0;
 }
 
@@ -279,7 +279,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab,
 		if (info->got_initialized == 0) {
 			Elf_Addr *gotent;
 
-			gotent = me->module_core + me->arch.got_offset +
+			gotent = me->core_layout.base + me->arch.got_offset +
 				info->got_offset;
 			*gotent = val;
 			info->got_initialized = 1;
@@ -302,7 +302,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab,
 			rc = apply_rela_bits(loc, val, 0, 64, 0);
 		else if (r_type == R_390_GOTENT ||
 			 r_type == R_390_GOTPLTENT) {
-			val += (Elf_Addr) me->module_core - loc;
+			val += (Elf_Addr) me->core_layout.base - loc;
 			rc = apply_rela_bits(loc, val, 1, 32, 1);
 		}
 		break;
@@ -315,7 +315,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab,
 	case R_390_PLTOFF64:	/* 16 bit offset from GOT to PLT. */
 		if (info->plt_initialized == 0) {
 			unsigned int *ip;
-			ip = me->module_core + me->arch.plt_offset +
+			ip = me->core_layout.base + me->arch.plt_offset +
 				info->plt_offset;
 			ip[0] = 0x0d10e310; /* basr 1,0; lg 1,10(1); br 1 */
 			ip[1] = 0x100a0004;
@@ -334,7 +334,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab,
 			       val - loc + 0xffffUL < 0x1ffffeUL) ||
 			      (r_type == R_390_PLT32DBL &&
 			       val - loc + 0xffffffffULL < 0x1fffffffeULL)))
-				val = (Elf_Addr) me->module_core +
+				val = (Elf_Addr) me->core_layout.base +
 					me->arch.plt_offset +
 					info->plt_offset;
 			val += rela->r_addend - loc;
@@ -356,7 +356,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab,
 	case R_390_GOTOFF32:	/* 32 bit offset to GOT.  */
 	case R_390_GOTOFF64:	/* 64 bit offset to GOT. */
 		val = val + rela->r_addend -
-			((Elf_Addr) me->module_core + me->arch.got_offset);
+			((Elf_Addr) me->core_layout.base + me->arch.got_offset);
 		if (r_type == R_390_GOTOFF16)
 			rc = apply_rela_bits(loc, val, 0, 16, 0);
 		else if (r_type == R_390_GOTOFF32)
@@ -366,7 +366,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab,
 		break;
 	case R_390_GOTPC:	/* 32 bit PC relative offset to GOT. */
 	case R_390_GOTPCDBL:	/* 32 bit PC rel. off. to GOT shifted by 1. */
-		val = (Elf_Addr) me->module_core + me->arch.got_offset +
+		val = (Elf_Addr) me->core_layout.base + me->arch.got_offset +
 			rela->r_addend - loc;
 		if (r_type == R_390_GOTPC)
 			rc = apply_rela_bits(loc, val, 1, 32, 0);
-- 
cgit 


From 7ec7c8c70b26de90f61be7523a6ad14df911219f Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Wed, 2 Dec 2015 14:27:03 +0100
Subject: KVM: s390: use assignment instead of memcpy

Replace two memcpy with proper assignment.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/kvm/kvm-s390.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 6857262eb7ae..6dec01d6c1c4 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2120,7 +2120,8 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
 	 */
 	kvm_check_async_pf_completion(vcpu);
 
-	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
+	vcpu->arch.sie_block->gg14 = vcpu->run->s.regs.gprs[14];
+	vcpu->arch.sie_block->gg15 = vcpu->run->s.regs.gprs[15];
 
 	if (need_resched())
 		schedule();
@@ -2185,7 +2186,8 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
 	if (guestdbg_enabled(vcpu))
 		kvm_s390_restore_guest_per_regs(vcpu);
 
-	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
+	vcpu->run->s.regs.gprs[14] = vcpu->arch.sie_block->gg14;
+	vcpu->run->s.regs.gprs[15] = vcpu->arch.sie_block->gg15;
 
 	if (vcpu->arch.sie_block->icptcode > 0) {
 		int rc = kvm_handle_sie_intercept(vcpu);
-- 
cgit 


From 8335713ad08caf2c3dfcb5bc2c93d7e0276142d4 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Tue, 8 Dec 2015 16:55:27 +0100
Subject: KVM: s390: obey kptr_restrict in traces

The s390dbf and trace events provide a debugfs interface.
If kptr_restrict is active, we should not expose kernel
pointers. We can fence the debugfs output by using %pK
instead of %p.

Cc: Kees Cook <keescook@chromium.org>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/kvm/kvm-s390.c   | 9 +++++----
 arch/s390/kvm/trace-s390.h | 6 +++---
 2 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 6dec01d6c1c4..c14845c3a6f8 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1185,7 +1185,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	kvm->arch.epoch = 0;
 
 	spin_lock_init(&kvm->arch.start_stop_lock);
-	KVM_EVENT(3, "vm 0x%p created by pid %u", kvm, current->pid);
+	KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
 
 	return 0;
 out_err:
@@ -1245,7 +1245,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		gmap_free(kvm->arch.gmap);
 	kvm_s390_destroy_adapters(kvm);
 	kvm_s390_clear_float_irqs(kvm);
-	KVM_EVENT(3, "vm 0x%p destroyed", kvm);
+	KVM_EVENT(3, "vm 0x%pK destroyed", kvm);
 }
 
 /* Section: vcpu related */
@@ -1349,7 +1349,8 @@ static int sca_switch_to_extended(struct kvm *kvm)
 
 	free_page((unsigned long)old_sca);
 
-	VM_EVENT(kvm, 2, "Switched to ESCA (%p -> %p)", old_sca, kvm->arch.sca);
+	VM_EVENT(kvm, 2, "Switched to ESCA (0x%pK -> 0x%pK)",
+		 old_sca, kvm->arch.sca);
 	return 0;
 }
 
@@ -1624,7 +1625,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	rc = kvm_vcpu_init(vcpu, kvm, id);
 	if (rc)
 		goto out_free_sie_block;
-	VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
+	VM_EVENT(kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", id, vcpu,
 		 vcpu->arch.sie_block);
 	trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
 
diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h
index cc1d6c68356f..396485bca191 100644
--- a/arch/s390/kvm/trace-s390.h
+++ b/arch/s390/kvm/trace-s390.h
@@ -55,8 +55,8 @@ TRACE_EVENT(kvm_s390_create_vcpu,
 		    __entry->sie_block = sie_block;
 		    ),
 
-	    TP_printk("create cpu %d at %p, sie block at %p", __entry->id,
-		      __entry->vcpu, __entry->sie_block)
+	    TP_printk("create cpu %d at 0x%pK, sie block at 0x%pK",
+		      __entry->id, __entry->vcpu, __entry->sie_block)
 	);
 
 TRACE_EVENT(kvm_s390_destroy_vcpu,
@@ -254,7 +254,7 @@ TRACE_EVENT(kvm_s390_enable_css,
 		    __entry->kvm = kvm;
 		    ),
 
-	    TP_printk("enabling channel I/O support (kvm @ %p)\n",
+	    TP_printk("enabling channel I/O support (kvm @ %pK)\n",
 		      __entry->kvm)
 	);
 
-- 
cgit 


From a3a92c31bf0b57ad0ca7f092a6f3a57168ba9ae2 Mon Sep 17 00:00:00 2001
From: Dominik Dingel <dingel@linux.vnet.ibm.com>
Date: Mon, 1 Dec 2014 17:24:42 +0100
Subject: KVM: s390: fix mismatch between user and in-kernel guest limit

While the userspace interface requests the maximum size the gmap code
expects to get a maximum address.

This error resulted in bigger page tables than necessary for some guest
sizes, e.g. a 2GB guest used 3 levels instead of 2.

At the same time we introduce KVM_S390_NO_MEM_LIMIT, which allows in a
bright future that a guest spans the complete 64 bit address space.

We also switch to TASK_MAX_SIZE for the initial memory size, this is a
cosmetic change as the previous size also resulted in a 4 level pagetable
creation.

Reported-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Dominik Dingel <dingel@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/include/asm/kvm_host.h |  1 +
 arch/s390/include/uapi/asm/kvm.h |  2 ++
 arch/s390/kvm/kvm-s390.c         | 25 ++++++++++++++++++++-----
 arch/s390/mm/pgtable.c           |  4 ++--
 4 files changed, 25 insertions(+), 7 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 12e9291da267..c83144110ea9 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -627,6 +627,7 @@ struct kvm_arch{
 	struct kvm_s390_float_interrupt float_int;
 	struct kvm_device *flic;
 	struct gmap *gmap;
+	unsigned long mem_limit;
 	int css_support;
 	int use_irqchip;
 	int use_cmma;
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index ef1a5fcc6c66..d2aea31252f2 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -66,6 +66,8 @@ struct kvm_s390_io_adapter_req {
 #define KVM_S390_VM_MEM_CLR_CMMA	1
 #define KVM_S390_VM_MEM_LIMIT_SIZE	2
 
+#define KVM_S390_NO_MEM_LIMIT		U64_MAX
+
 /* kvm attributes for KVM_S390_VM_TOD */
 #define KVM_S390_VM_TOD_LOW		0
 #define KVM_S390_VM_TOD_HIGH		1
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index c14845c3a6f8..8aa5e55a8ecd 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -378,8 +378,8 @@ static int kvm_s390_get_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 	case KVM_S390_VM_MEM_LIMIT_SIZE:
 		ret = 0;
 		VM_EVENT(kvm, 3, "QUERY: max guest memory: %lu bytes",
-			 kvm->arch.gmap->asce_end);
-		if (put_user(kvm->arch.gmap->asce_end, (u64 __user *)attr->addr))
+			 kvm->arch.mem_limit);
+		if (put_user(kvm->arch.mem_limit, (u64 __user *)attr->addr))
 			ret = -EFAULT;
 		break;
 	default:
@@ -431,9 +431,17 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 		if (get_user(new_limit, (u64 __user *)attr->addr))
 			return -EFAULT;
 
-		if (new_limit > kvm->arch.gmap->asce_end)
+		if (kvm->arch.mem_limit != KVM_S390_NO_MEM_LIMIT &&
+		    new_limit > kvm->arch.mem_limit)
 			return -E2BIG;
 
+		if (!new_limit)
+			return -EINVAL;
+
+		/* gmap_alloc takes last usable address */
+		if (new_limit != KVM_S390_NO_MEM_LIMIT)
+			new_limit -= 1;
+
 		ret = -EBUSY;
 		mutex_lock(&kvm->lock);
 		if (atomic_read(&kvm->online_vcpus) == 0) {
@@ -450,7 +458,9 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 			}
 		}
 		mutex_unlock(&kvm->lock);
-		VM_EVENT(kvm, 3, "SET: max guest memory: %lu bytes", new_limit);
+		VM_EVENT(kvm, 3, "SET: max guest address: %lu", new_limit);
+		VM_EVENT(kvm, 3, "New guest asce: 0x%pK",
+			 (void *) kvm->arch.gmap->asce);
 		break;
 	}
 	default:
@@ -1172,8 +1182,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	if (type & KVM_VM_S390_UCONTROL) {
 		kvm->arch.gmap = NULL;
+		kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT;
 	} else {
-		kvm->arch.gmap = gmap_alloc(current->mm, (1UL << 44) - 1);
+		kvm->arch.mem_limit = TASK_MAX_SIZE;
+		kvm->arch.gmap = gmap_alloc(current->mm, kvm->arch.mem_limit - 1);
 		if (!kvm->arch.gmap)
 			goto out_err;
 		kvm->arch.gmap->private = kvm;
@@ -2829,6 +2841,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	if (mem->memory_size & 0xffffful)
 		return -EINVAL;
 
+	if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit)
+		return -EINVAL;
+
 	return 0;
 }
 
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 54ef3bc01b43..63b039899a5e 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -133,7 +133,7 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
 /**
  * gmap_alloc - allocate a guest address space
  * @mm: pointer to the parent mm_struct
- * @limit: maximum size of the gmap address space
+ * @limit: maximum address of the gmap address space
  *
  * Returns a guest address space structure.
  */
@@ -402,7 +402,7 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from,
 	if ((from | to | len) & (PMD_SIZE - 1))
 		return -EINVAL;
 	if (len == 0 || from + len < from || to + len < to ||
-	    from + len > TASK_MAX_SIZE || to + len > gmap->asce_end)
+	    from + len - 1 > TASK_MAX_SIZE || to + len - 1 > gmap->asce_end)
 		return -EINVAL;
 
 	flush = 0;
-- 
cgit 


From 32e6b236d26946eb076d1450bfb8f9978f15d6b9 Mon Sep 17 00:00:00 2001
From: Guenther Hutzl <hutzl@linux.vnet.ibm.com>
Date: Mon, 1 Dec 2014 17:24:42 +0100
Subject: KVM: s390: consider system MHA for guest storage

Verify that the guest maximum storage address is below the MHA (maximum
host address) value allowed on the host.

Acked-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Guenther Hutzl <hutzl@linux.vnet.ibm.com>
Signed-off-by: Dominik Dingel <dingel@linux.vnet.ibm.com>
[adopt to match recent limit,size changes]

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/kvm/kvm-s390.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 8aa5e55a8ecd..940e9ff231a3 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1184,7 +1184,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		kvm->arch.gmap = NULL;
 		kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT;
 	} else {
-		kvm->arch.mem_limit = TASK_MAX_SIZE;
+		if (sclp.hamax == U64_MAX)
+			kvm->arch.mem_limit = TASK_MAX_SIZE;
+		else
+			kvm->arch.mem_limit = min_t(unsigned long, TASK_MAX_SIZE,
+						    sclp.hamax + 1);
 		kvm->arch.gmap = gmap_alloc(current->mm, kvm->arch.mem_limit - 1);
 		if (!kvm->arch.gmap)
 			goto out_err;
-- 
cgit 


From 9552a66fe622ed53b87278a90917a37a5245e68a Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Tue, 24 Nov 2015 12:18:22 +0100
Subject: s390/facilities: use stfl mnemonic instead of insn magic

Now that 31 bit support is gone, the assembler always knows about the
stfl instruction. Therefore lets use a readable mnemonic.  Also remove
the not needed extable entry for the inline assembly and fix the
output constraint.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/facility.h | 6 ++----
 arch/s390/kernel/head.S          | 2 +-
 2 files changed, 3 insertions(+), 5 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h
index 0aa6a7ed95a3..b4f99d22ba04 100644
--- a/arch/s390/include/asm/facility.h
+++ b/arch/s390/include/asm/facility.h
@@ -44,10 +44,8 @@ static inline void stfle(u64 *stfle_fac_list, int size)
 
 	preempt_disable();
 	asm volatile(
-		"	.insn s,0xb2b10000,0(0)\n" /* stfl */
-		"0:\n"
-		EX_TABLE(0b, 0b)
-		: "+m" (S390_lowcore.stfl_fac_list));
+		"	stfl	0(0)\n"
+		: "=m" (S390_lowcore.stfl_fac_list));
 	nr = 4; /* bytes stored by stfl */
 	memcpy(stfle_fac_list, &S390_lowcore.stfl_fac_list, 4);
 	if (S390_lowcore.stfl_fac_list & 0x01000000) {
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index 301ee9c70688..d893d5aeb307 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -306,7 +306,7 @@ ENTRY(startup_kdump)
 	mvc	__LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13)
 	xc	__LC_STFL_FAC_LIST(8),__LC_STFL_FAC_LIST
 	# check capabilities against MARCH_{G5,Z900,Z990,Z9_109,Z10}
-	.insn	s,0xb2b10000,0		# store facilities @ __LC_STFL_FAC_LIST
+	stfl	0(%r0)			# store facilities @ __LC_STFL_FAC_LIST
 	tm	__LC_STFL_FAC_LIST,0x01	# stfle available ?
 	jz	0f
 	la	%r0,1
-- 
cgit 


From 76cdd44c2e56ffabc297494c090c6babc8985998 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Tue, 24 Nov 2015 12:33:07 +0100
Subject: s390/facilities: always use lowcore's stfle field for storing
 facility bits

head.s contains an stfle instruction which stores it result at the
storage location that is assigned to the stfl instruction.

This is currently no problem, since we only care about one double
word. However if the number of double words in the ALS bitfield grows
the current code is not very stable.

E.g. before issuing the stfle command the memory to which it stores
must be cleared, since the instruction may or may not clear memory
contents where no bits are set.

In order to simplify the code a bit always use the storage location
that we reserved for the stfle result.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/asm-offsets.c |  1 +
 arch/s390/kernel/head.S        | 10 +++++-----
 arch/s390/kernel/head64.S      |  2 +-
 3 files changed, 7 insertions(+), 6 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index ae7b565b6c4c..d8d18f8d8b77 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -120,6 +120,7 @@ int main(void)
 	OFFSET(__LC_IO_INT_PARM, _lowcore, io_int_parm);
 	OFFSET(__LC_IO_INT_WORD, _lowcore, io_int_word);
 	OFFSET(__LC_STFL_FAC_LIST, _lowcore, stfl_fac_list);
+	OFFSET(__LC_STFLE_FAC_LIST, _lowcore, stfle_fac_list);
 	OFFSET(__LC_MCCK_CODE, _lowcore, mcck_interruption_code);
 	OFFSET(__LC_MCCK_FAIL_STOR_ADDR, _lowcore, failing_storage_address);
 	OFFSET(__LC_LAST_BREAK, _lowcore, breaking_event_addr);
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index d893d5aeb307..d28a14849126 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -300,19 +300,19 @@ ENTRY(startup_kdump)
 	xc	0x200(256),0x200	# partially clear lowcore
 	xc	0x300(256),0x300
 	xc	0xe00(256),0xe00
+	xc	0xf00(256),0xf00
 	lctlg	%c0,%c15,0x200(%r0)	# initialize control registers
 	stck	__LC_LAST_UPDATE_CLOCK
 	spt	6f-.LPG0(%r13)
 	mvc	__LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13)
-	xc	__LC_STFL_FAC_LIST(8),__LC_STFL_FAC_LIST
-	# check capabilities against MARCH_{G5,Z900,Z990,Z9_109,Z10}
 	stfl	0(%r0)			# store facilities @ __LC_STFL_FAC_LIST
-	tm	__LC_STFL_FAC_LIST,0x01	# stfle available ?
+	mvc	__LC_STFLE_FAC_LIST(4),__LC_STFL_FAC_LIST
+	tm	__LC_STFLE_FAC_LIST,0x01	# stfle available ?
 	jz	0f
 	la	%r0,1
-	.insn	s,0xb2b00000,__LC_STFL_FAC_LIST	# store facility list extended
+	.insn	s,0xb2b00000,__LC_STFLE_FAC_LIST # store facility list extended
 	# verify if all required facilities are supported by the machine
-0:	la	%r1,__LC_STFL_FAC_LIST
+0:	la	%r1,__LC_STFLE_FAC_LIST
 	la	%r2,3f+8-.LPG0(%r13)
 	l	%r3,0(%r2)
 1:	l	%r0,0(%r1)
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 58b719fa8067..c5febe84eba6 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -16,7 +16,7 @@
 
 __HEAD
 ENTRY(startup_continue)
-	tm	__LC_STFL_FAC_LIST+6,0x80	# LPP available ?
+	tm	__LC_STFLE_FAC_LIST+6,0x80	# LPP available ?
 	jz	0f
 	xc	__LC_LPP+1(7,0),__LC_LPP+1	# clear lpp and current_pid
 	mvi	__LC_LPP,0x80			#   and set LPP_MAGIC
-- 
cgit 


From c30f6828fed9d33c2d54dfaf3621717c56f9c779 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Mon, 2 Feb 2015 07:08:44 +0100
Subject: s390/facilities: add helper tool to generate facility lists

Modifying the architecture level set facility lists was always very
error prone. Given the numbering of the facility bits within the
Principles of Operation, where the most significant bit number is 0,
it happened a lot of times that wrong bits were set or cleared.

