From 5abb9351dfd937d43193f4d09af9c72bfe2c4180 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Mon, 1 Apr 2019 19:11:03 +0200
Subject: s390/uv: introduce guest side ultravisor code

The Ultravisor Call Facility (stfle bit 158) defines an API to the
Ultravisor (UV calls), a mini hypervisor located at machine
level. With help of the Ultravisor, KVM will be able to run
"protected" VMs, special VMs whose memory and management data are
unavailable to KVM.

The protected VMs can also request services from the Ultravisor.
The guest api consists of UV calls to share and unshare memory with the
kvm hypervisor.

To enable this feature support PROTECTED_VIRTUALIZATION_GUEST kconfig
option has been introduced.

Co-developed-by: Janosch Frank <frankja@de.ibm.com>
Signed-off-by: Janosch Frank <frankja@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Kconfig | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'arch/s390/Kconfig')

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index b6e3d0653002..4ac8d49e206a 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -837,6 +837,17 @@ config HAVE_PNETID
 
 menu "Virtualization"
 
+config PROTECTED_VIRTUALIZATION_GUEST
+	def_bool n
+	prompt "Protected virtualization guest support"
+	help
+	  Select this option, if you want to be able to run this
+	  kernel as a protected virtualization KVM guest.
+	  Protected virtualization capable machines have a mini hypervisor
+	  located at machine level (an ultravisor). With help of the
+	  Ultravisor, KVM will be able to run "protected" VMs, special
+	  VMs whose memory and management data are unavailable to KVM.
+
 config PFAULT
 	def_bool y
 	prompt "Pseudo page fault support"
-- 
cgit v1.2.3-59-g8ed1b


From 96ca7674ea66e9f0e2cb9f75588d4d16e5abb724 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 8 Apr 2019 23:26:15 +0200
Subject: s390: don't build vdso32 with clang

clang does not support 31 bit object files on s390, so skip
the 32-bit vdso here, and only build it when using gcc to compile
the kernel.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Kconfig         |  3 +++
 arch/s390/kernel/Makefile |  2 +-
 arch/s390/kernel/vdso.c   | 10 +++++-----
 3 files changed, 9 insertions(+), 6 deletions(-)

(limited to 'arch/s390/Kconfig')

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 4ac8d49e206a..566f0b460d21 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -388,6 +388,9 @@ config COMPAT
 	  (and some other stuff like libraries and such) is needed for
 	  executing 31 bit applications.  It is safe to say "Y".
 
+config COMPAT_VDSO
+	def_bool COMPAT && !CC_IS_CLANG
+
 config SYSVIPC_COMPAT
 	def_bool y if COMPAT && SYSVIPC
 
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 8a62c7f72e1b..1222db6d4ee9 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -86,7 +86,7 @@ obj-$(CONFIG_TRACEPOINTS)	+= trace.o
 
 # vdso
 obj-y				+= vdso64/
-obj-$(CONFIG_COMPAT)		+= vdso32/
+obj-$(CONFIG_COMPAT_VDSO)	+= vdso32/
 
 chkbss := head64.o early_nobss.o
 include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index e7920a68a12e..243d8b1185bf 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -29,7 +29,7 @@
 #include <asm/vdso.h>
 #include <asm/facility.h>
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_VDSO
 extern char vdso32_start, vdso32_end;
 static void *vdso32_kbase = &vdso32_start;
 static unsigned int vdso32_pages;
@@ -55,7 +55,7 @@ static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
 
 	vdso_pagelist = vdso64_pagelist;
 	vdso_pages = vdso64_pages;
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_VDSO
 	if (vma->vm_mm->context.compat_mm) {
 		vdso_pagelist = vdso32_pagelist;
 		vdso_pages = vdso32_pages;
@@ -76,7 +76,7 @@ static int vdso_mremap(const struct vm_special_mapping *sm,
 	unsigned long vdso_pages;
 
 	vdso_pages = vdso64_pages;
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_VDSO
 	if (vma->vm_mm->context.compat_mm)
 		vdso_pages = vdso32_pages;
 #endif
@@ -223,7 +223,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 		return 0;
 
 	vdso_pages = vdso64_pages;
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_VDSO
 	mm->context.compat_mm = is_compat_task();
 	if (mm->context.compat_mm)
 		vdso_pages = vdso32_pages;
@@ -280,7 +280,7 @@ static int __init vdso_init(void)
 	int i;
 
 	vdso_init_data(vdso_data);
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_VDSO
 	/* Calculate the size of the 32 bit vDSO */
 	vdso32_pages = ((&vdso32_end - &vdso32_start
 			 + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;
-- 
cgit v1.2.3-59-g8ed1b


From 1a42010cdc26bb7e5912984f3c91b8c6d55f089a Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Tue, 23 Apr 2019 10:53:21 +0200
Subject: s390/mm: convert to the generic get_user_pages_fast code