Therefore this patch adds a tool "gen_facilities" which generates
include/generated/facilites.h.  The definition of the bits to be set
is contained within arch/s390/include/asm/facilities_src.h and can be
easily extended to e.g. also generate such lists for the KVM module.

The generated file looks like this:

 #define FACILITIES_ALS _AC(0xc1006450f0040000,UL)
 #define FACILITIES_ALS_DWORDS 1

The facility bits defined in this patch match 1:1 to the current masks
that can be found in head.S.

That is if the tool gets executed with -march=z990 then the generated
masks will equal the masks in head.S for CONFIG_MARCH_Z990.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Makefile                     |  5 +++
 arch/s390/include/asm/facilities_src.h | 67 ++++++++++++++++++++++++++++++++++
 arch/s390/include/asm/facility.h       |  5 +++
 arch/s390/tools/.gitignore             |  1 +
 arch/s390/tools/Makefile               | 15 ++++++++
 arch/s390/tools/gen_facilities.c       | 67 ++++++++++++++++++++++++++++++++++
 6 files changed, 160 insertions(+)
 create mode 100644 arch/s390/include/asm/facilities_src.h
 create mode 100644 arch/s390/tools/.gitignore
 create mode 100644 arch/s390/tools/Makefile
 create mode 100644 arch/s390/tools/gen_facilities.c

(limited to 'arch/s390')

diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 647bd14b223e..224b42734f0d 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -106,6 +106,7 @@ drivers-y	+= drivers/s390/
 drivers-$(CONFIG_OPROFILE)	+= arch/s390/oprofile/
 
 boot		:= arch/s390/boot
+tools		:= arch/s390/tools
 
 all: image bzImage
 
@@ -124,6 +125,10 @@ vdso_install:
 
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
+	$(Q)$(MAKE) $(clean)=$(tools)
+
+archprepare:
+	$(Q)$(MAKE) $(build)=$(tools) include/generated/facilities.h
 
 # Don't use tabs in echo arguments
 define archhelp
diff --git a/arch/s390/include/asm/facilities_src.h b/arch/s390/include/asm/facilities_src.h
new file mode 100644
index 000000000000..4555fa69a29e
--- /dev/null
+++ b/arch/s390/include/asm/facilities_src.h
@@ -0,0 +1,67 @@
+/*
+ *    Copyright IBM Corp. 2015
+ */
+
+#ifndef S390_GEN_FACILITIES_C
+#error "This file can only be included by gen_facilities.c"
+#endif
+
+#include <linux/kconfig.h>
+
+struct facility_def {
+	char *name;
+	int *bits;
+};
+
+static struct facility_def facility_defs[] = {
+	{
+		/*
+		 * FACILITIES_ALS contains the list of facilities that are
+		 * required to run a kernel that is compiled e.g. with
+		 * -march=<machine>.
+		 */
+		.name = "FACILITIES_ALS",
+		.bits = (int[]){
+#ifdef CONFIG_HAVE_MARCH_Z900_FEATURES
+			0,  /* N3 instructions */
+			1,  /* z/Arch mode installed */
+#endif
+#ifdef CONFIG_HAVE_MARCH_Z990_FEATURES
+			18, /* long displacement facility */
+#endif
+#ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES
+			7,  /* stfle */
+			16, /* extended translation facility 2 */
+			17, /* message security assist */
+			20, /* HFP-multiply-and-add */
+			21, /* extended-immediate facility */
+			22, /* extended-translation facility 3 */
+			23, /* HFP-unnormalized-extension */
+			24, /* ETF2-enhancement */
+			25, /* store clock fast */
+			30, /* ETF3-enhancement */
+#endif
+#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
+			26, /* parsing enhancement facility */
+			27, /* mvcos */
+			32, /* compare and swap and store */
+			33, /* compare and swap and store 2 */
+			34, /* general extension facility */
+			35, /* execute extensions */
+			41, /* floating point support enhancement */
+			42, /* DFP facility */
+			44, /* PFPO */
+#endif
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+			37, /* floating point extension */
+			45, /* fast-BCR, etc. */
+#endif
+#ifdef CONFIG_HAVE_MARCH_ZEC12_FEATURES
+			48, /* decimal floating point zoned */
+			49, /* misc-instruction-extensions */
+			52, /* interlocked facility 2 */
+#endif
+			-1 /* END */
+		}
+	},
+};
diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h
index b4f99d22ba04..007163f91856 100644
--- a/arch/s390/include/asm/facility.h
+++ b/arch/s390/include/asm/facility.h
@@ -7,6 +7,10 @@
 #ifndef __ASM_FACILITY_H
 #define __ASM_FACILITY_H
 
+#include <generated/facilities.h>
+
+#ifndef __ASSEMBLY__
+
 #include <linux/string.h>
 #include <linux/preempt.h>
 #include <asm/lowcore.h>
@@ -62,4 +66,5 @@ static inline void stfle(u64 *stfle_fac_list, int size)
 	preempt_enable();
 }
 
+#endif /* __ASSEMBLY__ */
 #endif /* __ASM_FACILITY_H */
diff --git a/arch/s390/tools/.gitignore b/arch/s390/tools/.gitignore
new file mode 100644
index 000000000000..72a4b2cf1365
--- /dev/null
+++ b/arch/s390/tools/.gitignore
@@ -0,0 +1 @@
+gen_facilities
diff --git a/arch/s390/tools/Makefile b/arch/s390/tools/Makefile
new file mode 100644
index 000000000000..6d9814c9df2b
--- /dev/null
+++ b/arch/s390/tools/Makefile
@@ -0,0 +1,15 @@
+#
+# Makefile for s390 specific build tools
+#
+
+hostprogs-y		    += gen_facilities
+HOSTCFLAGS_gen_facilities.o += -Wall $(LINUXINCLUDE)
+
+define filechk_facilities.h
+	$(obj)/gen_facilities
+endef
+
+$(obj)/gen_facilities.o: $(srctree)/arch/s390/tools/gen_facilities.c
+
+include/generated/facilities.h: $(obj)/gen_facilities FORCE
+	$(call filechk,facilities.h)
diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c
new file mode 100644
index 000000000000..e2660d27889b
--- /dev/null
+++ b/arch/s390/tools/gen_facilities.c
@@ -0,0 +1,67 @@
+/*
+ * Simple program to generate defines out of facility lists that use the bit
+ * numbering scheme from the Princples of Operations: most significant bit
+ * has bit number 0.
+ *
+ *    Copyright IBM Corp. 2015
+ *
+ */
+
+#define S390_GEN_FACILITIES_C
+
+#include <strings.h>
+#include <string.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <asm/facilities_src.h>
+
+static void print_facility_list(struct facility_def *def)
+{
+	unsigned int high, bit, dword, i;
+	unsigned long long *array;
+
+	array = calloc(1, 8);
+	if (!array)
+		exit(EXIT_FAILURE);
+	high = 0;
+	for (i = 0; def->bits[i] != -1; i++) {
+		bit = 63 - (def->bits[i] & 63);
+		dword = def->bits[i] / 64;
+		if (dword > high) {
+			array = realloc(array, (dword + 1) * 8);
+			if (!array)
+				exit(EXIT_FAILURE);
+			memset(array + high + 1, 0, (dword - high) * 8);
+			high = dword;
+		}
+		array[dword] |= 1ULL << bit;
+	}
+	printf("#define %s ", def->name);
+	for (i = 0; i <= high; i++)
+		printf("_AC(0x%016llx,UL)%c", array[i], i < high ? ',' : '\n');
+	printf("#define %s_DWORDS %d\n", def->name, high + 1);
+	free(array);
+}
+
+static void print_facility_lists(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < sizeof(facility_defs) / sizeof(facility_defs[0]); i++)
+		print_facility_list(&facility_defs[i]);
+}
+
+int main(int argc, char **argv)
+{
+	printf("#ifndef __ASM_S390_FACILITIES__\n");
+	printf("#define __ASM_S390_FACILITIES__\n");
+	printf("/*\n");
+	printf(" * DO NOT MODIFY.\n");
+	printf(" *\n");
+	printf(" * This file was generated by %s\n", __FILE__);
+	printf(" */\n\n");
+	printf("#include <linux/const.h>\n\n");
+	print_facility_lists();
+	printf("\n#endif\n");
+	return 0;
+}
-- 
cgit 


From 0358ecf7327f0cb206b14138353e1cbe612c5d64 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Tue, 24 Nov 2015 12:47:14 +0100
Subject: s390/facilities: make use of generated facility list

Change head.S to make use of the generated facility list.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/head.S | 35 +++++++++++------------------------
 1 file changed, 11 insertions(+), 24 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index d28a14849126..fcaefb041364 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -25,6 +25,7 @@
 #include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
+#include <asm/facility.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
 
@@ -309,18 +310,18 @@ ENTRY(startup_kdump)
 	mvc	__LC_STFLE_FAC_LIST(4),__LC_STFL_FAC_LIST
 	tm	__LC_STFLE_FAC_LIST,0x01	# stfle available ?
 	jz	0f
-	la	%r0,1
+	lghi	%r0,FACILITIES_ALS_DWORDS-1
 	.insn	s,0xb2b00000,__LC_STFLE_FAC_LIST # store facility list extended
 	# verify if all required facilities are supported by the machine
 0:	la	%r1,__LC_STFLE_FAC_LIST
 	la	%r2,3f+8-.LPG0(%r13)
-	l	%r3,0(%r2)
-1:	l	%r0,0(%r1)
-	n	%r0,4(%r2)
-	cl	%r0,4(%r2)
+	lhi	%r3,FACILITIES_ALS_DWORDS
+1:	lg	%r0,0(%r1)
+	ng	%r0,0(%r2)
+	clg	%r0,0(%r2)
 	jne	2f
-	la	%r1,4(%r1)
-	la	%r2,4(%r2)
+	la	%r1,8(%r1)
+	la	%r2,8(%r2)
 	ahi	%r3,-1
 	jnz	1b
 	j	4f
@@ -340,24 +341,10 @@ ENTRY(startup_kdump)
 3:	.long	0x000a0000,0x8badcccc
 
 # List of facilities that are required. If not all facilities are present
-# the kernel will crash. Format is number of facility words with bits set,
-# followed by the facility words.
+# the kernel will crash.
+
+	.quad FACILITIES_ALS
 
-#if defined(CONFIG_MARCH_Z13)
-	.long 2, 0xc100eff2, 0xf46cc800
-#elif defined(CONFIG_MARCH_ZEC12)
-	.long 2, 0xc100eff2, 0xf46cc800
-#elif defined(CONFIG_MARCH_Z196)
-	.long 2, 0xc100eff2, 0xf46c0000
-#elif defined(CONFIG_MARCH_Z10)
-	.long 2, 0xc100eff2, 0xf0680000
-#elif defined(CONFIG_MARCH_Z9_109)
-	.long 1, 0xc100efc2
-#elif defined(CONFIG_MARCH_Z990)
-	.long 1, 0xc0002000
-#elif defined(CONFIG_MARCH_Z900)
-	.long 1, 0xc0000000
-#endif
 4:
 	/* Continue with startup code in head64.S */
 	jg	startup_continue
-- 
cgit 


From 185edd4431f0dfd48a465e19ccc3280b08e9fa1a Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Tue, 24 Nov 2015 13:11:18 +0100
Subject: s390/facilities: remove unneeded facility bits

The facility lists contain a lot of bits which are not necessary to
run the kernel.  Therefore remove them and keep only those bits which
are required for the kernel.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/facilities_src.h | 12 ------------
 1 file changed, 12 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/facilities_src.h b/arch/s390/include/asm/facilities_src.h
index 4555fa69a29e..493e88b4941c 100644
--- a/arch/s390/include/asm/facilities_src.h
+++ b/arch/s390/include/asm/facilities_src.h
@@ -31,33 +31,21 @@ static struct facility_def facility_defs[] = {
 #endif
 #ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES
 			7,  /* stfle */
-			16, /* extended translation facility 2 */
 			17, /* message security assist */
-			20, /* HFP-multiply-and-add */
 			21, /* extended-immediate facility */
-			22, /* extended-translation facility 3 */
-			23, /* HFP-unnormalized-extension */
-			24, /* ETF2-enhancement */
 			25, /* store clock fast */
-			30, /* ETF3-enhancement */
 #endif
 #ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
-			26, /* parsing enhancement facility */
 			27, /* mvcos */
 			32, /* compare and swap and store */
 			33, /* compare and swap and store 2 */
 			34, /* general extension facility */
 			35, /* execute extensions */
-			41, /* floating point support enhancement */
-			42, /* DFP facility */
-			44, /* PFPO */
 #endif
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
-			37, /* floating point extension */
 			45, /* fast-BCR, etc. */
 #endif
 #ifdef CONFIG_HAVE_MARCH_ZEC12_FEATURES
-			48, /* decimal floating point zoned */
 			49, /* misc-instruction-extensions */
 			52, /* interlocked facility 2 */
 #endif
-- 
cgit 


From 6ab6c31a5450b73133e04c3976469d6d72f55df3 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Tue, 24 Nov 2015 13:48:27 +0100
Subject: s390/facilities: optimize test_facility()

test_facility() can be optimized for bits which must be set anyway,
due to the check in head.S. This removes a couple of superfluous
runtime checks.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/facility.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h
index 007163f91856..09b406db7529 100644
--- a/arch/s390/include/asm/facility.h
+++ b/arch/s390/include/asm/facility.h
@@ -34,6 +34,12 @@ static inline int __test_facility(unsigned long nr, void *facilities)
  */
 static inline int test_facility(unsigned long nr)
 {
+	unsigned long facilities_als[] = { FACILITIES_ALS };
+
+	if (__builtin_constant_p(nr) && nr < sizeof(facilities_als) * 8) {
+		if (__test_facility(nr, &facilities_als))
+			return 1;
+	}
 	return __test_facility(nr, &S390_lowcore.stfle_fac_list);
 }
 
-- 
cgit 


From f3d05f9de75e233d8f1090af91fc6c23ddc600e8 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 25 Nov 2015 12:54:46 +0100
Subject: s390/facilities: add z13 als bit

If configured for z13 assume the kernel makes use of the instructions
that are part of the load-and-zero-rightmost-byte facility and
load/store-on-condition facility 2.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/facilities_src.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/facilities_src.h b/arch/s390/include/asm/facilities_src.h
index 493e88b4941c..4917728e5828 100644
--- a/arch/s390/include/asm/facilities_src.h
+++ b/arch/s390/include/asm/facilities_src.h
@@ -48,6 +48,9 @@ static struct facility_def facility_defs[] = {
 #ifdef CONFIG_HAVE_MARCH_ZEC12_FEATURES
 			49, /* misc-instruction-extensions */
 			52, /* interlocked facility 2 */
+#endif
+#ifdef CONFIG_HAVE_MARCH_Z13_FEATURES
+			53, /* load-and-zero-rightmost-byte, etc. */
 #endif
 			-1 /* END */
 		}
-- 
cgit 


From 6527f6e0cb6a14c3938140f609d2fde59f4299fc Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Thu, 5 Nov 2015 14:03:32 +0100
Subject: s390: compile head.S always with -march=z900

head.S on s390 contains some sanity checks if the kernel will run on a
machine or if the machine is too old, e.g. if the kernel contains
instructions not available on the machine. If so, it will emit an error
message to the console before it stops execution.

Therefore head.S contains only instructions which are availanble with the
earliest machine generation (z900).  In order to make sure we don't
accidently add instructions which are not available on z900, always compile
with -march=z900. This makes sure compilation will fail if wrong
instructions are used.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/Makefile | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index dc167a23b920..e9a328d42610 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -34,8 +34,10 @@ CFLAGS_sysinfo.o += -w
 #
 CFLAGS_REMOVE_sclp.o = $(CC_FLAGS_FTRACE)
 ifneq ($(CC_FLAGS_MARCH),-march=z900)
-CFLAGS_REMOVE_sclp.o += $(CC_FLAGS_MARCH)
-CFLAGS_sclp.o	+= -march=z900
+CFLAGS_REMOVE_sclp.o	+= $(CC_FLAGS_MARCH)
+CFLAGS_sclp.o		+= -march=z900
+AFLAGS_REMOVE_head.o	+= $(CC_FLAGS_MARCH)
+AFLAGS_head.o		+= -march=z900
 endif
 GCOV_PROFILE_sclp.o := n
 
-- 
cgit 


From f9101e639cf7e707b9a379737ea1b66a16e82097 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Mon, 7 Dec 2015 11:03:30 +0100
Subject: s390/traps: Remove unused variable

location is assigned but never used.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/traps.c | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 1b18118bbc06..d69d648759c9 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -260,11 +260,8 @@ void vector_exception(struct pt_regs *regs)
 
 void data_exception(struct pt_regs *regs)
 {
-	__u16 __user *location;
 	int signal = 0;
 
-	location = get_trap_ip(regs);
-
 	save_fpu_regs();
 	if (current->thread.fpu.fpc & FPC_DXC_MASK)
 		signal = SIGFPE;
-- 
cgit 


From 292d8d71576c471e53eb7342ea6130f0241145e8 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Mon, 7 Dec 2015 12:50:03 +0100
Subject: s390/fault: remove unused variable

address is assigned but never used.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/mm/fault.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index ec1a30d0d11a..1b903f6ad54a 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -254,7 +254,6 @@ static noinline void do_sigsegv(struct pt_regs *regs, int si_code)
 static noinline void do_no_context(struct pt_regs *regs)
 {
 	const struct exception_table_entry *fixup;
-	unsigned long address;
 
 	/* Are we prepared to handle this kernel fault?  */
 	fixup = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN);
@@ -267,7 +266,6 @@ static noinline void do_no_context(struct pt_regs *regs)
 	 * Oops. The kernel tried to access some bad page. We'll have to
 	 * terminate things with extreme prejudice.
 	 */
-	address = regs->int_parm_long & __FAIL_ADDR_MASK;
 	if (!user_space_fault(regs))
 		printk(KERN_ALERT "Unable to handle kernel pointer dereference"
 		       " in virtual kernel address space\n");
-- 
cgit 


From 90f405e859840abe1ebf64a836a61e300c11e1c9 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Mon, 7 Dec 2015 12:52:20 +0100
Subject: s390/extmem: remove unused variable

findseg_scode is assigned, but never used.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/mm/extmem.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c
index 18fccc303db7..a1bf4ad8925d 100644
--- a/arch/s390/mm/extmem.c
+++ b/arch/s390/mm/extmem.c
@@ -94,7 +94,7 @@ static DEFINE_MUTEX(dcss_lock);
 static LIST_HEAD(dcss_list);
 static char *segtype_string[] = { "SW", "EW", "SR", "ER", "SN", "EN", "SC",
 					"EW/EN-MIXED" };
-static int loadshr_scode, loadnsr_scode, findseg_scode;
+static int loadshr_scode, loadnsr_scode;
 static int segext_scode, purgeseg_scode;
 static int scode_set;
 
@@ -130,7 +130,6 @@ dcss_set_subcodes(void)
 		loadshr_scode = DCSS_LOADSHRX;
 		loadnsr_scode = DCSS_LOADNSRX;
 		purgeseg_scode = DCSS_PURGESEG;
-		findseg_scode = DCSS_FINDSEGX;
 		segext_scode = DCSS_SEGEXTX;
 		return 0;
 	}
@@ -138,7 +137,6 @@ dcss_set_subcodes(void)
 	loadshr_scode = DCSS_LOADNOLY;
 	loadnsr_scode = DCSS_LOADNSR;
 	purgeseg_scode = DCSS_PURGESEG;
-	findseg_scode = DCSS_FINDSEG;
 	segext_scode = DCSS_SEGEXT;
 	return 0;
 }
-- 
cgit 


From e527aec434b59745654d3b34a3aa7ce3392a85a5 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Mon, 7 Dec 2015 13:08:48 +0100
Subject: s390/sysinfo: Remove unused variables

max_mnest and rc are never used.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/sysinfo.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index 99babea026ca..efacda2fc568 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -111,8 +111,7 @@ static void stsi_1_1_1(struct seq_file *m, struct sysinfo_1_1_1 *info)
 
 static void stsi_15_1_x(struct seq_file *m, struct sysinfo_15_1_x *info)
 {
-	static int max_mnest;
-	int i, rc;
+	int i;
 
 	seq_putc(m, '\n');
 	if (!MACHINE_HAS_TOPOLOGY)
-- 
cgit 


From 3dbc78d3a179d99611111d2d86d4283f1f4f82b4 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Tue, 8 Dec 2015 14:10:12 +0100
Subject: s390/smp: save timestamp on external calls

This is supposed to make debugging easier: if within a dump we can see
that an external call or emergency signal IPI is pending but all cpus
are idle, we have no idea for how long the interrupt is outstanding.