Define the gup_fast_permitted to check against the asce_limit of the
mm attached to the current task, then replace the s390 specific gup
code with the generic implementation in mm/gup.c.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Kconfig               |   1 +
 arch/s390/include/asm/pgtable.h |  12 ++
 arch/s390/mm/Makefile           |   2 +-
 arch/s390/mm/gup.c              | 291 ----------------------------------------
 4 files changed, 14 insertions(+), 292 deletions(-)
 delete mode 100644 arch/s390/mm/gup.c

(limited to 'arch/s390/Kconfig')

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 566f0b460d21..1c3fcf19c3af 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -149,6 +149,7 @@ config S390
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_GCC_PLUGINS
+	select HAVE_GENERIC_GUP
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZ4
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index d48be9c27df9..394bec31cb97 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1265,6 +1265,18 @@ static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address)
 #define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
 #define pte_unmap(pte) do { } while (0)
 
+static inline bool gup_fast_permitted(unsigned long start, int nr_pages)
+{
+	unsigned long len, end;
+
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+	if (end < start)
+		return false;
+	return end <= current->mm->context.asce_limit;
+}
+#define gup_fast_permitted gup_fast_permitted
+
 #define pfn_pte(pfn,pgprot) mk_pte_phys(__pa((pfn) << PAGE_SHIFT),(pgprot))
 #define pte_pfn(x) (pte_val(x) >> PAGE_SHIFT)
 #define pte_page(x) pfn_to_page(pte_pfn(x))
diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile
index f5880bfd1b0c..3175413186b9 100644
--- a/arch/s390/mm/Makefile
+++ b/arch/s390/mm/Makefile
@@ -4,7 +4,7 @@
 #
 
 obj-y		:= init.o fault.o extmem.o mmap.o vmem.o maccess.o
-obj-y		+= page-states.o gup.o pageattr.o pgtable.o pgalloc.o
+obj-y		+= page-states.o pageattr.o pgtable.o pgalloc.o
 
 obj-$(CONFIG_CMM)		+= cmm.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
deleted file mode 100644
index a5ffcb132191..000000000000
--- a/arch/s390/mm/gup.c
+++ /dev/null
@@ -1,291 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- *  Lockless get_user_pages_fast for s390
- *
- *  Copyright IBM Corp. 2010
- *  Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- */
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/hugetlb.h>
-#include <linux/vmstat.h>
-#include <linux/pagemap.h>
-#include <linux/rwsem.h>
-#include <asm/pgtable.h>
-
-/*
- * The performance critical leaf functions are made noinline otherwise gcc
- * inlines everything into a single function which results in too much
- * register pressure.
- */
-static inline int gup_pte_range(pmd_t pmd, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	struct page *head, *page;
-	unsigned long mask;
-	pte_t *ptep, pte;
-
-	mask = (write ? _PAGE_PROTECT : 0) | _PAGE_INVALID | _PAGE_SPECIAL;
-
-	ptep = pte_offset_map(&pmd, addr);
-	do {
-		pte = *ptep;
-		barrier();
-		/* Similar to the PMD case, NUMA hinting must take slow path */
-		if (pte_protnone(pte))
-			return 0;
-		if ((pte_val(pte) & mask) != 0)
-			return 0;
-		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-		page = pte_page(pte);
-		head = compound_head(page);
-		if (!page_cache_get_speculative(head))
-			return 0;
-		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-			put_page(head);
-			return 0;
-		}
-		VM_BUG_ON_PAGE(compound_head(page) != head, page);
-		pages[*nr] = page;
-		(*nr)++;
-
-	} while (ptep++, addr += PAGE_SIZE, addr != end);
-
-	return 1;
-}
-
-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)
-{
-	struct page *head, *page;
-	unsigned long mask;
-	int refs;
-
-	mask = (write ? _SEGMENT_ENTRY_PROTECT : 0) | _SEGMENT_ENTRY_INVALID;
-	if ((pmd_val(pmd) & mask) != 0)
-		return 0;
-	VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT));
-
-	refs = 0;
-	head = pmd_page(pmd);
-	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	do {
-		VM_BUG_ON(compound_head(page) != head);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
-
-	if (!page_cache_add_speculative(head, refs)) {
-		*nr -= refs;
-		return 0;
-	}
-
-	if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
-		return 0;
-	}
-
-	return 1;
-}
-
-
-static inline int gup_pmd_range(pud_t pud, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long next;
-	pmd_t *pmdp, pmd;
-
-	pmdp = pmd_offset(&pud, addr);
-	do {
-		pmd = *pmdp;
-		barrier();
-		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd))
-			return 0;
-		if (unlikely(pmd_large(pmd))) {
-			/*
-			 * NUMA hinting faults need to be handled in the GUP
-			 * slowpath for accounting purposes and so that they
-			 * can be serialised against THP migration.
-			 */
-			if (pmd_protnone(pmd))
-				return 0;
-			if (!gup_huge_pmd(pmdp, pmd, addr, next,
-					  write, pages, nr))
-				return 0;
-		} else if (!gup_pte_range(pmd, addr, next,
-					  write, pages, nr))
-			return 0;
-	} while (pmdp++, addr = next, addr != end);
-
-	return 1;
-}
-
-static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	struct page *head, *page;
-	unsigned long mask;
-	int refs;
-
-	mask = (write ? _REGION_ENTRY_PROTECT : 0) | _REGION_ENTRY_INVALID;
-	if ((pud_val(pud) & mask) != 0)
-		return 0;
-	VM_BUG_ON(!pfn_valid(pud_pfn(pud)));
-
-	refs = 0;
-	head = pud_page(pud);
-	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	do {
-		VM_BUG_ON_PAGE(compound_head(page) != head, page);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
-
-	if (!page_cache_add_speculative(head, refs)) {
-		*nr -= refs;
-		return 0;
-	}
-
-	if (unlikely(pud_val(pud) != pud_val(*pudp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
-		return 0;
-	}
-
-	return 1;
-}
-
-static inline int gup_pud_range(p4d_t p4d, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long next;
-	pud_t *pudp, pud;
-
-	pudp = pud_offset(&p4d, addr);
-	do {
-		pud = *pudp;
-		barrier();
-		next = pud_addr_end(addr, end);
-		if (pud_none(pud))
-			return 0;
-		if (unlikely(pud_large(pud))) {
-			if (!gup_huge_pud(pudp, pud, addr, next, write, pages,
-					  nr))
-				return 0;
-		} else if (!gup_pmd_range(pud, addr, next, write, pages,
-					  nr))
-			return 0;
-	} while (pudp++, addr = next, addr != end);
-
-	return 1;
-}
-
-static inline int gup_p4d_range(pgd_t pgd, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long next;
-	p4d_t *p4dp, p4d;
-
-	p4dp = p4d_offset(&pgd, addr);
-	do {
-		p4d = *p4dp;
-		barrier();
-		next = p4d_addr_end(addr, end);
-		if (p4d_none(p4d))
-			return 0;
-		if (!gup_pud_range(p4d, addr, next, write, pages, nr))
-			return 0;
-	} while (p4dp++, addr = next, addr != end);
-
-	return 1;
-}
-
-/*
- * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
- * back to the regular GUP.
- * Note a difference with get_user_pages_fast: this always returns the
- * number of pages pinned, 0 if no pages were pinned.
- */
-int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
-			  struct page **pages)
-{
-	struct mm_struct *mm = current->mm;
-	unsigned long addr, len, end;
-	unsigned long next, flags;
-	pgd_t *pgdp, pgd;
-	int nr = 0;
-
-	start &= PAGE_MASK;
-	addr = start;
-	len = (unsigned long) nr_pages << PAGE_SHIFT;
-	end = start + len;
-	if ((end <= start) || (end > mm->context.asce_limit))
-		return 0;
-	/*
-	 * local_irq_save() doesn't prevent pagetable teardown, but does
-	 * prevent the pagetables from being freed on s390.
-	 *
-	 * So long as we atomically load page table pointers versus teardown,
-	 * we can follow the address down to the the page and take a ref on it.
-	 */
-	local_irq_save(flags);
-	pgdp = pgd_offset(mm, addr);
-	do {
-		pgd = *pgdp;
-		barrier();
-		next = pgd_addr_end(addr, end);
-		if (pgd_none(pgd))
-			break;
-		if (!gup_p4d_range(pgd, addr, next, write, pages, &nr))
-			break;
-	} while (pgdp++, addr = next, addr != end);
-	local_irq_restore(flags);
-
-	return nr;
-}
-
-/**
- * get_user_pages_fast() - pin user pages in memory
- * @start:	starting user address
- * @nr_pages:	number of pages from start to pin
- * @write:	whether pages will be written to
- * @pages:	array that receives pointers to the pages pinned.
- *		Should be at least nr_pages long.
- *
- * Attempt to pin user pages in memory without taking mm->mmap_sem.
- * If not successful, it will fall back to taking the lock and
- * calling get_user_pages().
- *
- * Returns number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno.
- */
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
-			struct page **pages)
-{
-	int nr, ret;
-
-	might_sleep();
-	start &= PAGE_MASK;
-	nr = __get_user_pages_fast(start, nr_pages, write, pages);
-	if (nr == nr_pages)
-		return nr;
-
-	/* Try to get the remaining pages with get_user_pages */
-	start += nr << PAGE_SHIFT;
-	pages += nr;
-	ret = get_user_pages_unlocked(start, nr_pages - nr, pages,
-				      write ? FOLL_WRITE : 0);
-	/* Have to be a bit careful with return values */
-	if (nr > 0)
-		ret = (ret < 0) ? nr : ret + nr;
-	return ret;
-}
-- 
cgit v1.2.3-59-g8ed1b


From e23a8020ce4e094e10d717d39a8ce799243bf8c1 Mon Sep 17 00:00:00 2001
From: Philipp Rudo <prudo@linux.ibm.com>
Date: Tue, 26 Feb 2019 10:50:39 +0100
Subject: s390/kexec_file: Signature verification prototype

Add kernel signature verification to kexec_file. The verification is based
on module signature verification and works with kernel images signed via
scripts/sign-file.