Therefore save a timestamp into the per cpu pcpu array of the target
cpu whenever such an IPI is sent.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/smp.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/s390')

diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 9da95d8dfc62..654c36ec0c60 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -66,6 +66,7 @@ static DEFINE_PER_CPU(struct cpu *, cpu_device);
 struct pcpu {
 	struct _lowcore *lowcore;	/* lowcore page(s) for the cpu */
 	unsigned long ec_mask;		/* bit mask for ec_xxx functions */
+	unsigned long ec_clk;		/* sigp timestamp for ec_xxx */
 	signed char state;		/* physical cpu state */
 	signed char polarization;	/* physical polarization */
 	u16 address;			/* physical cpu address */
@@ -174,6 +175,7 @@ static void pcpu_ec_call(struct pcpu *pcpu, int ec_bit)
 	if (test_and_set_bit(ec_bit, &pcpu->ec_mask))
 		return;
 	order = pcpu_running(pcpu) ? SIGP_EXTERNAL_CALL : SIGP_EMERGENCY_SIGNAL;
+	pcpu->ec_clk = get_tod_clock_fast();
 	pcpu_sigp_retry(pcpu, order, 0);
 }
 
-- 
cgit 


From d7ae65aec0dac187d29a2963ac46574aad840a20 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Tue, 15 Dec 2015 09:26:30 +0100
Subject: s390/setup: cleanup machine flags

Over time some machine flags got unused (e.g. MACHINE_FLAG_MVPG)
or are available on all 64bit systems (MACHINE_FLAG_CSP,
MACHINE_FLAG_IEEE) - let's remove them.
Reorder the other ones to match the order of the MACHINE_HAS_*
macros and renumber all bits to avoid holes.
Also fix the comment about where the flags are detected.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/setup.h | 31 ++++++++++++++-----------------
 1 file changed, 14 insertions(+), 17 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 23537661da0e..69837225119e 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -12,27 +12,24 @@
 #define PARMAREA		0x10400
 
 /*
- * Machine features detected in head.S
+ * Machine features detected in early.c
  */
 
 #define MACHINE_FLAG_VM		_BITUL(0)
-#define MACHINE_FLAG_IEEE	_BITUL(1)
-#define MACHINE_FLAG_CSP	_BITUL(2)
-#define MACHINE_FLAG_MVPG	_BITUL(3)
-#define MACHINE_FLAG_DIAG44	_BITUL(4)
+#define MACHINE_FLAG_KVM	_BITUL(1)
+#define MACHINE_FLAG_LPAR	_BITUL(2)
+#define MACHINE_FLAG_DIAG9C	_BITUL(3)
+#define MACHINE_FLAG_ESOP	_BITUL(4)
 #define MACHINE_FLAG_IDTE	_BITUL(5)
-#define MACHINE_FLAG_DIAG9C	_BITUL(6)
-#define MACHINE_FLAG_KVM	_BITUL(8)
-#define MACHINE_FLAG_ESOP	_BITUL(9)
-#define MACHINE_FLAG_EDAT1	_BITUL(10)
-#define MACHINE_FLAG_EDAT2	_BITUL(11)
-#define MACHINE_FLAG_LPAR	_BITUL(12)
-#define MACHINE_FLAG_LPP	_BITUL(13)
-#define MACHINE_FLAG_TOPOLOGY	_BITUL(14)
-#define MACHINE_FLAG_TE		_BITUL(15)
-#define MACHINE_FLAG_TLB_LC	_BITUL(17)
-#define MACHINE_FLAG_VX		_BITUL(18)
-#define MACHINE_FLAG_CAD	_BITUL(19)
+#define MACHINE_FLAG_DIAG44	_BITUL(6)
+#define MACHINE_FLAG_EDAT1	_BITUL(7)
+#define MACHINE_FLAG_EDAT2	_BITUL(8)
+#define MACHINE_FLAG_LPP	_BITUL(9)
+#define MACHINE_FLAG_TOPOLOGY	_BITUL(10)
+#define MACHINE_FLAG_TE		_BITUL(11)
+#define MACHINE_FLAG_TLB_LC	_BITUL(12)
+#define MACHINE_FLAG_VX		_BITUL(13)
+#define MACHINE_FLAG_CAD	_BITUL(14)
 
 #define LPP_MAGIC		_BITUL(31)
 #define LPP_PFAULT_PID_MASK	_AC(0xffffffff, UL)
-- 
cgit 


From 2ab59de7c5ce7c5ed6db07278554901d43fe80a0 Mon Sep 17 00:00:00 2001
From: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Date: Fri, 18 Dec 2015 12:59:32 +0100
Subject: s390/cio: Consolidate inline assemblies and related data definitions

Replace the current semi-arbitrary distribution of inline assemblies:
 - Inline assemblies used by CIO go into ioasm.h
 - Data definitions used by inline assemblies go into cio.h

Beyond cleaning up the current structure this is also required for
use of tracepoints in inline assemblies introduced by a follow-on
patch.

Signed-off-by: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Acked-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/crw.h | 14 --------------
 1 file changed, 14 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/crw.h b/arch/s390/include/asm/crw.h
index 7c31d3e25cd1..bcb9cd2a730a 100644
--- a/arch/s390/include/asm/crw.h
+++ b/arch/s390/include/asm/crw.h
@@ -52,18 +52,4 @@ void crw_wait_for_channel_report(void);
 #define CRW_ERC_PERRI	 0x07 /* perm. error, facility init */
 #define CRW_ERC_PMOD	 0x08 /* installed parameters modified */
 
-static inline int stcrw(struct crw *pcrw)
-{
-	int ccode;
-
-	asm volatile(
-		"	stcrw	0(%2)\n"
-		"	ipm	%0\n"
-		"	srl	%0,28\n"
-		: "=d" (ccode), "=m" (*pcrw)
-		: "a" (pcrw)
-		: "cc" );
-	return ccode;
-}
-
 #endif /* _ASM_S390_CRW_H */
-- 
cgit 


From 8b614aebecdf2b1f72d51b1527f5a75d218b78e2 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 17 Dec 2015 23:51:54 +0100
Subject: bpf: move clearing of A/X into classic to eBPF migration prologue

Back in the days where eBPF (or back then "internal BPF" ;->) was not
exposed to user space, and only the classic BPF programs internally
translated into eBPF programs, we missed the fact that for classic BPF
A and X needed to be cleared. It was fixed back then via 83d5b7ef99c9
("net: filter: initialize A and X registers"), and thus classic BPF
specifics were added to the eBPF interpreter core to work around it.

This added some confusion for JIT developers later on that take the
eBPF interpreter code as an example for deriving their JIT. F.e. in
f75298f5c3fe ("s390/bpf: clear correct BPF accumulator register"), at
least X could leak stack memory. Furthermore, since this is only needed
for classic BPF translations and not for eBPF (verifier takes care
that read access to regs cannot be done uninitialized), more complexity
is added to JITs as they need to determine whether they deal with
migrations or native eBPF where they can just omit clearing A/X in
their prologue and thus reduce image size a bit, see f.e. cde66c2d88da
("s390/bpf: Only clear A and X for converted BPF programs"). In other
cases (x86, arm64), A and X is being cleared in the prologue also for
eBPF case, which is unnecessary.

Lets move this into the BPF migration in bpf_convert_filter() where it
actually belongs as long as the number of eBPF JITs are still few. It
can thus be done generically; allowing us to remove the quirk from
__bpf_prog_run() and to slightly reduce JIT image size in case of eBPF,
while reducing code duplication on this matter in current(/future) eBPF
JITs.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Tested-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Cc: Zi Shen Lim <zlim.lnx@gmail.com>
Cc: Yang Shi <yang.shi@linaro.org>
Acked-by: Yang Shi <yang.shi@linaro.org>
Acked-by: Zi Shen Lim <zlim.lnx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/s390/net/bpf_jit_comp.c | 13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 9a0c4c22e536..3c0bfc1f2694 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -408,7 +408,7 @@ static void emit_load_skb_data_hlen(struct bpf_jit *jit)
  * Save registers and create stack frame if necessary.
  * See stack frame layout desription in "bpf_jit.h"!
  */
-static void bpf_jit_prologue(struct bpf_jit *jit, bool is_classic)
+static void bpf_jit_prologue(struct bpf_jit *jit)
 {
 	if (jit->seen & SEEN_TAIL_CALL) {
 		/* xc STK_OFF_TCCNT(4,%r15),STK_OFF_TCCNT(%r15) */
@@ -448,15 +448,6 @@ static void bpf_jit_prologue(struct bpf_jit *jit, bool is_classic)
 		/* stg %b1,ST_OFF_SKBP(%r0,%r15) */
 		EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15,
 			      STK_OFF_SKBP);
-	/* Clear A (%b0) and X (%b7) registers for converted BPF programs */
-	if (is_classic) {
-		if (REG_SEEN(BPF_REG_A))
-			/* lghi %ba,0 */
-			EMIT4_IMM(0xa7090000, BPF_REG_A, 0);
-		if (REG_SEEN(BPF_REG_X))
-			/* lghi %bx,0 */
-			EMIT4_IMM(0xa7090000, BPF_REG_X, 0);
-	}
 }
 
 /*
@@ -1245,7 +1236,7 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp)
 	jit->lit = jit->lit_start;
 	jit->prg = 0;
 
-	bpf_jit_prologue(jit, bpf_prog_was_classic(fp));
+	bpf_jit_prologue(jit);
 	for (i = 0; i < fp->len; i += insn_count) {
 		insn_count = bpf_jit_insn(jit, fp, i);
 		if (insn_count < 0)
-- 
cgit 


From c095a94932ceee19fe36942aa49df7276f9e30b5 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Mon, 28 Dec 2015 12:53:51 +0100
Subject: s390/Kconfig: remove pointless 64 bit dependencies

s390 is always 64 bit.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Kconfig | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 3a55f493c7da..d66a7c47faf3 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -166,8 +166,7 @@ config SCHED_OMIT_FRAME_POINTER
 
 config PGTABLE_LEVELS
 	int
-	default 4 if 64BIT
-	default 2
+	default 4
 
 source "init/Kconfig"
 
@@ -403,7 +402,7 @@ config NODES_SPAN_OTHER_NODES
 
 config NUMA
 	bool "NUMA support"
-	depends on SMP && 64BIT && SCHED_TOPOLOGY
+	depends on SMP && SCHED_TOPOLOGY
 	default n
 	help
 	  Enable NUMA support
-- 
cgit 


From 9236b4dd6bfabefcf2063544083a66cd5f3a738d Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Mon, 28 Dec 2015 13:20:43 +0100
Subject: s390: get rid of CONFIG_SCHED_MC and CONFIG_SCHED_BOOK

Use CONFIG_TOPOLOGY which selects CONFIG_SCHED_* all over the place to
reduce the random usage of the previous config options.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Kconfig                | 6 +++---
 arch/s390/include/asm/topology.h | 6 +++---
 arch/s390/kernel/Makefile        | 2 +-
 arch/s390/kernel/sysinfo.c       | 2 +-
 4 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index d66a7c47faf3..6d0ae7d30724 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -389,9 +389,6 @@ config HOTPLUG_CPU
 	  can be controlled through /sys/devices/system/cpu/cpu#.
 	  Say N if you want to disable CPU hotplug.
 
-config SCHED_SMT
-	def_bool n
-
 # Some NUMA nodes have memory ranges that span
 # other nodes.	Even though a pfn is valid and
 # between a node's start and end pfns, it may not
@@ -462,6 +459,9 @@ config EMU_SIZE
 
 endmenu
 
+config SCHED_SMT
+	def_bool n
+
 config SCHED_MC
 	def_bool n
 
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 94fc55fc72ce..6b53962e807e 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -7,7 +7,7 @@
 struct sysinfo_15_1_x;
 struct cpu;
 
-#ifdef CONFIG_SCHED_BOOK
+#ifdef CONFIG_SCHED_TOPOLOGY
 
 struct cpu_topology_s390 {
 	unsigned short thread_id;
@@ -40,13 +40,13 @@ void store_topology(struct sysinfo_15_1_x *info);
 void topology_expect_change(void);
 const struct cpumask *cpu_coregroup_mask(int cpu);
 
-#else /* CONFIG_SCHED_BOOK */
+#else /* CONFIG_SCHED_TOPOLOGY */
 
 static inline void topology_schedule_update(void) { }
 static inline int topology_cpu_init(struct cpu *cpu) { return 0; }
 static inline void topology_expect_change(void) { }
 
-#endif /* CONFIG_SCHED_BOOK */
+#endif /* CONFIG_SCHED_TOPOLOGY */
 
 #define POLARIZATION_UNKNOWN	(-1)
 #define POLARIZATION_HRZ	(0)
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index e9a328d42610..2f5586ab8a6a 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -52,7 +52,7 @@ extra-y				+= head.o head64.o vmlinux.lds
 
 obj-$(CONFIG_MODULES)		+= s390_ksyms.o module.o
 obj-$(CONFIG_SMP)		+= smp.o
-obj-$(CONFIG_SCHED_BOOK)	+= topology.o
+obj-$(CONFIG_SCHED_TOPOLOGY)	+= topology.o
 obj-$(CONFIG_HIBERNATION)	+= suspend.o swsusp.o
 obj-$(CONFIG_AUDIT)		+= audit.o
 compat-obj-$(CONFIG_AUDIT)	+= compat_audit.o
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index efacda2fc568..0512f944eaf3 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -122,7 +122,7 @@ static void stsi_15_1_x(struct seq_file *m, struct sysinfo_15_1_x *info)
 	for (i = 0; i < TOPOLOGY_NR_MAG; i++)
 		seq_printf(m, " %d", info->mag[i]);
 	seq_putc(m, '\n');
-#ifdef CONFIG_SCHED_MC
+#ifdef CONFIG_SCHED_TOPOLOGY
 	store_topology(info);
 	seq_printf(m, "CPU Topology SW:     ");
 	for (i = 0; i < TOPOLOGY_NR_MAG; i++)
-- 
cgit 


From 538950a1b7527a0a52ccd9337e3fcd304f027f13 Mon Sep 17 00:00:00 2001
From: Craig Gallek <kraig@google.com>
Date: Mon, 4 Jan 2016 17:41:47 -0500
Subject: soreuseport: setsockopt SO_ATTACH_REUSEPORT_[CE]BPF

Expose socket options for setting a classic or extended BPF program
for use when selecting sockets in an SO_REUSEPORT group.  These options
can be used on the first socket to belong to a group before bind or
on any socket in the group after bind.

This change includes refactoring of the existing sk_filter code to
allow reuse of the existing BPF filter validation checks.

Signed-off-by: Craig Gallek <kraig@google.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/s390/include/uapi/asm/socket.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/s390')

diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index 296942d56e6a..d02e89d14fef 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -91,4 +91,7 @@
 #define SO_ATTACH_BPF		50
 #define SO_DETACH_BPF		SO_DETACH_FILTER
 
+#define SO_ATTACH_REUSEPORT_CBPF	51
+#define SO_ATTACH_REUSEPORT_EBPF	52
+
 #endif /* _ASM_SOCKET_H */
-- 
cgit 


From c57ee5faf4503b0cd586c3af663262a3d5599fc1 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Tue, 5 Jan 2016 18:20:24 +0200
Subject: kvm/s390: drop unpaired smp_mb

smp_mb on vcpu destroy isn't paired with anything, violating pairing
rules, and seems to be useless.

Drop it.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Message-Id: <1452010811-25486-1-git-send-email-mst@redhat.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/kvm/kvm-s390.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 940e9ff231a3..9f8eea3e2987 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1221,7 +1221,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kvm_clear_async_pf_completion_queue(vcpu);
 	if (!kvm_is_ucontrol(vcpu->kvm))
 		sca_del_vcpu(vcpu);
-	smp_mb();
 
 	if (kvm_is_ucontrol(vcpu->kvm))
 		gmap_free(vcpu->arch.gmap);
-- 
cgit 


From c6e5f166373a20a433c38a34bd16f2b62bd0864c Mon Sep 17 00:00:00 2001
From: Fan Zhang <zhangfan@linux.vnet.ibm.com>
Date: Thu, 7 Jan 2016 18:24:29 +0800
Subject: KVM: s390: implement the RI support of guest

This patch adds runtime instrumentation support for KVM guest. We need to
setup a save area for the runtime instrumentation-controls control block(RICCB)
and implement the necessary interfaces to live migrate the guest settings.

We setup the sie control block in a way, that the runtime
instrumentation instructions of a guest are handled by hardware.

We also add a capability KVM_CAP_S390_RI to make this feature opt-in as
it needs migration support.