Signed-off-by: Philipp Rudo <prudo@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Kconfig                       | 11 +++++
 arch/s390/configs/debug_defconfig       |  1 +
 arch/s390/configs/performance_defconfig |  1 +
 arch/s390/defconfig                     |  1 +
 arch/s390/include/asm/kexec.h           |  1 +
 arch/s390/kernel/kexec_elf.c            |  3 ++
 arch/s390/kernel/kexec_image.c          |  3 ++
 arch/s390/kernel/machine_kexec_file.c   | 74 +++++++++++++++++++++++++++++++++
 8 files changed, 95 insertions(+)

(limited to 'arch/s390/Kconfig')

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 1c3fcf19c3af..21e851b0a989 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -553,6 +553,17 @@ config ARCH_HAS_KEXEC_PURGATORY
 	def_bool y
 	depends on KEXEC_FILE
 
+config KEXEC_VERIFY_SIG
+	bool "Verify kernel signature during kexec_file_load() syscall"
+	depends on KEXEC_FILE && SYSTEM_DATA_VERIFICATION
+	help
+	  This option makes kernel signature verification mandatory for
+	  the kexec_file_load() syscall.
+
+	  In addition to that option, you need to enable signature
+	  verification for the corresponding kernel image type being
+	  loaded in order for this to work.
+
 config ARCH_RANDOM
 	def_bool y
 	prompt "s390 architectural random number generation API"
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 9824c7bad9d4..b0920b35f87b 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -64,6 +64,7 @@ CONFIG_NUMA=y
 CONFIG_PREEMPT=y
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
+CONFIG_KEXEC_VERIFY_SIG=y
 CONFIG_EXPOLINE=y
 CONFIG_EXPOLINE_AUTO=y
 CONFIG_MEMORY_HOTPLUG=y
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 4fcbe5792744..09aa5cb14873 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -65,6 +65,7 @@ CONFIG_NR_CPUS=512
 CONFIG_NUMA=y
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
+CONFIG_KEXEC_VERIFY_SIG=y
 CONFIG_EXPOLINE=y
 CONFIG_EXPOLINE_AUTO=y
 CONFIG_MEMORY_HOTPLUG=y
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 4d58a92b5d97..c59b922cb6c5 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -39,6 +39,7 @@ CONFIG_NR_CPUS=256
 CONFIG_NUMA=y
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
+CONFIG_KEXEC_VERIFY_SIG=y
 CONFIG_CRASH_DUMP=y
 CONFIG_HIBERNATION=y
 CONFIG_PM_DEBUG=y
diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h
index 9ec077b0fb4d..59026899e766 100644
--- a/arch/s390/include/asm/kexec.h
+++ b/arch/s390/include/asm/kexec.h
@@ -65,6 +65,7 @@ struct s390_load_data {
 	size_t memsz;
 };
 
+int s390_verify_sig(const char *kernel, unsigned long kernel_len);
 void *kexec_file_add_components(struct kimage *image,
 				int (*add_kernel)(struct kimage *image,
 						  struct s390_load_data *data));
diff --git a/arch/s390/kernel/kexec_elf.c b/arch/s390/kernel/kexec_elf.c
index 42bcd93f4318..01e45d89b636 100644
--- a/arch/s390/kernel/kexec_elf.c
+++ b/arch/s390/kernel/kexec_elf.c
@@ -125,4 +125,7 @@ static int s390_elf_probe(const char *buf, unsigned long len)
 const struct kexec_file_ops s390_kexec_elf_ops = {
 	.probe = s390_elf_probe,
 	.load = s390_elf_load,
+#ifdef CONFIG_KEXEC_VERIFY_SIG
+	.verify_sig = s390_verify_sig,
+#endif /* CONFIG_KEXEC_VERIFY_SIG */
 };
diff --git a/arch/s390/kernel/kexec_image.c b/arch/s390/kernel/kexec_image.c
index 7281540605b7..c378bbac5b35 100644
--- a/arch/s390/kernel/kexec_image.c
+++ b/arch/s390/kernel/kexec_image.c
@@ -54,4 +54,7 @@ static int s390_image_probe(const char *buf, unsigned long len)
 const struct kexec_file_ops s390_kexec_image_ops = {
 	.probe = s390_image_probe,
 	.load = s390_image_load,
+#ifdef CONFIG_KEXEC_VERIFY_SIG
+	.verify_sig = s390_verify_sig,
+#endif /* CONFIG_KEXEC_VERIFY_SIG */
 };
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index 0e2a5a7a1b7c..e0f6e618e1bf 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -8,7 +8,11 @@
  */
 
 #include <linux/elf.h>
+#include <linux/errno.h>
 #include <linux/kexec.h>
+#include <linux/module.h>
+#include <linux/verification.h>
+#include <asm/ipl.h>
 #include <asm/setup.h>
 
 const struct kexec_file_ops * const kexec_file_loaders[] = {
@@ -17,6 +21,76 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
 	NULL,
 };
 
+#ifdef CONFIG_KEXEC_VERIFY_SIG
+/*
+ * Module signature information block.
+ *
+ * The constituents of the signature section are, in order:
+ *
+ *	- Signer's name
+ *	- Key identifier
+ *	- Signature data
+ *	- Information block
+ */
+struct module_signature {
+	u8	algo;		/* Public-key crypto algorithm [0] */
+	u8	hash;		/* Digest algorithm [0] */
+	u8	id_type;	/* Key identifier type [PKEY_ID_PKCS7] */
+	u8	signer_len;	/* Length of signer's name [0] */
+	u8	key_id_len;	/* Length of key identifier [0] */
+	u8	__pad[3];
+	__be32	sig_len;	/* Length of signature data */
+};
+
+#define PKEY_ID_PKCS7 2
+
+int s390_verify_sig(const char *kernel, unsigned long kernel_len)
+{
+	const unsigned long marker_len = sizeof(MODULE_SIG_STRING) - 1;
+	struct module_signature *ms;
+	unsigned long sig_len;
+
+	/* Skip signature verification when not secure IPLed. */
+	if (!ipl_secure_flag)
+		return 0;
+
+	if (marker_len > kernel_len)
+		return -EKEYREJECTED;
+
+	if (memcmp(kernel + kernel_len - marker_len, MODULE_SIG_STRING,
+		   marker_len))
+		return -EKEYREJECTED;
+	kernel_len -= marker_len;
+
+	ms = (void *)kernel + kernel_len - sizeof(*ms);
+	kernel_len -= sizeof(*ms);
+
+	sig_len = be32_to_cpu(ms->sig_len);
+	if (sig_len >= kernel_len)
+		return -EKEYREJECTED;
+	kernel_len -= sig_len;
+
+	if (ms->id_type != PKEY_ID_PKCS7)
+		return -EKEYREJECTED;
+
+	if (ms->algo != 0 ||
+	    ms->hash != 0 ||
+	    ms->signer_len != 0 ||
+	    ms->key_id_len != 0 ||
+	    ms->__pad[0] != 0 ||
+	    ms->__pad[1] != 0 ||
+	    ms->__pad[2] != 0) {
+		return -EBADMSG;
+	}
+
+	return verify_pkcs7_signature(kernel, kernel_len,
+				      kernel + kernel_len, sig_len,
+				      VERIFY_USE_PLATFORM_KEYRING,
+				      VERIFYING_MODULE_SIGNATURE,
+				      NULL, NULL);
+}
+#endif /* CONFIG_KEXEC_VERIFY_SIG */
+
 static int kexec_file_update_purgatory(struct kimage *image,
 				       struct s390_load_data *data)
 {
-- 
cgit v1.2.3-59-g8ed1b


From 805bc0bc238f7209fca5e39c152b0d3c12046ac9 Mon Sep 17 00:00:00 2001
From: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Date: Sun, 3 Feb 2019 21:35:45 +0100
Subject: s390/kernel: build a relocatable kernel

This patch adds support for building a relocatable kernel with -fPIE.
The kernel will be relocated to 0 early in the boot process.

Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Reviewed-by: Philipp Rudo <prudo@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Kconfig                        | 13 ++++++++
 arch/s390/Makefile                       |  4 +++
 arch/s390/boot/Makefile                  |  1 +
 arch/s390/boot/compressed/decompressor.h |  3 ++
 arch/s390/boot/machine_kexec_reloc.c     |  2 ++
 arch/s390/boot/startup.c                 | 27 ++++++++++++++++
 arch/s390/include/asm/kexec.h            |  2 ++
 arch/s390/kernel/Makefile                |  2 +-
 arch/s390/kernel/machine_kexec_file.c    | 44 ++------------------------
 arch/s390/kernel/machine_kexec_reloc.c   | 53 ++++++++++++++++++++++++++++++++
 arch/s390/kernel/vmlinux.lds.S           | 15 +++++++++
 11 files changed, 124 insertions(+), 42 deletions(-)
 create mode 100644 arch/s390/boot/machine_kexec_reloc.c
 create mode 100644 arch/s390/kernel/machine_kexec_reloc.c

(limited to 'arch/s390/Kconfig')

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 21e851b0a989..4c99e4f5f366 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -624,6 +624,19 @@ config EXPOLINE_FULL
 
 endchoice
 
+config RELOCATABLE
+	bool "Build a relocatable kernel"
+	select MODULE_REL_CRCS if MODVERSIONS
+	default y
+	help
+	  This builds a kernel image that retains relocation information
+	  so it can be loaded at an arbitrary address.
+	  The kernel is linked as a position-independent executable (PIE)
+	  and contains dynamic relocations which are processed early in the
+	  bootup process.
+	  The relocations make the kernel image about 15% larger (compressed
+	  10%), but are discarded at runtime.
+
 endmenu
 