Signed-off-by: Fan Zhang <zhangfan@linux.vnet.ibm.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/include/asm/kvm_host.h |  3 ++-
 arch/s390/include/uapi/asm/kvm.h |  3 +++
 arch/s390/kvm/kvm-s390.c         | 22 ++++++++++++++++++++++
 3 files changed, 27 insertions(+), 1 deletion(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index c83144110ea9..df0acff5d699 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -217,7 +217,8 @@ struct kvm_s390_sie_block {
 	__u64	pp;			/* 0x01de */
 	__u8	reserved1e6[2];		/* 0x01e6 */
 	__u64	itdba;			/* 0x01e8 */
-	__u8	reserved1f0[16];	/* 0x01f0 */
+	__u64   riccbd;			/* 0x01f0 */
+	__u8    reserved1f8[8];		/* 0x01f8 */
 } __attribute__((packed));
 
 struct kvm_s390_itdb {
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index d2aea31252f2..fe84bd5fe7ce 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -153,6 +153,7 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_ARCH0  (1UL << 4)
 #define KVM_SYNC_PFAULT (1UL << 5)
 #define KVM_SYNC_VRS    (1UL << 6)
+#define KVM_SYNC_RICCB  (1UL << 7)
 /* definition of registers in kvm_run */
 struct kvm_sync_regs {
 	__u64 prefix;	/* prefix register */
@@ -170,6 +171,8 @@ struct kvm_sync_regs {
 	__u64 vrs[32][2];	/* vector registers */
 	__u8  reserved[512];	/* for future vector expansion */
 	__u32 fpc;	/* only valid with vector registers */
+	__u8 padding[52];	/* riccb needs to be 64byte aligned */
+	__u8 riccb[64];		/* runtime instrumentation controls block */
 };
 
 #define KVM_REG_S390_TODPR	(KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 9f8eea3e2987..5927c61d322a 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -258,6 +258,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_VECTOR_REGISTERS:
 		r = MACHINE_HAS_VX;
 		break;
+	case KVM_CAP_S390_RI:
+		r = test_facility(64);
+		break;
 	default:
 		r = 0;
 	}
@@ -358,6 +361,20 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_VECTOR_REGISTERS %s",
 			 r ? "(not available)" : "(success)");
 		break;
+	case KVM_CAP_S390_RI:
+		r = -EINVAL;
+		mutex_lock(&kvm->lock);
+		if (atomic_read(&kvm->online_vcpus)) {
+			r = -EBUSY;
+		} else if (test_facility(64)) {
+			set_kvm_facility(kvm->arch.model.fac->mask, 64);
+			set_kvm_facility(kvm->arch.model.fac->list, 64);
+			r = 0;
+		}
+		mutex_unlock(&kvm->lock);
+		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_RI %s",
+			 r ? "(not available)" : "(success)");
+		break;
 	case KVM_CAP_S390_USER_STSI:
 		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI");
 		kvm->arch.user_stsi = 1;
@@ -1395,6 +1412,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 				    KVM_SYNC_CRS |
 				    KVM_SYNC_ARCH0 |
 				    KVM_SYNC_PFAULT;
+	if (test_kvm_facility(vcpu->kvm, 64))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
 	if (test_kvm_facility(vcpu->kvm, 129))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
 
@@ -1578,10 +1597,13 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 		vcpu->arch.sie_block->eca |= 1;
 	if (sclp.has_sigpif)
 		vcpu->arch.sie_block->eca |= 0x10000000U;
+	if (test_kvm_facility(vcpu->kvm, 64))
+		vcpu->arch.sie_block->ecb3 |= 0x01;
 	if (test_kvm_facility(vcpu->kvm, 129)) {
 		vcpu->arch.sie_block->eca |= 0x00020000;
 		vcpu->arch.sie_block->ecd |= 0x20000000;
 	}
+	vcpu->arch.sie_block->riccbd = (unsigned long) &vcpu->run->s.regs.riccb;
 	vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
 
 	if (vcpu->kvm->arch.use_cmma) {
-- 
cgit 


From 2860c4b1678646c99f5f1d77d026cd12ffd8a3a9 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 7 Jan 2016 15:05:10 +0100
Subject: KVM: move architecture-dependent requests to arch/

Since the numbers now overlap, it makes sense to enumerate
them in asm/kvm_host.h rather than linux/kvm_host.h.  Functions
that refer to architecture-specific requests are also moved
to arch/.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/s390/include/asm/kvm_host.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index df0acff5d699..6742414dbd6f 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -39,6 +39,10 @@
 #define KVM_IRQCHIP_NUM_PINS 4096
 #define KVM_HALT_POLL_NS_DEFAULT 0
 
+/* s390-specific vcpu->requests bit members */
+#define KVM_REQ_ENABLE_IBS         8
+#define KVM_REQ_DISABLE_IBS        9
+
 #define SIGP_CTRL_C		0x80
 #define SIGP_CTRL_SCN_MASK	0x3f
 
-- 
cgit 


From bdb97e91e0140230bda9a83f6dbaa29b0c2e0522 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 9 Jan 2016 02:16:04 -0500
Subject: [s390] page_to_phys() always returns a multiple of PAGE_SIZE

Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/s390/pci/pci_dma.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index d348f2c09a1e..32da0a6ecec2 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -366,8 +366,7 @@ static void *s390_dma_alloc(struct device *dev, size_t size,
 	pa = page_to_phys(page);
 	memset((void *) pa, 0, size);
 
-	map = s390_dma_map_pages(dev, page, pa % PAGE_SIZE,
-				 size, DMA_BIDIRECTIONAL, NULL);
+	map = s390_dma_map_pages(dev, page, 0, size, DMA_BIDIRECTIONAL, NULL);
 	if (dma_mapping_error(dev, map)) {
 		free_pages(pa, get_order(size));
 		return NULL;
-- 
cgit 


From 21266be9ed542f13436bd9c75316d43e1e84f6ae Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Thu, 19 Nov 2015 18:19:29 -0800
Subject: arch: consolidate CONFIG_STRICT_DEVM in lib/Kconfig.debug

Let all the archs that implement devmem_is_allowed() opt-in to a common
definition of CONFIG_STRICT_DEVM in lib/Kconfig.debug.

Cc: Kees Cook <keescook@chromium.org>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "David S. Miller" <davem@davemloft.net>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
[heiko: drop 'default y' for s390]
Acked-by: Ingo Molnar <mingo@redhat.com>
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 arch/s390/Kconfig       |  1 +
 arch/s390/Kconfig.debug | 12 ------------
 2 files changed, 1 insertion(+), 12 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 3a55f493c7da..779becb895be 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -66,6 +66,7 @@ config S390
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
+	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_SG_CHAIN
diff --git a/arch/s390/Kconfig.debug b/arch/s390/Kconfig.debug
index c56878e1245f..26c5d5beb4be 100644
--- a/arch/s390/Kconfig.debug
+++ b/arch/s390/Kconfig.debug
@@ -5,18 +5,6 @@ config TRACE_IRQFLAGS_SUPPORT
 
 source "lib/Kconfig.debug"
 
-config STRICT_DEVMEM
-	def_bool y
-	prompt "Filter access to /dev/mem"
-	---help---
-	  This option restricts access to /dev/mem.  If this option is
-	  disabled, you allow userspace access to all memory, including
-	  kernel and userspace memory. Accidental memory access is likely
-	  to be disastrous.
-	  Memory access is required for experts who want to debug the kernel.
-
-	  If you are unsure, say Y.
-
 config S390_PTDUMP
 	bool "Export kernel pagetable layout to userspace via debugfs"
 	depends on DEBUG_KERNEL
-- 
cgit 


From 7022ec496005b47257b8c0a1c1a40df92df7c79f Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 30 Dec 2015 13:42:37 +0100
Subject: s390/sysinfo: add missing SYSIB 1.2.2 multithreading fields

Add missing multithreading fields of SYSIB 1.2.2 (Basic-Machine CPUs)
to the output of /proc/sysinfo.

Also use bitfields for SYSIB 2.2.2 to simplify the C code a bit.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/sysinfo.h | 17 +++++++++++++----
 arch/s390/kernel/sysinfo.c      | 15 ++++++++-------
 2 files changed, 21 insertions(+), 11 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h
index f7054a892d9e..2728114d5484 100644
--- a/arch/s390/include/asm/sysinfo.h
+++ b/arch/s390/include/asm/sysinfo.h
@@ -56,7 +56,12 @@ struct sysinfo_1_2_2 {
 	char format;
 	char reserved_0[1];
 	unsigned short acc_offset;
-	char reserved_1[20];
+	unsigned char mt_installed :1;
+	unsigned char :2;
+	unsigned char mt_stid :5;
+	unsigned char :3;
+	unsigned char mt_gtid :5;
+	char reserved_1[18];
 	unsigned int nominal_cap;
 	unsigned int secondary_cap;
 	unsigned int capability;
@@ -92,9 +97,13 @@ struct sysinfo_2_2_2 {
 	char name[8];
 	unsigned int caf;
 	char reserved_2[8];
-	unsigned char mt_installed;
-	unsigned char mt_general;
-	unsigned char mt_psmtid;
+	unsigned char mt_installed :1;
+	unsigned char :2;
+	unsigned char mt_stid :5;
+	unsigned char :3;
+	unsigned char mt_gtid :5;
+	unsigned char :3;
+	unsigned char mt_psmtid :5;
 	char reserved_3[5];
 	unsigned short cpus_dedicated;
 	unsigned short cpus_shared;
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index 0512f944eaf3..f7dba3887a54 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -144,6 +144,10 @@ static void stsi_1_2_2(struct seq_file *m, struct sysinfo_1_2_2 *info)
 	seq_printf(m, "CPUs Configured:      %d\n", info->cpus_configured);
 	seq_printf(m, "CPUs Standby:         %d\n", info->cpus_standby);
 	seq_printf(m, "CPUs Reserved:        %d\n", info->cpus_reserved);
+	if (info->mt_installed) {
+		seq_printf(m, "CPUs G-MTID:          %d\n", info->mt_gtid);
+		seq_printf(m, "CPUs S-MTID:          %d\n", info->mt_stid);
+	}
 	/*
 	 * Sigh 2. According to the specification the alternate
 	 * capability field is a 32 bit floating point number
@@ -193,13 +197,10 @@ static void stsi_2_2_2(struct seq_file *m, struct sysinfo_2_2_2 *info)
 	seq_printf(m, "LPAR CPUs Reserved:   %d\n", info->cpus_reserved);
 	seq_printf(m, "LPAR CPUs Dedicated:  %d\n", info->cpus_dedicated);
 	seq_printf(m, "LPAR CPUs Shared:     %d\n", info->cpus_shared);
-	if (info->mt_installed & 0x80) {
-		seq_printf(m, "LPAR CPUs G-MTID:     %d\n",
-			   info->mt_general & 0x1f);
-		seq_printf(m, "LPAR CPUs S-MTID:     %d\n",
-			   info->mt_installed & 0x1f);
-		seq_printf(m, "LPAR CPUs PS-MTID:    %d\n",
-			   info->mt_psmtid & 0x1f);
+	if (info->mt_installed) {
+		seq_printf(m, "LPAR CPUs G-MTID:     %d\n", info->mt_gtid);
+		seq_printf(m, "LPAR CPUs S-MTID:     %d\n", info->mt_stid);
+		seq_printf(m, "LPAR CPUs PS-MTID:    %d\n", info->mt_psmtid);
 	}
 }
 
-- 
cgit 


From cb951785a78c68bf802f5e3d9016b0205ddd24c2 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Thu, 31 Dec 2015 09:58:02 +0100
Subject: s390/ptrace: get rid of long longs in psw_bits

The long longs were introduced by me in order to have a working
definition of the struct psw_bits also in 31 bit mode. Since that is
gone also get rid of the long longs.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/ptrace.h | 38 +++++++++++++++++++-------------------
 1 file changed, 19 insertions(+), 19 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index 37cbc50947f2..f00cd35c8ac4 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -24,25 +24,25 @@
 			 PSW_MASK_PSTATE | PSW_ASC_PRIMARY)
 
 struct psw_bits {
-	unsigned long long	: 1;
-	unsigned long long r	: 1; /* PER-Mask */
-	unsigned long long	: 3;
-	unsigned long long t	: 1; /* DAT Mode */
-	unsigned long long i	: 1; /* Input/Output Mask */
-	unsigned long long e	: 1; /* External Mask */
-	unsigned long long key	: 4; /* PSW Key */
-	unsigned long long	: 1;
-	unsigned long long m	: 1; /* Machine-Check Mask */
-	unsigned long long w	: 1; /* Wait State */
-	unsigned long long p	: 1; /* Problem State */
-	unsigned long long as	: 2; /* Address Space Control */
-	unsigned long long cc	: 2; /* Condition Code */
-	unsigned long long pm	: 4; /* Program Mask */
-	unsigned long long ri	: 1; /* Runtime Instrumentation */
-	unsigned long long	: 6;
-	unsigned long long eaba : 2; /* Addressing Mode */
-	unsigned long long	: 31;
-	unsigned long long ia	: 64;/* Instruction Address */
+	unsigned long	   :  1;
+	unsigned long r	   :  1; /* PER-Mask */
+	unsigned long	   :  3;
+	unsigned long t	   :  1; /* DAT Mode */
+	unsigned long i	   :  1; /* Input/Output Mask */
+	unsigned long e	   :  1; /* External Mask */
+	unsigned long key  :  4; /* PSW Key */
+	unsigned long	   :  1;
+	unsigned long m	   :  1; /* Machine-Check Mask */
+	unsigned long w	   :  1; /* Wait State */
+	unsigned long p	   :  1; /* Problem State */
+	unsigned long as   :  2; /* Address Space Control */
+	unsigned long cc   :  2; /* Condition Code */
+	unsigned long pm   :  4; /* Program Mask */
+	unsigned long ri   :  1; /* Runtime Instrumentation */
+	unsigned long	   :  6;
+	unsigned long eaba :  2; /* Addressing Mode */
+	unsigned long	   : 31;
+	unsigned long ia   : 64; /* Instruction Address */
 };
 
 enum {
-- 
cgit 


From 423d5b364c108c00d98e3da9f72d598e8f2ef948 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Thu, 31 Dec 2015 10:07:21 +0100
Subject: s390/mem_detect: use unsigned longs

The memory detection code historically had to use unsigned long long
since the machine reported the true memory size (>4GB) even if the
virtual machine was running in ESA/390 mode.

Since the old code is gone use unsigned long everywhere and also get
rid of an unused ADDR2G define.

(this patch converts all long longs within sclp_info to longs)

There are many more possible conversions, however that can be done if
somebody touches the corresponding code.  Since people started to
convert unrelated long types to long longs because of the types within
struct sclp_info convert this now.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/sclp.h | 8 ++++----
 arch/s390/mm/mem_detect.c    | 7 ++-----
 2 files changed, 6 insertions(+), 9 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index cb691602f295..5e3da0414b47 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -57,12 +57,12 @@ struct sclp_info {
 	unsigned int mtid;
 	unsigned int mtid_cp;
 	unsigned int mtid_prev;
-	unsigned long long rzm;
-	unsigned long long rnmax;
-	unsigned long long hamax;
+	unsigned long rzm;
+	unsigned long rnmax;
+	unsigned long hamax;
 	unsigned int max_cores;
 	unsigned long hsa_size;
-	unsigned long long facilities;
+	unsigned long facilities;
 };
 extern struct sclp_info sclp;
 
diff --git a/arch/s390/mm/mem_detect.c b/arch/s390/mm/mem_detect.c
index e00f0d5d296d..d612cc3eec6a 100644
--- a/arch/s390/mm/mem_detect.c
+++ b/arch/s390/mm/mem_detect.c
@@ -14,8 +14,6 @@
 #include <asm/sclp.h>
 #include <asm/setup.h>
 
-#define ADDR2G (1ULL << 31)
-
 #define CHUNK_READ_WRITE 0
 #define CHUNK_READ_ONLY  1
 
@@ -27,15 +25,14 @@ static inline void memblock_physmem_add(phys_addr_t start, phys_addr_t size)
 
 void __init detect_memory_memblock(void)
 {
-	unsigned long long memsize, rnmax, rzm;
-	unsigned long addr, size;
+	unsigned long memsize, rnmax, rzm, addr, size;
 	int type;
 
 	rzm = sclp.rzm;
 	rnmax = sclp.rnmax;
 	memsize = rzm * rnmax;
 	if (!rzm)
-		rzm = 1ULL << 17;
+		rzm = 1UL << 17;
 	max_physmem_end = memsize;
 	addr = 0;
 	/* keep memblock lists close to the kernel */
-- 
cgit 


From c667aeacc16e0de9e205faa93f57121d6f691973 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Thu, 31 Dec 2015 10:29:00 +0100
Subject: s390: rename struct _lowcore to struct lowcore

Finally get rid of the leading underscore. I tried this already two or
three years ago, however Michael Holzheu objected since this would
break the crash utility (again).