 menu "Memory setup"
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 9c079a506325..54b8a12d64e8 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -16,6 +16,10 @@ KBUILD_AFLAGS_MODULE += -fPIC
 KBUILD_CFLAGS_MODULE += -fPIC
 KBUILD_AFLAGS	+= -m64
 KBUILD_CFLAGS	+= -m64
+ifeq ($(CONFIG_RELOCATABLE),y)
+KBUILD_CFLAGS	+= -fPIE
+LDFLAGS_vmlinux	:= -pie
+endif
 aflags_dwarf	:= -Wa,-gdwarf-2
 KBUILD_AFLAGS_DECOMPRESSOR := -m64 -D__ASSEMBLY__
 KBUILD_AFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),$(aflags_dwarf))
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index c1993c57300f..4df43e83363a 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -32,6 +32,7 @@ obj-y	:= head.o als.o startup.o mem_detect.o ipl_parm.o ipl_report.o
 obj-y	+= string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o
 obj-y	+= ctype.o
 obj-$(CONFIG_PROTECTED_VIRTUALIZATION_GUEST)	+= uv.o
+obj-$(CONFIG_RELOCATABLE)	+= machine_kexec_reloc.o
 targets	:= bzImage startup.a section_cmp.boot.data section_cmp.boot.preserved.data $(obj-y)
 subdir-	:= compressed
 
diff --git a/arch/s390/boot/compressed/decompressor.h b/arch/s390/boot/compressed/decompressor.h
index 424cf524aac1..c15eb7114d83 100644
--- a/arch/s390/boot/compressed/decompressor.h
+++ b/arch/s390/boot/compressed/decompressor.h
@@ -19,6 +19,9 @@ struct vmlinux_info {
 	unsigned long bootdata_size;
 	unsigned long bootdata_preserved_off;
 	unsigned long bootdata_preserved_size;
+	unsigned long dynsym_start;
+	unsigned long rela_dyn_start;
+	unsigned long rela_dyn_end;
 };
 
 extern char _vmlinux_info[];
diff --git a/arch/s390/boot/machine_kexec_reloc.c b/arch/s390/boot/machine_kexec_reloc.c
new file mode 100644
index 000000000000..b7a5d0f72097
--- /dev/null
+++ b/arch/s390/boot/machine_kexec_reloc.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../kernel/machine_kexec_reloc.c"
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 90898976a941..b7d6a76cb5e9 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/string.h>
+#include <linux/elf.h>
 #include <asm/setup.h>
+#include <asm/kexec.h>
 #include <asm/sclp.h>
 #include <asm/uv.h>
 #include "compressed/decompressor.h"
@@ -47,6 +49,29 @@ static void copy_bootdata(void)
 	memcpy((void *)vmlinux.bootdata_preserved_off, __boot_data_preserved_start, vmlinux.bootdata_preserved_size);
 }
 
+static void handle_relocs(unsigned long offset)
+{
+	Elf64_Rela *rela_start, *rela_end, *rela;
+	int r_type, r_sym, rc;
+	Elf64_Addr loc, val;
+	Elf64_Sym *dynsym;
+
+	rela_start = (Elf64_Rela *) vmlinux.rela_dyn_start;
+	rela_end = (Elf64_Rela *) vmlinux.rela_dyn_end;
+	dynsym = (Elf64_Sym *) vmlinux.dynsym_start;
+	for (rela = rela_start; rela < rela_end; rela++) {
+		loc = rela->r_offset + offset;
+		val = rela->r_addend + offset;
+		r_sym = ELF64_R_SYM(rela->r_info);
+		if (r_sym)
+			val += dynsym[r_sym].st_value;
+		r_type = ELF64_R_TYPE(rela->r_info);
+		rc = arch_kexec_do_relocs(r_type, (void *) loc, val, 0);
+		if (rc)
+			error("Unknown relocation type");
+	}
+}
+
 void startup_kernel(void)
 {
 	unsigned long safe_addr;
@@ -67,5 +92,7 @@ void startup_kernel(void)
 		memmove((void *)vmlinux.default_lma, img, vmlinux.image_size);
 	}
 	copy_bootdata();
+	if (IS_ENABLED(CONFIG_RELOCATABLE))
+		handle_relocs(0);
 	vmlinux.entry();
 }
diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h
index 305d3465574f..ea398a05f643 100644
--- a/arch/s390/include/asm/kexec.h
+++ b/arch/s390/include/asm/kexec.h
@@ -71,6 +71,8 @@ int s390_verify_sig(const char *kernel, unsigned long kernel_len);
 void *kexec_file_add_components(struct kimage *image,
 				int (*add_kernel)(struct kimage *image,
 						  struct s390_load_data *data));
+int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val,
+			 unsigned long addr);
 
 extern const struct kexec_file_ops s390_kexec_image_ops;
 extern const struct kexec_file_ops s390_kexec_elf_ops;
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index d28acd7ba81e..19425605a83d 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -51,7 +51,7 @@ obj-y	+= debug.o irq.o ipl.o dis.o diag.o vdso.o early_nobss.o
 obj-y	+= sysinfo.o lgr.o os_info.o machine_kexec.o pgm_check.o
 obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
 obj-y	+= entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o
-obj-y	+= nospec-branch.o ipl_vmparm.o
+obj-y	+= nospec-branch.o ipl_vmparm.o machine_kexec_reloc.o
 
 extra-y				+= head64.o vmlinux.lds
 
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index 48cab9600ed9..42c23a5c8229 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -290,7 +290,7 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
 				     const Elf_Shdr *symtab)
 {
 	Elf_Rela *relas;
-	int i;
+	int i, r_type;
 
 	relas = (void *)pi->ehdr + relsec->sh_offset;
 