However Michael integrated support for the new name into the crash
utility back then, so it doesn't break if the name will be changed
now.  So finally get rid of the ever confusing leading underscore.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/lowcore.h   |   6 +-
 arch/s390/include/asm/processor.h |   2 +-
 arch/s390/include/asm/vdso.h      |   4 +-
 arch/s390/kernel/asm-offsets.c    | 174 +++++++++++++++++++-------------------
 arch/s390/kernel/crash_dump.c     |   4 +-
 arch/s390/kernel/ipl.c            |   4 +-
 arch/s390/kernel/setup.c          |   6 +-
 arch/s390/kernel/smp.c            |  16 ++--
 arch/s390/kernel/vdso.c           |   6 +-
 arch/s390/kvm/interrupt.c         |   4 +-
 arch/s390/kvm/priv.c              |   2 +-
 arch/s390/mm/maccess.c            |   4 +-
 12 files changed, 116 insertions(+), 116 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 5dbbf199ba2e..d79ba7cf75b0 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -16,7 +16,7 @@
 #define LC_ORDER 1
 #define LC_PAGES 2
 
-struct _lowcore {
+struct lowcore {
 	__u8	pad_0x0000[0x0014-0x0000];	/* 0x0000 */
 	__u32	ipl_parmblock_ptr;		/* 0x0014 */
 	__u8	pad_0x0018[0x0080-0x0018];	/* 0x0018 */
@@ -183,9 +183,9 @@ struct _lowcore {
 	__u8	vector_save_area[1024];		/* 0x1c00 */
 } __packed;
 
-#define S390_lowcore (*((struct _lowcore *) 0))
+#define S390_lowcore (*((struct lowcore *) 0))
 
-extern struct _lowcore *lowcore_ptr[];
+extern struct lowcore *lowcore_ptr[];
 
 static inline void set_prefix(__u32 address)
 {
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 5592c94ebe31..f16debf6a612 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -60,7 +60,7 @@ static inline int test_cpu_flag(int flag)
  */
 static inline int test_cpu_flag_of(int flag, int cpu)
 {
-	struct _lowcore *lc = lowcore_ptr[cpu];
+	struct lowcore *lc = lowcore_ptr[cpu];
 	return !!(lc->cpu_flags & (1UL << flag));
 }
 
diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h
index 787acd4f9668..f9b02d300d60 100644
--- a/arch/s390/include/asm/vdso.h
+++ b/arch/s390/include/asm/vdso.h
@@ -42,8 +42,8 @@ struct vdso_per_cpu_data {
 
 extern struct vdso_data *vdso_data;
 
-int vdso_alloc_per_cpu(struct _lowcore *lowcore);
-void vdso_free_per_cpu(struct _lowcore *lowcore);
+int vdso_alloc_per_cpu(struct lowcore *lowcore);
+void vdso_free_per_cpu(struct lowcore *lowcore);
 
 #endif /* __ASSEMBLY__ */
 #endif /* __S390_VDSO_H__ */
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index d8d18f8d8b77..d5916ef9c619 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -97,96 +97,96 @@ int main(void)
 	OFFSET(__TIMER_IDLE_EXIT, s390_idle_data, timer_idle_exit);
 	BLANK();
 	/* hardware defined lowcore locations 0x000 - 0x1ff */
-	OFFSET(__LC_EXT_PARAMS, _lowcore, ext_params);
-	OFFSET(__LC_EXT_CPU_ADDR, _lowcore, ext_cpu_addr);
-	OFFSET(__LC_EXT_INT_CODE, _lowcore, ext_int_code);
-	OFFSET(__LC_SVC_ILC, _lowcore, svc_ilc);
-	OFFSET(__LC_SVC_INT_CODE, _lowcore, svc_code);
-	OFFSET(__LC_PGM_ILC, _lowcore, pgm_ilc);
-	OFFSET(__LC_PGM_INT_CODE, _lowcore, pgm_code);
-	OFFSET(__LC_DATA_EXC_CODE, _lowcore, data_exc_code);
-	OFFSET(__LC_MON_CLASS_NR, _lowcore, mon_class_num);
-	OFFSET(__LC_PER_CODE, _lowcore, per_code);
-	OFFSET(__LC_PER_ATMID, _lowcore, per_atmid);
-	OFFSET(__LC_PER_ADDRESS, _lowcore, per_address);
-	OFFSET(__LC_EXC_ACCESS_ID, _lowcore, exc_access_id);
-	OFFSET(__LC_PER_ACCESS_ID, _lowcore, per_access_id);
-	OFFSET(__LC_OP_ACCESS_ID, _lowcore, op_access_id);
-	OFFSET(__LC_AR_MODE_ID, _lowcore, ar_mode_id);
-	OFFSET(__LC_TRANS_EXC_CODE, _lowcore, trans_exc_code);
-	OFFSET(__LC_MON_CODE, _lowcore, monitor_code);
-	OFFSET(__LC_SUBCHANNEL_ID, _lowcore, subchannel_id);
-	OFFSET(__LC_SUBCHANNEL_NR, _lowcore, subchannel_nr);
-	OFFSET(__LC_IO_INT_PARM, _lowcore, io_int_parm);
-	OFFSET(__LC_IO_INT_WORD, _lowcore, io_int_word);
-	OFFSET(__LC_STFL_FAC_LIST, _lowcore, stfl_fac_list);
-	OFFSET(__LC_STFLE_FAC_LIST, _lowcore, stfle_fac_list);
-	OFFSET(__LC_MCCK_CODE, _lowcore, mcck_interruption_code);
-	OFFSET(__LC_MCCK_FAIL_STOR_ADDR, _lowcore, failing_storage_address);
-	OFFSET(__LC_LAST_BREAK, _lowcore, breaking_event_addr);
-	OFFSET(__LC_RST_OLD_PSW, _lowcore, restart_old_psw);
-	OFFSET(__LC_EXT_OLD_PSW, _lowcore, external_old_psw);
-	OFFSET(__LC_SVC_OLD_PSW, _lowcore, svc_old_psw);
-	OFFSET(__LC_PGM_OLD_PSW, _lowcore, program_old_psw);
-	OFFSET(__LC_MCK_OLD_PSW, _lowcore, mcck_old_psw);
-	OFFSET(__LC_IO_OLD_PSW, _lowcore, io_old_psw);
-	OFFSET(__LC_RST_NEW_PSW, _lowcore, restart_psw);
-	OFFSET(__LC_EXT_NEW_PSW, _lowcore, external_new_psw);
-	OFFSET(__LC_SVC_NEW_PSW, _lowcore, svc_new_psw);
-	OFFSET(__LC_PGM_NEW_PSW, _lowcore, program_new_psw);
-	OFFSET(__LC_MCK_NEW_PSW, _lowcore, mcck_new_psw);
-	OFFSET(__LC_IO_NEW_PSW, _lowcore, io_new_psw);
+	OFFSET(__LC_EXT_PARAMS, lowcore, ext_params);
+	OFFSET(__LC_EXT_CPU_ADDR, lowcore, ext_cpu_addr);
+	OFFSET(__LC_EXT_INT_CODE, lowcore, ext_int_code);
+	OFFSET(__LC_SVC_ILC, lowcore, svc_ilc);
+	OFFSET(__LC_SVC_INT_CODE, lowcore, svc_code);
+	OFFSET(__LC_PGM_ILC, lowcore, pgm_ilc);
+	OFFSET(__LC_PGM_INT_CODE, lowcore, pgm_code);
+	OFFSET(__LC_DATA_EXC_CODE, lowcore, data_exc_code);
+	OFFSET(__LC_MON_CLASS_NR, lowcore, mon_class_num);
+	OFFSET(__LC_PER_CODE, lowcore, per_code);
+	OFFSET(__LC_PER_ATMID, lowcore, per_atmid);
+	OFFSET(__LC_PER_ADDRESS, lowcore, per_address);
+	OFFSET(__LC_EXC_ACCESS_ID, lowcore, exc_access_id);
+	OFFSET(__LC_PER_ACCESS_ID, lowcore, per_access_id);
+	OFFSET(__LC_OP_ACCESS_ID, lowcore, op_access_id);
+	OFFSET(__LC_AR_MODE_ID, lowcore, ar_mode_id);
+	OFFSET(__LC_TRANS_EXC_CODE, lowcore, trans_exc_code);
+	OFFSET(__LC_MON_CODE, lowcore, monitor_code);
+	OFFSET(__LC_SUBCHANNEL_ID, lowcore, subchannel_id);
+	OFFSET(__LC_SUBCHANNEL_NR, lowcore, subchannel_nr);
+	OFFSET(__LC_IO_INT_PARM, lowcore, io_int_parm);
+	OFFSET(__LC_IO_INT_WORD, lowcore, io_int_word);
+	OFFSET(__LC_STFL_FAC_LIST, lowcore, stfl_fac_list);
+	OFFSET(__LC_STFLE_FAC_LIST, lowcore, stfle_fac_list);
+	OFFSET(__LC_MCCK_CODE, lowcore, mcck_interruption_code);
+	OFFSET(__LC_MCCK_FAIL_STOR_ADDR, lowcore, failing_storage_address);
+	OFFSET(__LC_LAST_BREAK, lowcore, breaking_event_addr);
+	OFFSET(__LC_RST_OLD_PSW, lowcore, restart_old_psw);
+	OFFSET(__LC_EXT_OLD_PSW, lowcore, external_old_psw);
+	OFFSET(__LC_SVC_OLD_PSW, lowcore, svc_old_psw);
+	OFFSET(__LC_PGM_OLD_PSW, lowcore, program_old_psw);
+	OFFSET(__LC_MCK_OLD_PSW, lowcore, mcck_old_psw);
+	OFFSET(__LC_IO_OLD_PSW, lowcore, io_old_psw);
+	OFFSET(__LC_RST_NEW_PSW, lowcore, restart_psw);
+	OFFSET(__LC_EXT_NEW_PSW, lowcore, external_new_psw);
+	OFFSET(__LC_SVC_NEW_PSW, lowcore, svc_new_psw);
+	OFFSET(__LC_PGM_NEW_PSW, lowcore, program_new_psw);
+	OFFSET(__LC_MCK_NEW_PSW, lowcore, mcck_new_psw);
+	OFFSET(__LC_IO_NEW_PSW, lowcore, io_new_psw);
 	/* software defined lowcore locations 0x200 - 0xdff*/
-	OFFSET(__LC_SAVE_AREA_SYNC, _lowcore, save_area_sync);
-	OFFSET(__LC_SAVE_AREA_ASYNC, _lowcore, save_area_async);
-	OFFSET(__LC_SAVE_AREA_RESTART, _lowcore, save_area_restart);
-	OFFSET(__LC_CPU_FLAGS, _lowcore, cpu_flags);
-	OFFSET(__LC_RETURN_PSW, _lowcore, return_psw);
-	OFFSET(__LC_RETURN_MCCK_PSW, _lowcore, return_mcck_psw);
-	OFFSET(__LC_SYNC_ENTER_TIMER, _lowcore, sync_enter_timer);
-	OFFSET(__LC_ASYNC_ENTER_TIMER, _lowcore, async_enter_timer);
-	OFFSET(__LC_MCCK_ENTER_TIMER, _lowcore, mcck_enter_timer);
-	OFFSET(__LC_EXIT_TIMER, _lowcore, exit_timer);
-	OFFSET(__LC_USER_TIMER, _lowcore, user_timer);
-	OFFSET(__LC_SYSTEM_TIMER, _lowcore, system_timer);
-	OFFSET(__LC_STEAL_TIMER, _lowcore, steal_timer);
-	OFFSET(__LC_LAST_UPDATE_TIMER, _lowcore, last_update_timer);
-	OFFSET(__LC_LAST_UPDATE_CLOCK, _lowcore, last_update_clock);
-	OFFSET(__LC_INT_CLOCK, _lowcore, int_clock);
-	OFFSET(__LC_MCCK_CLOCK, _lowcore, mcck_clock);
-	OFFSET(__LC_CURRENT, _lowcore, current_task);
-	OFFSET(__LC_THREAD_INFO, _lowcore, thread_info);
-	OFFSET(__LC_KERNEL_STACK, _lowcore, kernel_stack);
-	OFFSET(__LC_ASYNC_STACK, _lowcore, async_stack);
-	OFFSET(__LC_PANIC_STACK, _lowcore, panic_stack);
-	OFFSET(__LC_RESTART_STACK, _lowcore, restart_stack);
-	OFFSET(__LC_RESTART_FN, _lowcore, restart_fn);
-	OFFSET(__LC_RESTART_DATA, _lowcore, restart_data);
-	OFFSET(__LC_RESTART_SOURCE, _lowcore, restart_source);
-	OFFSET(__LC_USER_ASCE, _lowcore, user_asce);
-	OFFSET(__LC_LPP, _lowcore, lpp);
-	OFFSET(__LC_CURRENT_PID, _lowcore, current_pid);
-	OFFSET(__LC_PERCPU_OFFSET, _lowcore, percpu_offset);
-	OFFSET(__LC_VDSO_PER_CPU, _lowcore, vdso_per_cpu_data);
-	OFFSET(__LC_MACHINE_FLAGS, _lowcore, machine_flags);
-	OFFSET(__LC_GMAP, _lowcore, gmap);
-	OFFSET(__LC_PASTE, _lowcore, paste);
+	OFFSET(__LC_SAVE_AREA_SYNC, lowcore, save_area_sync);
+	OFFSET(__LC_SAVE_AREA_ASYNC, lowcore, save_area_async);
+	OFFSET(__LC_SAVE_AREA_RESTART, lowcore, save_area_restart);
+	OFFSET(__LC_CPU_FLAGS, lowcore, cpu_flags);
+	OFFSET(__LC_RETURN_PSW, lowcore, return_psw);
+	OFFSET(__LC_RETURN_MCCK_PSW, lowcore, return_mcck_psw);
+	OFFSET(__LC_SYNC_ENTER_TIMER, lowcore, sync_enter_timer);
+	OFFSET(__LC_ASYNC_ENTER_TIMER, lowcore, async_enter_timer);
+	OFFSET(__LC_MCCK_ENTER_TIMER, lowcore, mcck_enter_timer);
+	OFFSET(__LC_EXIT_TIMER, lowcore, exit_timer);
+	OFFSET(__LC_USER_TIMER, lowcore, user_timer);
+	OFFSET(__LC_SYSTEM_TIMER, lowcore, system_timer);
+	OFFSET(__LC_STEAL_TIMER, lowcore, steal_timer);
+	OFFSET(__LC_LAST_UPDATE_TIMER, lowcore, last_update_timer);
+	OFFSET(__LC_LAST_UPDATE_CLOCK, lowcore, last_update_clock);
+	OFFSET(__LC_INT_CLOCK, lowcore, int_clock);
+	OFFSET(__LC_MCCK_CLOCK, lowcore, mcck_clock);
+	OFFSET(__LC_CURRENT, lowcore, current_task);
+	OFFSET(__LC_THREAD_INFO, lowcore, thread_info);
+	OFFSET(__LC_KERNEL_STACK, lowcore, kernel_stack);
+	OFFSET(__LC_ASYNC_STACK, lowcore, async_stack);
+	OFFSET(__LC_PANIC_STACK, lowcore, panic_stack);
+	OFFSET(__LC_RESTART_STACK, lowcore, restart_stack);
+	OFFSET(__LC_RESTART_FN, lowcore, restart_fn);
+	OFFSET(__LC_RESTART_DATA, lowcore, restart_data);
+	OFFSET(__LC_RESTART_SOURCE, lowcore, restart_source);
+	OFFSET(__LC_USER_ASCE, lowcore, user_asce);
+	OFFSET(__LC_LPP, lowcore, lpp);
+	OFFSET(__LC_CURRENT_PID, lowcore, current_pid);
+	OFFSET(__LC_PERCPU_OFFSET, lowcore, percpu_offset);
+	OFFSET(__LC_VDSO_PER_CPU, lowcore, vdso_per_cpu_data);
+	OFFSET(__LC_MACHINE_FLAGS, lowcore, machine_flags);
+	OFFSET(__LC_GMAP, lowcore, gmap);
+	OFFSET(__LC_PASTE, lowcore, paste);
 	/* software defined ABI-relevant lowcore locations 0xe00 - 0xe20 */
-	OFFSET(__LC_DUMP_REIPL, _lowcore, ipib);
+	OFFSET(__LC_DUMP_REIPL, lowcore, ipib);
 	/* hardware defined lowcore locations 0x1000 - 0x18ff */
-	OFFSET(__LC_VX_SAVE_AREA_ADDR, _lowcore, vector_save_area_addr);
-	OFFSET(__LC_EXT_PARAMS2, _lowcore, ext_params2);
-	OFFSET(__LC_FPREGS_SAVE_AREA, _lowcore, floating_pt_save_area);
-	OFFSET(__LC_GPREGS_SAVE_AREA, _lowcore, gpregs_save_area);
-	OFFSET(__LC_PSW_SAVE_AREA, _lowcore, psw_save_area);
-	OFFSET(__LC_PREFIX_SAVE_AREA, _lowcore, prefixreg_save_area);
-	OFFSET(__LC_FP_CREG_SAVE_AREA, _lowcore, fpt_creg_save_area);
-	OFFSET(__LC_TOD_PROGREG_SAVE_AREA, _lowcore, tod_progreg_save_area);
-	OFFSET(__LC_CPU_TIMER_SAVE_AREA, _lowcore, cpu_timer_save_area);
-	OFFSET(__LC_CLOCK_COMP_SAVE_AREA, _lowcore, clock_comp_save_area);
-	OFFSET(__LC_AREGS_SAVE_AREA, _lowcore, access_regs_save_area);
-	OFFSET(__LC_CREGS_SAVE_AREA, _lowcore, cregs_save_area);
-	OFFSET(__LC_PGM_TDB, _lowcore, pgm_tdb);
+	OFFSET(__LC_VX_SAVE_AREA_ADDR, lowcore, vector_save_area_addr);
+	OFFSET(__LC_EXT_PARAMS2, lowcore, ext_params2);
+	OFFSET(__LC_FPREGS_SAVE_AREA, lowcore, floating_pt_save_area);
+	OFFSET(__LC_GPREGS_SAVE_AREA, lowcore, gpregs_save_area);
+	OFFSET(__LC_PSW_SAVE_AREA, lowcore, psw_save_area);
+	OFFSET(__LC_PREFIX_SAVE_AREA, lowcore, prefixreg_save_area);
+	OFFSET(__LC_FP_CREG_SAVE_AREA, lowcore, fpt_creg_save_area);
+	OFFSET(__LC_TOD_PROGREG_SAVE_AREA, lowcore, tod_progreg_save_area);
+	OFFSET(__LC_CPU_TIMER_SAVE_AREA, lowcore, cpu_timer_save_area);
+	OFFSET(__LC_CLOCK_COMP_SAVE_AREA, lowcore, clock_comp_save_area);
+	OFFSET(__LC_AREGS_SAVE_AREA, lowcore, access_regs_save_area);
+	OFFSET(__LC_CREGS_SAVE_AREA, lowcore, cregs_save_area);
+	OFFSET(__LC_PGM_TDB, lowcore, pgm_tdb);
 	BLANK();
 	/* gmap/sie offsets */
 	OFFSET(__GMAP_ASCE, gmap, asce);
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 823ed6ab53c8..a92b39fd0e63 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -83,9 +83,9 @@ struct save_area * __init save_area_boot_cpu(void)
  */
 void __init save_area_add_regs(struct save_area *sa, void *regs)
 {
-	struct _lowcore *lc;
+	struct lowcore *lc;
 
-	lc = (struct _lowcore *)(regs - __LC_FPREGS_SAVE_AREA);
+	lc = (struct lowcore *)(regs - __LC_FPREGS_SAVE_AREA);
 	memcpy(&sa->psw, &lc->psw_save_area, sizeof(sa->psw));
 	memcpy(&sa->ctrs, &lc->cregs_save_area, sizeof(sa->ctrs));
 	memcpy(&sa->gprs, &lc->gpregs_save_area, sizeof(sa->gprs));
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 26d58cf72573..0a5a6b661b93 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2041,9 +2041,9 @@ static void do_reset_calls(void)
 
 void s390_reset_system(void)
 {
-	struct _lowcore *lc;
+	struct lowcore *lc;
 
-	lc = (struct _lowcore *)(unsigned long) store_prefix();
+	lc = (struct lowcore *)(unsigned long) store_prefix();
 
 	/* Stack for interrupt/machine check handler */
 	lc->panic_stack = S390_lowcore.panic_stack;
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 22756bb0819e..ea2454d5dcba 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -97,7 +97,7 @@ unsigned long MODULES_VADDR;
 unsigned long MODULES_END;
 
 /* An array with a pointer to the lowcore of every CPU. */
-struct _lowcore *lowcore_ptr[NR_CPUS];
+struct lowcore *lowcore_ptr[NR_CPUS];
 EXPORT_SYMBOL(lowcore_ptr);
 
 /*
@@ -291,12 +291,12 @@ void *restart_stack __attribute__((__section__(".data")));
 
 static void __init setup_lowcore(void)
 {
-	struct _lowcore *lc;
+	struct lowcore *lc;
 
 	/*
 	 * Setup lowcore for boot cpu
 	 */
-	BUILD_BUG_ON(sizeof(struct _lowcore) != LC_PAGES * 4096);
+	BUILD_BUG_ON(sizeof(struct lowcore) != LC_PAGES * 4096);
 	lc = __alloc_bootmem_low(LC_PAGES * PAGE_SIZE, LC_PAGES * PAGE_SIZE, 0);
 	lc->restart_psw.mask = PSW_KERNEL_BITS;
 	lc->restart_psw.addr =
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 654c36ec0c60..a13468b9a913 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -64,7 +64,7 @@ enum {
 static DEFINE_PER_CPU(struct cpu *, cpu_device);
 
 struct pcpu {
-	struct _lowcore *lowcore;	/* lowcore page(s) for the cpu */
+	struct lowcore *lowcore;	/* lowcore page(s) for the cpu */
 	unsigned long ec_mask;		/* bit mask for ec_xxx functions */
 	unsigned long ec_clk;		/* sigp timestamp for ec_xxx */
 	signed char state;		/* physical cpu state */
@@ -185,10 +185,10 @@ static void pcpu_ec_call(struct pcpu *pcpu, int ec_bit)
 static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
 {
 	unsigned long async_stack, panic_stack;
-	struct _lowcore *lc;
+	struct lowcore *lc;
 
 	if (pcpu != &pcpu_devices[0]) {
-		pcpu->lowcore =	(struct _lowcore *)
+		pcpu->lowcore =	(struct lowcore *)
 			__get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER);
 		async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER);
 		panic_stack = __get_free_page(GFP_KERNEL);
@@ -240,7 +240,7 @@ static void pcpu_free_lowcore(struct pcpu *pcpu)
 
 static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
 {
-	struct _lowcore *lc = pcpu->lowcore;
+	struct lowcore *lc = pcpu->lowcore;
 
 	if (MACHINE_HAS_TLB_LC)
 		cpumask_set_cpu(cpu, &init_mm.context.cpu_attach_mask);
@@ -260,7 +260,7 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
 
 static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk)
 {
-	struct _lowcore *lc = pcpu->lowcore;
+	struct lowcore *lc = pcpu->lowcore;
 	struct thread_info *ti = task_thread_info(tsk);
 
 	lc->kernel_stack = (unsigned long) task_stack_page(tsk)
@@ -276,7 +276,7 @@ static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk)
 
 static void pcpu_start_fn(struct pcpu *pcpu, void (*func)(void *), void *data)
 {
-	struct _lowcore *lc = pcpu->lowcore;
+	struct lowcore *lc = pcpu->lowcore;
 
 	lc->restart_stack = lc->kernel_stack;
 	lc->restart_fn = (unsigned long) func;
@@ -291,7 +291,7 @@ static void pcpu_start_fn(struct pcpu *pcpu, void (*func)(void *), void *data)
 static void pcpu_delegate(struct pcpu *pcpu, void (*func)(void *),
 			  void *data, unsigned long stack)
 {
-	struct _lowcore *lc = lowcore_ptr[pcpu - pcpu_devices];
+	struct lowcore *lc = lowcore_ptr[pcpu - pcpu_devices];
 	unsigned long source_cpu = stap();
 
 	__load_psw_mask(PSW_KERNEL_BITS);
@@ -923,7 +923,7 @@ void __init smp_prepare_boot_cpu(void)
 
 	pcpu->state = CPU_STATE_CONFIGURED;
 	pcpu->address = stap();
-	pcpu->lowcore = (struct _lowcore *)(unsigned long) store_prefix();
+	pcpu->lowcore = (struct lowcore *)(unsigned long) store_prefix();
 	S390_lowcore.percpu_offset = __per_cpu_offset[0];
 	smp_cpu_set_polarization(0, POLARIZATION_UNKNOWN);
 	set_cpu_present(0, true);
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 59eddb0e1a3e..4f07eaced960 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -90,7 +90,7 @@ static void vdso_init_data(struct vdso_data *vd)
  */
 #define SEGMENT_ORDER	2
 
-int vdso_alloc_per_cpu(struct _lowcore *lowcore)
+int vdso_alloc_per_cpu(struct lowcore *lowcore)
 {
 	unsigned long segment_table, page_table, page_frame;
 	u32 *psal, *aste;
@@ -138,7 +138,7 @@ out:
 	return -ENOMEM;
 }
 
-void vdso_free_per_cpu(struct _lowcore *lowcore)
+void vdso_free_per_cpu(struct lowcore *lowcore)
 {
 	unsigned long segment_table, page_table, page_frame;
 	u32 *psal, *aste;
@@ -163,7 +163,7 @@ static void vdso_init_cr5(void)
 
 	if (!vdso_enabled)
 		return;
-	cr5 = offsetof(struct _lowcore, paste);
+	cr5 = offsetof(struct lowcore, paste);
 	__ctl_load(cr5, 5, 5);
 }
 
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 6a75352f453c..cbad2e6d7dd7 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -399,9 +399,9 @@ static int __must_check __deliver_restart(struct kvm_vcpu *vcpu)
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0);
 
 	rc  = write_guest_lc(vcpu,
-			     offsetof(struct _lowcore, restart_old_psw),
+			     offsetof(struct lowcore, restart_old_psw),
 			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
-	rc |= read_guest_lc(vcpu, offsetof(struct _lowcore, restart_psw),
+	rc |= read_guest_lc(vcpu, offsetof(struct lowcore, restart_psw),
 			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
 	clear_bit(IRQ_PEND_RESTART, &li->pending_irqs);
 	return rc ? -EFAULT : 0;
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index d76b51cb4b62..ed74e86d9b9e 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -355,7 +355,7 @@ static int handle_stfl(struct kvm_vcpu *vcpu)
 	 * into a u32 memory representation. They will remain bits 0-31.
 	 */
 	fac = *vcpu->kvm->arch.model.fac->list >> 32;
-	rc = write_guest_lc(vcpu, offsetof(struct _lowcore, stfl_fac_list),
+	rc = write_guest_lc(vcpu, offsetof(struct lowcore, stfl_fac_list),
 			    &fac, sizeof(fac));
 	if (rc)
 		return rc;
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 8a993a53fcd6..fec59c067d0d 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -163,11 +163,11 @@ static int is_swapped(unsigned long addr)
 	unsigned long lc;
 	int cpu;
 
-	if (addr < sizeof(struct _lowcore))
+	if (addr < sizeof(struct lowcore))
 		return 1;
 	for_each_online_cpu(cpu) {
 		lc = (unsigned long) lowcore_ptr[cpu];
-		if (addr > lc + sizeof(struct _lowcore) - 1 || addr < lc)
+		if (addr > lc + sizeof(struct lowcore) - 1 || addr < lc)
 			continue;
 		return 1;
 	}
-- 
cgit 


From 0dab3e0e59ac3692e2f95cb37ba17d5dfb3d1e5f Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Tue, 5 Jan 2016 18:17:53 +0200
Subject: s390: drop smp_mb in vdso_init

The initial s390 vdso code is heavily influenced by the powerpc version
which does have a smp_wmb in vdso_init right before the vdso_ready=1
assignment. s390 has no need for that.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Message-Id: <1452010645-25380-1-git-send-email-mst@redhat.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/vdso.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 4f07eaced960..604f4a68b524 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -299,8 +299,6 @@ static int __init vdso_init(void)
 
 	get_page(virt_to_page(vdso_data));
 
-	smp_mb();
-
 	return 0;
 }
 early_initcall(vdso_init);
-- 
cgit 


From 249c543b97e1409b13fb9539b2f880e58ddd87cf Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Tue, 5 Jan 2016 13:29:38 +0100
Subject: s390/vdso: optimize getcpu system call

Add the CPU number to the per-cpu vdso data page and add the
__kernel_getcpu function to the vdso object to retrieve the
CPU number in user space.

Suggested-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/vdso.h         |  2 ++
 arch/s390/kernel/asm-offsets.c       |  2 ++
 arch/s390/kernel/vdso.c              |  9 +++++++-
 arch/s390/kernel/vdso32/Makefile     |  2 +-
 arch/s390/kernel/vdso32/getcpu.S     | 43 ++++++++++++++++++++++++++++++++++++
 arch/s390/kernel/vdso32/vdso32.lds.S |  1 +
 arch/s390/kernel/vdso64/Makefile     |  2 +-
 arch/s390/kernel/vdso64/getcpu.S     | 42 +++++++++++++++++++++++++++++++++++
 arch/s390/kernel/vdso64/vdso64.lds.S |  1 +
 9 files changed, 101 insertions(+), 3 deletions(-)
 create mode 100644 arch/s390/kernel/vdso32/getcpu.S
 create mode 100644 arch/s390/kernel/vdso64/getcpu.S

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h
index f9b02d300d60..d0a2dbf2433d 100644
--- a/arch/s390/include/asm/vdso.h
+++ b/arch/s390/include/asm/vdso.h
@@ -38,6 +38,8 @@ struct vdso_data {
 struct vdso_per_cpu_data {
 	__u64 ectg_timer_base;
 	__u64 ectg_user_time;
+	__u32 cpu_nr;
+	__u32 node_id;
 };
 
 extern struct vdso_data *vdso_data;
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index d5916ef9c619..53bbc9e8b281 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -80,6 +80,8 @@ int main(void)
 	OFFSET(__VDSO_TK_SHIFT, vdso_data, tk_shift);
 	OFFSET(__VDSO_ECTG_BASE, vdso_per_cpu_data, ectg_timer_base);
 	OFFSET(__VDSO_ECTG_USER, vdso_per_cpu_data, ectg_user_time);
+	OFFSET(__VDSO_CPU_NR, vdso_per_cpu_data, cpu_nr);
+	OFFSET(__VDSO_NODE_ID, vdso_per_cpu_data, node_id);
 	BLANK();
 	/* constants used by the vdso */
 	DEFINE(__CLOCK_REALTIME, CLOCK_REALTIME);
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 604f4a68b524..94495cac8be3 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -80,7 +80,7 @@ struct vdso_data *vdso_data = &vdso_data_store.data;
 /*
  * Setup vdso data page.
  */
-static void vdso_init_data(struct vdso_data *vd)
+static void __init vdso_init_data(struct vdso_data *vd)
 {
 	vd->ectg_available = test_facility(31);
 }
@@ -93,6 +93,7 @@ static void vdso_init_data(struct vdso_data *vd)
 int vdso_alloc_per_cpu(struct lowcore *lowcore)
 {
 	unsigned long segment_table, page_table, page_frame;
+	struct vdso_per_cpu_data *vd;
 	u32 *psal, *aste;
 	int i;
 
@@ -107,6 +108,12 @@ int vdso_alloc_per_cpu(struct lowcore *lowcore)
 	if (!segment_table || !page_table || !page_frame)
 		goto out;
 
+	/* Initialize per-cpu vdso data page */
+	vd = (struct vdso_per_cpu_data *) page_frame;
+	vd->cpu_nr = lowcore->cpu_nr;
+	vd->node_id = cpu_to_node(vd->cpu_nr);
+
+	/* Set up access register mode page table */
 	clear_table((unsigned long *) segment_table, _SEGMENT_ENTRY_EMPTY,
 		    PAGE_SIZE << SEGMENT_ORDER);
 	clear_table((unsigned long *) page_table, _PAGE_INVALID,
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index ee8a18e50a25..f9c459586649 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -1,6 +1,6 @@
 # List of files in the vdso, has to be asm only for now
 
-obj-vdso32 = gettimeofday.o clock_getres.o clock_gettime.o note.o
+obj-vdso32 = gettimeofday.o clock_getres.o clock_gettime.o note.o getcpu.o
 
 # Build rules
 
diff --git a/arch/s390/kernel/vdso32/getcpu.S b/arch/s390/kernel/vdso32/getcpu.S
new file mode 100644
index 000000000000..c1ed0b72030f
--- /dev/null
+++ b/arch/s390/kernel/vdso32/getcpu.S
@@ -0,0 +1,43 @@
+/*
+ * Userland implementation of getcpu() for 32 bits processes in a
+ * s390 kernel for use in the vDSO
+ *
+ *  Copyright IBM Corp. 2016
+ *  Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+#include <asm/vdso.h>
+#include <asm/asm-offsets.h>
+
+	.text
+	.align 4
+	.globl __kernel_getcpu
+	.type  __kernel_getcpu,@function
+__kernel_getcpu:
+	.cfi_startproc
+	ear	%r1,%a4
+	lhi	%r4,1
+	sll	%r4,24
+	sar	%a4,%r4
+	la	%r4,0
+	epsw	%r0,0
+	sacf	512
+	l	%r5,__VDSO_CPU_NR(%r4)
+	l	%r4,__VDSO_NODE_ID(%r4)
+	tml	%r0,0x4000
+	jo	1f
+	tml	%r0,0x8000
+	jno	0f
+	sacf	256
+	j	1f
+0:	sacf	0
+1:	sar	%a4,%r1
+	ltr	%r2,%r2
+	jz	2f
+	st	%r5,0(%r2)
+2:	ltr	%r3,%r3
+	jz	3f
+	st	%r4,0(%r3)
+3:	lhi	%r2,0
+	br	%r14
+	.cfi_endproc
+	.size	__kernel_getcpu,.-__kernel_getcpu
diff --git a/arch/s390/kernel/vdso32/vdso32.lds.S b/arch/s390/kernel/vdso32/vdso32.lds.S
index a8c379fa1247..8f048c2d6d13 100644
--- a/arch/s390/kernel/vdso32/vdso32.lds.S
+++ b/arch/s390/kernel/vdso32/vdso32.lds.S
@@ -132,6 +132,7 @@ VERSION
 		__kernel_gettimeofday;
 		__kernel_clock_gettime;
 		__kernel_clock_getres;
+		__kernel_getcpu;
 
 	local: *;
 	};
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index c4b03f9ed228..058659c1b8cf 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -1,6 +1,6 @@
 # List of files in the vdso, has to be asm only for now
 
-obj-vdso64 = gettimeofday.o clock_getres.o clock_gettime.o note.o
+obj-vdso64 = gettimeofday.o clock_getres.o clock_gettime.o note.o getcpu.o
 
 # Build rules
 
diff --git a/arch/s390/kernel/vdso64/getcpu.S b/arch/s390/kernel/vdso64/getcpu.S
new file mode 100644
index 000000000000..4cbe98291931
--- /dev/null
+++ b/arch/s390/kernel/vdso64/getcpu.S
@@ -0,0 +1,42 @@
+/*
+ * Userland implementation of getcpu() for 64 bits processes in a
+ * s390 kernel for use in the vDSO
+ *
+ *  Copyright IBM Corp. 2016
+ *  Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+#include <asm/vdso.h>
+#include <asm/asm-offsets.h>
+
+	.text
+	.align 4
+	.globl __kernel_getcpu
+	.type  __kernel_getcpu,@function
+__kernel_getcpu:
+	.cfi_startproc
+	ear	%r1,%a4
+	llilh	%r4,0x0100
+	sar	%a4,%r4
+	la	%r4,0
+	epsw	%r0,0
+	sacf	512
+	l	%r5,__VDSO_CPU_NR(%r4)
+	l	%r4,__VDSO_NODE_ID(%r4)
+	tml	%r0,0x4000
+	jo	1f
+	tml	%r0,0x8000
+	jno	0f
+	sacf	256
+	j	1f
+0:	sacf	0
+1:	sar	%a4,%r1
+	ltgr	%r2,%r2
+	jz	2f
+	st	%r5,0(%r2)
+2:	ltgr	%r3,%r3
+	jz	3f
+	st	%r4,0(%r3)
+3:	lghi	%r2,0
+	br	%r14
+	.cfi_endproc
+	.size	__kernel_getcpu,.-__kernel_getcpu
diff --git a/arch/s390/kernel/vdso64/vdso64.lds.S b/arch/s390/kernel/vdso64/vdso64.lds.S
index 9f5979d102a9..f35455d497fe 100644
--- a/arch/s390/kernel/vdso64/vdso64.lds.S
+++ b/arch/s390/kernel/vdso64/vdso64.lds.S
@@ -132,6 +132,7 @@ VERSION
 		__kernel_gettimeofday;
 		__kernel_clock_gettime;
 		__kernel_clock_getres;
+		__kernel_getcpu;
 
 	local: *;
 	};
-- 
cgit 


From cb14def6a9cae973ba6f702443c8fc589998279c Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Thu, 2 Jul 2015 17:30:31 +0200
Subject: s390/configs: update default configurations