@@ -324,46 +324,8 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
 
 		addr = section->sh_addr + relas[i].r_offset;
 
-		switch (ELF64_R_TYPE(relas[i].r_info)) {
-		case R_390_8:		/* Direct 8 bit.   */
-			*(u8 *)loc = val;
-			break;
-		case R_390_12:		/* Direct 12 bit.  */
-			*(u16 *)loc &= 0xf000;
-			*(u16 *)loc |= val & 0xfff;
-			break;
-		case R_390_16:		/* Direct 16 bit.  */
-			*(u16 *)loc = val;
-			break;
-		case R_390_20:		/* Direct 20 bit.  */
-			*(u32 *)loc &= 0xf00000ff;
-			*(u32 *)loc |= (val & 0xfff) << 16;	/* DL */
-			*(u32 *)loc |= (val & 0xff000) >> 4;	/* DH */
-			break;
-		case R_390_32:		/* Direct 32 bit.  */
-			*(u32 *)loc = val;
-			break;
-		case R_390_64:		/* Direct 64 bit.  */
-			*(u64 *)loc = val;
-			break;
-		case R_390_PC16:	/* PC relative 16 bit.	*/
-			*(u16 *)loc = (val - addr);
-			break;
-		case R_390_PC16DBL:	/* PC relative 16 bit shifted by 1.  */
-			*(u16 *)loc = (val - addr) >> 1;
-			break;
-		case R_390_PC32DBL:	/* PC relative 32 bit shifted by 1.  */
-			*(u32 *)loc = (val - addr) >> 1;
-			break;
-		case R_390_PC32:	/* PC relative 32 bit.	*/
-			*(u32 *)loc = (val - addr);
-			break;
-		case R_390_PC64:	/* PC relative 64 bit.	*/
-			*(u64 *)loc = (val - addr);
-			break;
-		default:
-			break;
-		}
+		r_type = ELF64_R_TYPE(relas[i].r_info);
+		arch_kexec_do_relocs(r_type, loc, val, addr);
 	}
 	return 0;
 }
diff --git a/arch/s390/kernel/machine_kexec_reloc.c b/arch/s390/kernel/machine_kexec_reloc.c
new file mode 100644
index 000000000000..1dded39239f8
--- /dev/null
+++ b/arch/s390/kernel/machine_kexec_reloc.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/elf.h>
+
+int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val,
+			 unsigned long addr)
+{
+	switch (r_type) {
+	case R_390_NONE:
+		break;
+	case R_390_8:		/* Direct 8 bit.   */
+		*(u8 *)loc = val;
+		break;
+	case R_390_12:		/* Direct 12 bit.  */
+		*(u16 *)loc &= 0xf000;
+		*(u16 *)loc |= val & 0xfff;
+		break;
+	case R_390_16:		/* Direct 16 bit.  */
+		*(u16 *)loc = val;
+		break;
+	case R_390_20:		/* Direct 20 bit.  */
+		*(u32 *)loc &= 0xf00000ff;
+		*(u32 *)loc |= (val & 0xfff) << 16;	/* DL */
+		*(u32 *)loc |= (val & 0xff000) >> 4;	/* DH */
+		break;
+	case R_390_32:		/* Direct 32 bit.  */
+		*(u32 *)loc = val;
+		break;
+	case R_390_64:		/* Direct 64 bit.  */
+		*(u64 *)loc = val;
+		break;
+	case R_390_PC16:	/* PC relative 16 bit.	*/
+		*(u16 *)loc = (val - addr);
+		break;
+	case R_390_PC16DBL:	/* PC relative 16 bit shifted by 1.  */
+		*(u16 *)loc = (val - addr) >> 1;
+		break;
+	case R_390_PC32DBL:	/* PC relative 32 bit shifted by 1.  */
+		*(u32 *)loc = (val - addr) >> 1;
+		break;
+	case R_390_PC32:	/* PC relative 32 bit.	*/
+		*(u32 *)loc = (val - addr);
+		break;
+	case R_390_PC64:	/* PC relative 64 bit.	*/
+		*(u64 *)loc = (val - addr);
+		break;
+	case R_390_RELATIVE:
+		*(unsigned long *) loc = val;
+		break;
+	default:
+		return 1;
+	}
+	return 0;
+}
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 6ef9c62bb01b..49d55327de0b 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -144,6 +144,18 @@ SECTIONS
 	INIT_DATA_SECTION(0x100)
 