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/configs/default_defconfig     | 27 ++++++++++++---------------
 arch/s390/configs/gcov_defconfig        | 24 ++++++++++--------------
 arch/s390/configs/performance_defconfig | 24 ++++++++++--------------
 arch/s390/configs/zfcpdump_defconfig    | 10 ++--------
 arch/s390/defconfig                     | 30 +++++++++++++++++++++++++++---
 5 files changed, 61 insertions(+), 54 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index ed7da281df66..0ac42cc4f880 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -10,28 +10,35 @@ CONFIG_TASKSTATS=y
 CONFIG_TASK_DELAY_ACCT=y
 CONFIG_TASK_XACCT=y
 CONFIG_TASK_IO_ACCOUNTING=y
-CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_NUMA_BALANCING=y
 CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_PIDS=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
+CONFIG_MEMCG=y
+CONFIG_MEMCG_SWAP=y
+CONFIG_MEMCG_KMEM=y
+CONFIG_CGROUP_HUGETLB=y
 CONFIG_CGROUP_PERF=y
 CONFIG_CFS_BANDWIDTH=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_CGROUP=y
 CONFIG_NAMESPACES=y
+CONFIG_USER_NS=y
 CONFIG_SCHED_AUTOGROUP=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 CONFIG_BPF_SYSCALL=y
+CONFIG_USERFAULTFD=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=m
 CONFIG_KPROBES=y
 CONFIG_JUMP_LABEL=y
+CONFIG_STATIC_KEYS_SELFTEST=y
 CONFIG_MODULES=y
 CONFIG_MODULE_FORCE_LOAD=y
 CONFIG_MODULE_UNLOAD=y
@@ -64,7 +71,6 @@ CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_CHSC_SCH=y
 CONFIG_CRASH_DUMP=y
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_HIBERNATION=y
 CONFIG_NET=y
@@ -106,7 +112,6 @@ CONFIG_TCP_CONG_LP=m
 CONFIG_TCP_CONG_VENO=m
 CONFIG_TCP_CONG_YEAH=m
 CONFIG_TCP_CONG_ILLINOIS=m
-CONFIG_IPV6=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
@@ -457,19 +462,9 @@ CONFIG_INFINIBAND=m
 CONFIG_INFINIBAND_USER_ACCESS=m
 CONFIG_MLX4_INFINIBAND=m
 CONFIG_VIRTIO_BALLOON=m
-# CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT2_FS=y
-CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT2_FS_POSIX_ACL=y
-CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
-CONFIG_JBD_DEBUG=y
 CONFIG_JBD2_DEBUG=y
 CONFIG_JFS_FS=m
 CONFIG_JFS_POSIX_ACL=y
@@ -490,7 +485,7 @@ CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_QFMT_V1=m
 CONFIG_QFMT_V2=m
 CONFIG_AUTOFS4_FS=m
-CONFIG_FUSE_FS=m
+CONFIG_FUSE_FS=y
 CONFIG_CUSE=m
 CONFIG_FSCACHE=m
 CONFIG_CACHEFILES=m
@@ -542,10 +537,11 @@ CONFIG_DLM=m
 CONFIG_PRINTK_TIME=y
 CONFIG_DYNAMIC_DEBUG=y
 CONFIG_DEBUG_INFO=y
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_FRAME_WARN=1024
 CONFIG_READABLE_ASM=y
 CONFIG_UNUSED_SYMBOLS=y
+CONFIG_HEADERS_CHECK=y
+CONFIG_DEBUG_SECTION_MISMATCH=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_PAGEALLOC=y
 CONFIG_DEBUG_OBJECTS=y
@@ -588,6 +584,7 @@ CONFIG_FAILSLAB=y
 CONFIG_FAIL_PAGE_ALLOC=y
 CONFIG_FAIL_MAKE_REQUEST=y
 CONFIG_FAIL_IO_TIMEOUT=y
+CONFIG_FAIL_FUTEX=y
 CONFIG_FAULT_INJECTION_DEBUG_FS=y
 CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
 CONFIG_LATENCYTOP=y
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index 9858b14cde1e..a31dcd56f7c0 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -10,21 +10,27 @@ CONFIG_TASKSTATS=y
 CONFIG_TASK_DELAY_ACCT=y
 CONFIG_TASK_XACCT=y
 CONFIG_TASK_IO_ACCOUNTING=y
-CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_NUMA_BALANCING=y
 CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_PIDS=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
+CONFIG_MEMCG=y
+CONFIG_MEMCG_SWAP=y
+CONFIG_MEMCG_KMEM=y
+CONFIG_CGROUP_HUGETLB=y
 CONFIG_CGROUP_PERF=y
 CONFIG_BLK_CGROUP=y
 CONFIG_NAMESPACES=y
+CONFIG_USER_NS=y
 CONFIG_SCHED_AUTOGROUP=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 CONFIG_BPF_SYSCALL=y
+CONFIG_USERFAULTFD=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=m
@@ -61,7 +67,6 @@ CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_CHSC_SCH=y
 CONFIG_CRASH_DUMP=y
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_HIBERNATION=y
 CONFIG_NET=y
@@ -103,7 +108,6 @@ CONFIG_TCP_CONG_LP=m
 CONFIG_TCP_CONG_VENO=m
 CONFIG_TCP_CONG_YEAH=m
 CONFIG_TCP_CONG_ILLINOIS=m
-CONFIG_IPV6=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
@@ -453,19 +457,9 @@ CONFIG_INFINIBAND=m
 CONFIG_INFINIBAND_USER_ACCESS=m
 CONFIG_MLX4_INFINIBAND=m
 CONFIG_VIRTIO_BALLOON=m
-# CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT2_FS=y
-CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT2_FS_POSIX_ACL=y
-CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
-CONFIG_JBD_DEBUG=y
 CONFIG_JBD2_DEBUG=y
 CONFIG_JFS_FS=m
 CONFIG_JFS_POSIX_ACL=y
@@ -485,7 +479,7 @@ CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_QFMT_V1=m
 CONFIG_QFMT_V2=m
 CONFIG_AUTOFS4_FS=m
-CONFIG_FUSE_FS=m
+CONFIG_FUSE_FS=y
 CONFIG_CUSE=m
 CONFIG_FSCACHE=m
 CONFIG_CACHEFILES=m
@@ -550,6 +544,7 @@ CONFIG_NOTIFIER_ERROR_INJECTION=m
 CONFIG_CPU_NOTIFIER_ERROR_INJECT=m
 CONFIG_PM_NOTIFIER_ERROR_INJECT=m
 CONFIG_LATENCYTOP=y
+CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
 CONFIG_BLK_DEV_IO_TRACE=y
 # CONFIG_KPROBE_EVENT is not set
 CONFIG_LKDTM=m
@@ -557,6 +552,7 @@ CONFIG_RBTREE_TEST=m
 CONFIG_INTERVAL_TREE_TEST=m
 CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
+CONFIG_TEST_BPF=m
 # CONFIG_STRICT_DEVMEM is not set
 CONFIG_S390_PTDUMP=y
 CONFIG_ENCRYPTED_KEYS=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 7f14f80717d4..7b73bf353345 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -10,22 +10,28 @@ CONFIG_TASKSTATS=y
 CONFIG_TASK_DELAY_ACCT=y
 CONFIG_TASK_XACCT=y
 CONFIG_TASK_IO_ACCOUNTING=y
-CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_NUMA_BALANCING=y
 # CONFIG_NUMA_BALANCING_DEFAULT_ENABLED is not set
 CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_PIDS=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
+CONFIG_MEMCG=y
+CONFIG_MEMCG_SWAP=y
+CONFIG_MEMCG_KMEM=y
+CONFIG_CGROUP_HUGETLB=y
 CONFIG_CGROUP_PERF=y
 CONFIG_BLK_CGROUP=y
 CONFIG_NAMESPACES=y
+CONFIG_USER_NS=y
 CONFIG_SCHED_AUTOGROUP=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 CONFIG_BPF_SYSCALL=y
+CONFIG_USERFAULTFD=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=m
@@ -61,7 +67,6 @@ CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_CHSC_SCH=y
 CONFIG_CRASH_DUMP=y
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_HIBERNATION=y
 CONFIG_NET=y
@@ -103,7 +108,6 @@ CONFIG_TCP_CONG_LP=m
 CONFIG_TCP_CONG_VENO=m
 CONFIG_TCP_CONG_YEAH=m
 CONFIG_TCP_CONG_ILLINOIS=m
-CONFIG_IPV6=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
@@ -453,19 +457,9 @@ CONFIG_INFINIBAND=m
 CONFIG_INFINIBAND_USER_ACCESS=m
 CONFIG_MLX4_INFINIBAND=m
 CONFIG_VIRTIO_BALLOON=m
-# CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT2_FS=y
-CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT2_FS_POSIX_ACL=y
-CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
-CONFIG_JBD_DEBUG=y
 CONFIG_JBD2_DEBUG=y
 CONFIG_JFS_FS=m
 CONFIG_JFS_POSIX_ACL=y
@@ -485,7 +479,7 @@ CONFIG_QUOTA_NETLINK_INTERFACE=y
 CONFIG_QFMT_V1=m
 CONFIG_QFMT_V2=m
 CONFIG_AUTOFS4_FS=m
-CONFIG_FUSE_FS=m
+CONFIG_FUSE_FS=y
 CONFIG_CUSE=m
 CONFIG_FSCACHE=m
 CONFIG_CACHEFILES=m
@@ -546,6 +540,7 @@ CONFIG_TIMER_STATS=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_RCU_CPU_STALL_TIMEOUT=60
 CONFIG_LATENCYTOP=y
+CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
 CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
@@ -554,6 +549,7 @@ CONFIG_UPROBE_EVENT=y
 CONFIG_LKDTM=m
 CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
+CONFIG_TEST_BPF=m
 # CONFIG_STRICT_DEVMEM is not set
 CONFIG_S390_PTDUMP=y
 CONFIG_ENCRYPTED_KEYS=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 92805d604173..1719843a55a2 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -23,8 +23,6 @@ CONFIG_CRASH_DUMP=y
 # CONFIG_SECCOMP is not set
 CONFIG_NET=y
 # CONFIG_IUCV is not set
-CONFIG_ATM=y
-CONFIG_ATM_LANE=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -54,14 +52,10 @@ CONFIG_RAW_DRIVER=y
 # CONFIG_S390_VMUR is not set
 # CONFIG_HID is not set
 # CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT4_FS=y
-CONFIG_EXT4_FS_POSIX_ACL=y
-CONFIG_EXT4_FS_SECURITY=y
+# CONFIG_DNOTIFY is not set
 # CONFIG_INOTIFY_USER is not set
 CONFIG_CONFIGFS_FS=y
+# CONFIG_MISC_FILESYSTEMS is not set
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_FS=y
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 9256b48e7e43..e24f2af4c73b 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -11,22 +11,31 @@ CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_CGROUPS=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_MEMCG=y
 CONFIG_MEMCG_SWAP=y
+CONFIG_MEMCG_KMEM=y
+CONFIG_CGROUP_HUGETLB=y
+CONFIG_CGROUP_PERF=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_CGROUP=y
 CONFIG_NAMESPACES=y
+CONFIG_USER_NS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 CONFIG_BPF_SYSCALL=y
+CONFIG_USERFAULTFD=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
 CONFIG_KPROBES=y
 CONFIG_JUMP_LABEL=y
+CONFIG_STATIC_KEYS_SELFTEST=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODVERSIONS=y
@@ -37,6 +46,7 @@ CONFIG_DEFAULT_DEADLINE=y
 CONFIG_LIVEPATCH=y
 CONFIG_MARCH_Z196=y
 CONFIG_NR_CPUS=256
+CONFIG_NUMA=y
 CONFIG_HZ_100=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
@@ -52,7 +62,6 @@ CONFIG_NET_KEY=y
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 # CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
 CONFIG_L2TP=m
 CONFIG_L2TP_DEBUGFS=m
 CONFIG_VLAN_8021Q=y
@@ -89,10 +98,26 @@ CONFIG_BLK_DEV_SR_VENDOR=y
 CONFIG_CHR_DEV_SG=y
 CONFIG_SCSI_CONSTANTS=y
 CONFIG_SCSI_LOGGING=y
-CONFIG_SCSI_SCAN_ASYNC=y
 CONFIG_SCSI_FC_ATTRS=y
 CONFIG_ZFCP=y
 CONFIG_SCSI_VIRTIO=y
+CONFIG_MD=y
+CONFIG_MD_LINEAR=m
+CONFIG_MD_RAID0=m
+CONFIG_MD_MULTIPATH=m
+CONFIG_BLK_DEV_DM=y
+CONFIG_DM_CRYPT=m
+CONFIG_DM_SNAPSHOT=m
+CONFIG_DM_MIRROR=m
+CONFIG_DM_LOG_USERSPACE=m
+CONFIG_DM_RAID=m
+CONFIG_DM_ZERO=m
+CONFIG_DM_MULTIPATH=m
+CONFIG_DM_MULTIPATH_QL=m
+CONFIG_DM_MULTIPATH_ST=m
+CONFIG_DM_UEVENT=y
+CONFIG_DM_VERITY=m
+CONFIG_DM_SWITCH=m
 CONFIG_NETDEVICES=y
 CONFIG_BONDING=m
 CONFIG_DUMMY=m
@@ -137,7 +162,6 @@ CONFIG_DEBUG_PI_LIST=y
 CONFIG_DEBUG_SG=y
 CONFIG_DEBUG_NOTIFIERS=y
 CONFIG_RCU_CPU_STALL_TIMEOUT=60
-# CONFIG_RCU_CPU_STALL_INFO is not set
 CONFIG_RCU_TRACE=y
 CONFIG_LATENCYTOP=y
 CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
-- 
cgit 


From bcb7825a77f41c7dd91da6f7ac10b928156a322e Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Fri, 1 Jan 2016 13:39:22 +0100
Subject: s390: fix normalization bug in exception table sorting

The normalization pass in the sorting routine of the relative exception
table serves two purposes:
- it ensures that the address fields of the exception table entries are
  fully ordered, so that no ambiguities arise between entries with
  identical instruction offsets (i.e., when two instructions that are
  exactly 8 bytes apart each have an exception table entry associated with
  them)
- it ensures that the offsets of both the instruction and the fixup fields
  of each entry are relative to their final location after sorting.

Commit eb608fb366de ("s390/exceptions: switch to relative exception table
entries") ported the relative exception table format from x86, but modified
the sorting routine to only normalize the instruction offset field and not
the fixup offset field. The result is that the fixup offset of each entry
will be relative to the original location of the entry before sorting,
likely leading to crashes when those entries are dereferenced.

Fixes: eb608fb366de ("s390/exceptions: switch to relative exception table entries")
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/mm/extable.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/mm/extable.c b/arch/s390/mm/extable.c
index 4d1ee88864e8..18c8b819b0aa 100644
--- a/arch/s390/mm/extable.c
+++ b/arch/s390/mm/extable.c
@@ -52,12 +52,16 @@ void sort_extable(struct exception_table_entry *start,
 	int i;
 
 	/* Normalize entries to being relative to the start of the section */
-	for (p = start, i = 0; p < finish; p++, i += 8)
+	for (p = start, i = 0; p < finish; p++, i += 8) {
 		p->insn += i;
+		p->fixup += i + 4;
+	}
 	sort(start, finish - start, sizeof(*start), cmp_ex, NULL);
 	/* Denormalize all entries */
-	for (p = start, i = 0; p < finish; p++, i += 8)
+	for (p = start, i = 0; p < finish; p++, i += 8) {
 		p->insn -= i;
+		p->fixup -= i + 4;
+	}
 }
 
 #ifdef CONFIG_MODULES
-- 
cgit 


From 5a1b26d7c629915446222ebe77d16567c98426ff Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Thu, 31 Dec 2015 12:09:13 +0200
Subject: lcoking/barriers, arch: Use smp barriers in smp_store_release()

With commit b92b8b35a2e ("locking/arch: Rename set_mb() to smp_store_mb()")
it was made clear that the context of this call (and thus set_mb)
is strictly for CPU ordering, as opposed to IO. As such all archs
should use the smp variant of mb(), respecting the semantics and
saving a mandatory barrier on UP.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <linux-arch@vger.kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: dave@stgolabs.net
Link: http://lkml.kernel.org/r/1445975631-17047-3-git-send-email-dave@stgolabs.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 arch/s390/include/asm/barrier.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index d68e11e0df5e..7ffd0b19135c 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -36,7 +36,7 @@
 #define smp_mb__before_atomic()		smp_mb()
 #define smp_mb__after_atomic()		smp_mb()
 
-#define smp_store_mb(var, value)		do { WRITE_ONCE(var, value); mb(); } while (0)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 
 #define smp_store_release(p, v)						\
 do {									\
-- 
cgit 


From 21535aaed9e33b4cc485ab2245dd2958816ee916 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Mon, 21 Dec 2015 09:22:18 +0200
Subject: s390: reuse asm-generic/barrier.h

On s390 read_barrier_depends, smp_read_barrier_depends
smp_store_mb(), smp_mb__before_atomic and smp_mb__after_atomic match the
asm-generic variants exactly. Drop the local definitions and pull in
asm-generic/barrier.h instead.

This is in preparation to refactoring this code area.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/s390/include/asm/barrier.h | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index 7ffd0b19135c..c358c31a7f07 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -30,14 +30,6 @@
 #define smp_rmb()			rmb()
 #define smp_wmb()			wmb()
 
-#define read_barrier_depends()		do { } while (0)
-#define smp_read_barrier_depends()	do { } while (0)
-
-#define smp_mb__before_atomic()		smp_mb()
-#define smp_mb__after_atomic()		smp_mb()
-
-#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); smp_mb(); } while (0)
-
 #define smp_store_release(p, v)						\
 do {									\
 	compiletime_assert_atomic_type(*p);				\
@@ -53,4 +45,6 @@ do {									\
 	___p1;								\
 })
 
+#include <asm-generic/barrier.h>
+
 #endif /* __ASM_BARRIER_H */
-- 
cgit 


From 82b44496abd91781ed4120c3b0c1a3d111c3e28e Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Sun, 27 Dec 2015 15:04:42 +0200
Subject: s390: define __smp_xxx

This defines __smp_xxx barriers for s390,
for use by virtualization.

Some smp_xxx barriers are removed as they are
defined correctly by asm-generic/barriers.h

Note: smp_mb, smp_rmb and smp_wmb are defined as full barriers
unconditionally on this architecture.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/s390/include/asm/barrier.h | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index c358c31a7f07..fbd25b299c8b 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -26,18 +26,21 @@
 #define wmb()				barrier()
 #define dma_rmb()			mb()
 #define dma_wmb()			mb()
-#define smp_mb()			mb()
-#define smp_rmb()			rmb()
-#define smp_wmb()			wmb()
-
-#define smp_store_release(p, v)						\
+#define __smp_mb()			mb()
+#define __smp_rmb()			rmb()
+#define __smp_wmb()			wmb()
+#define smp_mb()			__smp_mb()
+#define smp_rmb()			__smp_rmb()
+#define smp_wmb()			__smp_wmb()
+
+#define __smp_store_release(p, v)					\
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	barrier();							\
 	WRITE_ONCE(*p, v);						\
 } while (0)
 
-#define smp_load_acquire(p)						\
+#define __smp_load_acquire(p)						\
 ({									\
 	typeof(*p) ___p1 = READ_ONCE(*p);				\
 	compiletime_assert_atomic_type(*p);				\
-- 
cgit 


From a677f4869576eb177570ffee68598d2202de030f Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Wed, 6 Jan 2016 09:13:14 +0200
Subject: s390: use generic memory barriers

The s390 kernel is SMP to 99.99%, we just didn't bother with a
non-smp variant for the memory-barriers. If the generic header
is used we'd get the non-smp version for free. It will save a
small amount of text space for CONFIG_SMP=n.

Suggested-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/s390/include/asm/barrier.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index fbd25b299c8b..4d26fa43ec90 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -29,9 +29,6 @@
 #define __smp_mb()			mb()
 #define __smp_rmb()			rmb()
 #define __smp_wmb()			wmb()
-#define smp_mb()			__smp_mb()
-#define smp_rmb()			__smp_rmb()
-#define smp_wmb()			__smp_wmb()
 
 #define __smp_store_release(p, v)					\
 do {									\
-- 
cgit 


From 779a6a36961b50cd154da5705d9e6508f819cc4e Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Sun, 10 Jan 2016 13:19:38 +0200
Subject: s390: more efficient smp barriers

As per: lkml.kernel.org/r/20150921112252.3c2937e1@mschwide
atomics imply a barrier on s390, so s390 should change
smp_mb__before_atomic and smp_mb__after_atomic to barrier() instead of
smp_mb() and hence should not use the generic versions.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Suggested-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/s390/include/asm/barrier.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index 4d26fa43ec90..5c8db3ce61c8 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -45,6 +45,9 @@ do {									\
 	___p1;								\
 })
 
+#define __smp_mb__before_atomic()	barrier()
+#define __smp_mb__after_atomic()	barrier()
+
 #include <asm-generic/barrier.h>
 
 #endif /* __ASM_BARRIER_H */
-- 
cgit 


From eca56ff906bdd0239485e8b47154a6e73dd9a2f3 Mon Sep 17 00:00:00 2001
From: Jerome Marchand <jmarchan@redhat.com>
Date: Thu, 14 Jan 2016 15:19:26 -0800
Subject: mm, shmem: add internal shmem resident memory accounting

Currently looking at /proc/<pid>/status or statm, there is no way to
distinguish shmem pages from pages mapped to a regular file (shmem pages
are mapped to /dev/zero), even though their implication in actual memory
use is quite different.

The internal accounting currently counts shmem pages together with
regular files.  As a preparation to extend the userspace interfaces,
this patch adds MM_SHMEMPAGES counter to mm_rss_stat to account for
shmem pages separately from MM_FILEPAGES.  The next patch will expose it
to userspace - this patch doesn't change the exported values yet, by
adding up MM_SHMEMPAGES to MM_FILEPAGES at places where MM_FILEPAGES was
used before.  The only user-visible change after this patch is the OOM
killer message that separates the reported "shmem-rss" from "file-rss".

[vbabka@suse.cz: forward-porting, tweak changelog]
Signed-off-by: Jerome Marchand <jmarchan@redhat.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/s390/mm/pgtable.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 63b039899a5e..aa34af0a0b26 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -603,10 +603,7 @@ static void gmap_zap_swap_entry(swp_entry_t entry, struct mm_struct *mm)
 	else if (is_migration_entry(entry)) {
 		struct page *page = migration_entry_to_page(entry);
 
-		if (PageAnon(page))
-			dec_mm_counter(mm, MM_ANONPAGES);
-		else
-			dec_mm_counter(mm, MM_FILEPAGES);
+		dec_mm_counter(mm, mm_counter(page));
 	}
 	free_swap_and_cache(entry);
 }
-- 
cgit 


From ddc58f27f9eee9117219936f77e90ad5b2e00e96 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Fri, 15 Jan 2016 16:52:56 -0800
Subject: mm: drop tail page refcounting

Tail page refcounting is utterly complicated and painful to support.

It uses ->_mapcount on tail pages to store how many times this page is
pinned.  get_page() bumps ->_mapcount on tail page in addition to
->_count on head.  This information is required by split_huge_page() to
be able to distribute pins from head of compound page to tails during
the split.

We will need ->_mapcount to account PTE mappings of subpages of the
compound page.  We eliminate need in current meaning of ->_mapcount in
tail pages by forbidding split entirely if the page is pinned.

The only user of tail page refcounting is THP which is marked BROKEN for
now.

Let's drop all this mess.  It makes get_page() and put_page() much
simpler.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Jerome Marchand <jmarchan@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/s390/mm/gup.c | 13 +------------
 1 file changed, 1 insertion(+), 12 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 21c74a71e2ab..1a2cad52babf 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -55,7 +55,7 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
 	unsigned long mask, result;
-	struct page *head, *page, *tail;
+	struct page *head, *page;
 	int refs;
 
 	result = write ? 0 : _SEGMENT_ENTRY_PROTECT;
@@ -67,7 +67,6 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 	refs = 0;
 	head = pmd_page(pmd);
 	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	tail = page;
 	do {
 		VM_BUG_ON(compound_head(page) != head);
 		pages[*nr] = page;
@@ -88,16 +87,6 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 		return 0;
 	}
 
-	/*
-	 * Any tail page need their mapcount reference taken before we
-	 * return.
-	 */
-	while (refs--) {
-		if (PageTail(tail))
-			get_huge_page_tail(tail);
-		tail++;
-	}
-
 	return 1;
 }
 
-- 
cgit 


From fecffad25458f0217e3d34613be09faaca208bad Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Fri, 15 Jan 2016 16:53:24 -0800
Subject: s390, thp: remove infrastructure for handling splitting PMDs

With new refcounting we don't need to mark PMDs splitting.  Let's drop
code to handle this.

pmdp_splitting_flush() is not needed too: on splitting PMD we will do
pmdp_clear_flush() + set_pte_at().  pmdp_clear_flush() will do IPI as
needed for fast_gup.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/s390/include/asm/pgtable.h | 16 +---------------
 arch/s390/mm/gup.c              | 11 +----------
 arch/s390/mm/pgtable.c          | 16 ----------------
 3 files changed, 2 insertions(+), 41 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 024f85f947ae..64ead8091248 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -286,7 +286,6 @@ static inline int is_module_addr(void *addr)
 
 #define _SEGMENT_ENTRY_DIRTY	0x2000	/* SW segment dirty bit */
 #define _SEGMENT_ENTRY_YOUNG	0x1000	/* SW segment young bit */
-#define _SEGMENT_ENTRY_SPLIT	0x0800	/* THP splitting bit */
 #define _SEGMENT_ENTRY_LARGE	0x0400	/* STE-format control, large page */
 #define _SEGMENT_ENTRY_READ	0x0002	/* SW segment read bit */
 #define _SEGMENT_ENTRY_WRITE	0x0001	/* SW segment write bit */
@@ -318,8 +317,6 @@ static inline int is_module_addr(void *addr)
  * SW-bits: y young, d dirty, r read, w write
  */
 
-#define _SEGMENT_ENTRY_SPLIT_BIT 11	/* THP splitting bit number */
-
 /* Page status table bits for virtualization */
 #define PGSTE_ACC_BITS	0xf000000000000000UL
 #define PGSTE_FP_BIT	0x0800000000000000UL
@@ -523,10 +520,6 @@ static inline int pmd_bad(pmd_t pmd)
 	return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0;
 }
 
-#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
-extern void pmdp_splitting_flush(struct vm_area_struct *vma,
-				 unsigned long addr, pmd_t *pmdp);
-
 #define  __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
 extern int pmdp_set_access_flags(struct vm_area_struct *vma,
 				 unsigned long address, pmd_t *pmdp,
@@ -1424,8 +1417,7 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 	if (pmd_large(pmd)) {
 		pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN_LARGE |
 			_SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_YOUNG |
-			_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SPLIT |
-			_SEGMENT_ENTRY_SOFT_DIRTY;
+			_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SOFT_DIRTY;
 		pmd_val(pmd) |= massage_pgprot_pmd(newprot);
 		if (!(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY))
 			pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
@@ -1533,12 +1525,6 @@ extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 #define __HAVE_ARCH_PGTABLE_WITHDRAW
 extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 
-static inline int pmd_trans_splitting(pmd_t pmd)
-{
-	return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) &&
-		(pmd_val(pmd) & _SEGMENT_ENTRY_SPLIT);
-}
-
 static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 			      pmd_t *pmdp, pmd_t entry)
 {
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 1a2cad52babf..13dab0c1645c 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -105,16 +105,7 @@ static inline int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr,
 		pmd = *pmdp;
 		barrier();
 		next = pmd_addr_end(addr, end);
-		/*
-		 * The pmd_trans_splitting() check below explains why
-		 * pmdp_splitting_flush() has to serialize with
-		 * smp_call_function() against our disabled IRQs, to stop
-		 * this gup-fast code from running while we set the
-		 * splitting bit in the pmd. Returning zero will take
-		 * the slow path that will call wait_split_huge_page()
-		 * if the pmd is still in splitting state.
-		 */
-		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
+		if (pmd_none(pmd))
 			return 0;
 		if (unlikely(pmd_large(pmd))) {
 			/*
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index aa34af0a0b26..4e54492f463a 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -1305,22 +1305,6 @@ int pmdp_set_access_flags(struct vm_area_struct *vma,
 	return 1;
 }
 
-static void pmdp_splitting_flush_sync(void *arg)
-{
-	/* Simply deliver the interrupt */
-}
-
-void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
-			  pmd_t *pmdp)
-{
-	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
-	if (!test_and_set_bit(_SEGMENT_ENTRY_SPLIT_BIT,
-			      (unsigned long *) pmdp)) {
-		/* need to serialize against gup-fast (IRQ disabled) */
-		smp_call_function(pmdp_splitting_flush_sync, NULL, 1);
-	}
-}
-
 void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 				pgtable_t pgtable)
 {
-- 
cgit 


From 4a9e1cda274893eca7d178d7dc265503ccb9d87a Mon Sep 17 00:00:00 2001
From: Dominik Dingel <dingel@linux.vnet.ibm.com>
Date: Fri, 15 Jan 2016 16:57:04 -0800
Subject: mm: bring in additional flag for fixup_user_fault to signal unlock

During Jason's work with postcopy migration support for s390 a problem
regarding gmap faults was discovered.

The gmap code will call fixup_user_fault which will end up always in
handle_mm_fault.  Till now we never cared about retries, but as the
userfaultfd code kind of relies on it.  this needs some fix.

This patchset does not take care of the futex code.  I will now look
closer at this.

This patch (of 2):

With the introduction of userfaultfd, kvm on s390 needs fixup_user_fault
to pass in FAULT_FLAG_ALLOW_RETRY and give feedback if during the
faulting we ever unlocked mmap_sem.

This patch brings in the logic to handle retries as well as it cleans up
the current documentation.  fixup_user_fault was not having the same
semantics as filemap_fault.  It never indicated if a retry happened and
so a caller wasn't able to handle that case.  So we now changed the
behaviour to always retry a locked mmap_sem.

Signed-off-by: Dominik Dingel <dingel@linux.vnet.ibm.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: "Jason J. Herne" <jjherne@linux.vnet.ibm.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Eric B Munson <emunson@akamai.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Dominik Dingel <dingel@linux.vnet.ibm.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/s390/mm/pgtable.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 4e54492f463a..84bddda8d412 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -585,7 +585,7 @@ int gmap_fault(struct gmap *gmap, unsigned long gaddr,
 		rc = vmaddr;
 		goto out_up;
 	}
-	if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags)) {
+	if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags, NULL)) {
 		rc = -EFAULT;
 		goto out_up;
 	}
@@ -727,7 +727,8 @@ int gmap_ipte_notify(struct gmap *gmap, unsigned long gaddr, unsigned long len)
 			break;
 		}
 		/* Get the page mapped */
-		if (fixup_user_fault(current, gmap->mm, addr, FAULT_FLAG_WRITE)) {
+		if (fixup_user_fault(current, gmap->mm, addr, FAULT_FLAG_WRITE,
+				     NULL)) {
 			rc = -EFAULT;
 			break;
 		}
@@ -802,7 +803,8 @@ retry:
 	if (!(pte_val(*ptep) & _PAGE_INVALID) &&
 	     (pte_val(*ptep) & _PAGE_PROTECT)) {
 		pte_unmap_unlock(ptep, ptl);
-		if (fixup_user_fault(current, mm, addr, FAULT_FLAG_WRITE)) {
+		if (fixup_user_fault(current, mm, addr, FAULT_FLAG_WRITE,
+				     NULL)) {
 			up_read(&mm->mmap_sem);
 			return -EFAULT;
 		}
-- 
cgit 


From fef8953ae4e2b87392434a1a3774694c3f8164f6 Mon Sep 17 00:00:00 2001
From: Dominik Dingel <dingel@linux.vnet.ibm.com>
Date: Fri, 15 Jan 2016 16:57:07 -0800
Subject: s390/mm: enable fixup_user_fault retrying

By passing a non-null flag we allow fixup_user_fault to retry, which
enables userfaultfd.  As during these retries we might drop the mmap_sem
we need to check if that happened and redo the complete chain of
actions.

Signed-off-by: Dominik Dingel <dingel@linux.vnet.ibm.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: "Jason J. Herne" <jjherne@linux.vnet.ibm.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Eric B Munson <emunson@akamai.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Dominik Dingel <dingel@linux.vnet.ibm.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/s390/mm/pgtable.c | 29 ++++++++++++++++++++++++++---
 1 file changed, 26 insertions(+), 3 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 84bddda8d412..a809fa8e6f8b 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -578,17 +578,29 @@ int gmap_fault(struct gmap *gmap, unsigned long gaddr,
 {
 	unsigned long vmaddr;
 	int rc;
+	bool unlocked;
 
 	down_read(&gmap->mm->mmap_sem);
+
+retry:
+	unlocked = false;
 	vmaddr = __gmap_translate(gmap, gaddr);
 	if (IS_ERR_VALUE(vmaddr)) {
 		rc = vmaddr;
 		goto out_up;
 	}
-	if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags, NULL)) {
+	if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags,
+			     &unlocked)) {
 		rc = -EFAULT;
 		goto out_up;
 	}
+	/*
+	 * In the case that fixup_user_fault unlocked the mmap_sem during
+	 * faultin redo __gmap_translate to not race with a map/unmap_segment.
+	 */
+	if (unlocked)
+		goto retry;
+
 	rc = __gmap_link(gmap, gaddr, vmaddr);
 out_up:
 	up_read(&gmap->mm->mmap_sem);
@@ -714,12 +726,14 @@ int gmap_ipte_notify(struct gmap *gmap, unsigned long gaddr, unsigned long len)
 	spinlock_t *ptl;
 	pte_t *ptep, entry;
 	pgste_t pgste;
+	bool unlocked;
 	int rc = 0;
 
 	if ((gaddr & ~PAGE_MASK) || (len & ~PAGE_MASK))
 		return -EINVAL;
 	down_read(&gmap->mm->mmap_sem);
 	while (len) {
+		unlocked = false;
 		/* Convert gmap address and connect the page tables */
 		addr = __gmap_translate(gmap, gaddr);
 		if (IS_ERR_VALUE(addr)) {
@@ -728,10 +742,13 @@ int gmap_ipte_notify(struct gmap *gmap, unsigned long gaddr, unsigned long len)
 		}
 		/* Get the page mapped */
 		if (fixup_user_fault(current, gmap->mm, addr, FAULT_FLAG_WRITE,
-				     NULL)) {
+				     &unlocked)) {
 			rc = -EFAULT;
 			break;
 		}
+		/* While trying to map mmap_sem got unlocked. Let us retry */
+		if (unlocked)
+			continue;
 		rc = __gmap_link(gmap, gaddr, addr);
 		if (rc)
 			break;
@@ -792,9 +809,11 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	spinlock_t *ptl;
 	pgste_t old, new;
 	pte_t *ptep;
+	bool unlocked;
 
 	down_read(&mm->mmap_sem);
 retry:
+	unlocked = false;
 	ptep = get_locked_pte(mm, addr, &ptl);
 	if (unlikely(!ptep)) {
 		up_read(&mm->mmap_sem);
@@ -803,8 +822,12 @@ retry:
 	if (!(pte_val(*ptep) & _PAGE_INVALID) &&
 	     (pte_val(*ptep) & _PAGE_PROTECT)) {
 		pte_unmap_unlock(ptep, ptl);
+		/*
+		 * We do not really care about unlocked. We will retry either
+		 * way. But this allows fixup_user_fault to enable userfaultfd.
+		 */
 		if (fixup_user_fault(current, mm, addr, FAULT_FLAG_WRITE,
-				     NULL)) {
+				     &unlocked)) {
 			up_read(&mm->mmap_sem);
 			return -EFAULT;
 		}
-- 
cgit 


From da48d094ce5d7c7dcdad9011648a81c42fd1c2ef Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Fri, 15 Jan 2016 16:58:07 -0800
Subject: Kconfig: remove HAVE_LATENCYTOP_SUPPORT

As illustrated by commit a3afe70b83fd ("[S390] latencytop s390
support."), HAVE_LATENCYTOP_SUPPORT is defined by an architecture to
advertise an implementation of save_stack_trace_tsk.

However, as of 9212ddb5eada ("stacktrace: provide save_stack_trace_tsk()
weak alias") a dummy implementation is provided if STACKTRACE=y.  Given
that LATENCYTOP already depends on STACKTRACE_SUPPORT and selects
STACKTRACE, we can remove HAVE_LATENCYTOP_SUPPORT altogether.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Helge Deller <deller@gmx.de>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/s390/Kconfig | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 24490344c30f..dbeeb3a049f2 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -10,9 +10,6 @@ config LOCKDEP_SUPPORT
 config STACKTRACE_SUPPORT
 	def_bool y
 
-config HAVE_LATENCYTOP_SUPPORT
-	def_bool y
-
 config RWSEM_GENERIC_SPINLOCK
 	bool
 
-- 
cgit 


From e1c7e324539ada3b2b13ca2898bcb4948a9ef9db Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 20 Jan 2016 15:02:05 -0800
Subject: dma-mapping: always provide the dma_map_ops based implementation

Move the generic implementation to <linux/dma-mapping.h> now that all
architectures support it and remove the HAVE_DMA_ATTR Kconfig symbol now
that everyone supports them.

[valentinrothberg@gmail.com: remove leftovers in Kconfig]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Aurelien Jacquiot <a-jacquiot@ti.com>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Haavard Skinnemoen <hskinnemoen@gmail.com>
Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no>
Cc: Helge Deller <deller@gmx.de>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Jesper Nilsson <jesper.nilsson@axis.com>
Cc: Koichi Yasutake <yasutake.koichi@jp.panasonic.com>
Cc: Ley Foon Tan <lftan@altera.com>
Cc: Mark Salter <msalter@redhat.com>
Cc: Mikael Starvik <starvik@axis.com>
Cc: Steven Miao <realmz6@gmail.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Valentin Rothberg <valentinrothberg@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/s390/Kconfig                   | 1 -
 arch/s390/include/asm/dma-mapping.h | 2 --
 2 files changed, 3 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index dbeeb3a049f2..3be9c832dec1 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -579,7 +579,6 @@ config QDIO
 
 menuconfig PCI
 	bool "PCI support"
-	select HAVE_DMA_ATTRS
 	select PCI_MSI
 	select IOMMU_SUPPORT
 	help
diff --git a/arch/s390/include/asm/dma-mapping.h b/arch/s390/include/asm/dma-mapping.h
index b3fd54d93dd2..e64bfcb9702f 100644
--- a/arch/s390/include/asm/dma-mapping.h
+++ b/arch/s390/include/asm/dma-mapping.h
@@ -23,8 +23,6 @@ static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 {
 }
 
-#include <asm-generic/dma-mapping-common.h>
-
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 {
 	if (!dev->dma_mask)
-- 
cgit 


From 5955102c9984fa081b2d570cfac75c97eecf8f3b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 22 Jan 2016 15:40:57 -0500
Subject: wrappers for ->i_mutex access

parallel to mutex_{lock,unlock,trylock,is_locked,lock_nested},
inode_foo(inode) being mutex_foo(&inode->i_mutex).

Please, use those for access to ->i_mutex; over the coming cycle
->i_mutex will become rwsem, with ->lookup() done with it held
only shared.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/s390/hypfs/inode.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index b2e5902bd8f4..0f3da2cb2bd6 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -67,7 +67,7 @@ static void hypfs_remove(struct dentry *dentry)
 	struct dentry *parent;
 
 	parent = dentry->d_parent;
-	mutex_lock(&d_inode(parent)->i_mutex);
+	inode_lock(d_inode(parent));
 	if (simple_positive(dentry)) {
 		if (d_is_dir(dentry))
 			simple_rmdir(d_inode(parent), dentry);
@@ -76,7 +76,7 @@ static void hypfs_remove(struct dentry *dentry)
 	}
 	d_delete(dentry);
 	dput(dentry);
-	mutex_unlock(&d_inode(parent)->i_mutex);
+	inode_unlock(d_inode(parent));
 }
 
 static void hypfs_delete_tree(struct dentry *root)
@@ -331,7 +331,7 @@ static struct dentry *hypfs_create_file(struct dentry *parent, const char *name,
 	struct dentry *dentry;
 	struct inode *inode;
 
-	mutex_lock(&d_inode(parent)->i_mutex);
+	inode_lock(d_inode(parent));
 	dentry = lookup_one_len(name, parent, strlen(name));
 	if (IS_ERR(dentry)) {
 		dentry = ERR_PTR(-ENOMEM);
@@ -359,7 +359,7 @@ static struct dentry *hypfs_create_file(struct dentry *parent, const char *name,
 	d_instantiate(dentry, inode);
 	dget(dentry);
 fail:
-	mutex_unlock(&d_inode(parent)->i_mutex);
+	inode_unlock(d_inode(parent));
 	return dentry;
 }
 
-- 
cgit