 	PERCPU_SECTION(0x100)
+
+	.dynsym ALIGN(8) : {
+		__dynsym_start = .;
+		*(.dynsym)
+		__dynsym_end = .;
+	}
+	.rela.dyn ALIGN(8) : {
+		__rela_dyn_start = .;
+		*(.rela*)
+		__rela_dyn_end = .;
+	}
+
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;		/* freed after init ends here */
 
@@ -165,6 +177,9 @@ SECTIONS
 		QUAD(__boot_data_preserved_start)		/* bootdata_preserved_off */
 		QUAD(__boot_data_preserved_end -
 		     __boot_data_preserved_start)		/* bootdata_preserved_size */
+		QUAD(__dynsym_start)				/* dynsym_start */
+		QUAD(__rela_dyn_start)				/* rela_dyn_start */
+		QUAD(__rela_dyn_end)				/* rela_dyn_end */
 	} :NONE
 
 	/* Debugging sections.	*/
-- 
cgit v1.2.3-59-g8ed1b


From b2d24b97b2a9691351920e700bfda4368c177232 Mon Sep 17 00:00:00 2001
From: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Date: Sun, 3 Feb 2019 21:37:20 +0100
Subject: s390/kernel: add support for kernel address space layout
 randomization (KASLR)

This patch adds support for relocating the kernel to a random address.
The random kernel offset is obtained from cpacf, using either TRNG, PRNO,
or KMC_PRNG, depending on supported MSA level.

KERNELOFFSET is added to vmcoreinfo, for crash --kaslr support.

Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Reviewed-by: Philipp Rudo <prudo@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Kconfig                |  10 +++
 arch/s390/boot/Makefile          |   1 +
 arch/s390/boot/boot.h            |   3 +
 arch/s390/boot/ipl_parm.c        |  15 +++-
 arch/s390/boot/kaslr.c           | 144 +++++++++++++++++++++++++++++++++++++++
 arch/s390/boot/startup.c         |  31 ++++++++-
 arch/s390/include/asm/setup.h    |   6 ++
 arch/s390/kernel/machine_kexec.c |   1 +
 arch/s390/kernel/setup.c         |   1 +
 9 files changed, 207 insertions(+), 5 deletions(-)
 create mode 100644 arch/s390/boot/kaslr.c

(limited to 'arch/s390/Kconfig')

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 4c99e4f5f366..8c15392ee985 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -637,6 +637,16 @@ config RELOCATABLE
 	  The relocations make the kernel image about 15% larger (compressed
 	  10%), but are discarded at runtime.
 
+config RANDOMIZE_BASE
+	bool "Randomize the address of the kernel image (KASLR)"
+	depends on RELOCATABLE
+	default y
+	help
+	  In support of Kernel Address Space Layout Randomization (KASLR),
+	  this randomizes the address at which the kernel image is loaded,
+	  as a security feature that deters exploit attempts relying on
+	  knowledge of the location of kernel internals.
+
 endmenu
 
 menu "Memory setup"
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index 88932c25ad26..cb40317dc3f7 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -33,6 +33,7 @@ obj-y	+= string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o
 obj-y	+= ctype.o text_dma.o
 obj-$(CONFIG_PROTECTED_VIRTUALIZATION_GUEST)	+= uv.o
 obj-$(CONFIG_RELOCATABLE)	+= machine_kexec_reloc.o
+obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr.o
 targets	:= bzImage startup.a section_cmp.boot.data section_cmp.boot.preserved.data $(obj-y)
 subdir-	:= compressed
 
diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h
index ca395fcff15e..ad57c2205a71 100644
--- a/arch/s390/boot/boot.h
+++ b/arch/s390/boot/boot.h
@@ -9,6 +9,9 @@ void setup_boot_command_line(void);
 void parse_boot_command_line(void);
 void setup_memory_end(void);
 void print_missing_facilities(void);
+unsigned long get_random_base(unsigned long safe_addr);
+
+extern int kaslr_enabled;
 
 unsigned long read_ipl_report(unsigned long safe_offset);
 
diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c
index 96777092fb14..b49bd97d33af 100644
--- a/arch/s390/boot/ipl_parm.c
+++ b/arch/s390/boot/ipl_parm.c
@@ -18,6 +18,8 @@ unsigned long __bootdata(memory_end);
 int __bootdata(memory_end_set);
 int __bootdata(noexec_disabled);
 
+int kaslr_enabled __section(.data);
+
 static inline int __diag308(unsigned long subcode, void *addr)
 {
 	register unsigned long _addr asm("0") = (unsigned long)addr;
@@ -214,6 +216,7 @@ void parse_boot_command_line(void)
 	char *args;
 	int rc;
 
+	kaslr_enabled = IS_ENABLED(CONFIG_RANDOMIZE_BASE);
 	args = strcpy(command_line_buf, early_command_line);
 	while (*args) {
 		args = next_arg(args, &param, &val);
@@ -231,15 +234,21 @@ void parse_boot_command_line(void)
 
 		if (!strcmp(param, "facilities"))
 			modify_fac_list(val);
+
+		if (!strcmp(param, "nokaslr"))
+			kaslr_enabled = 0;
 	}
 }
 
 void setup_memory_end(void)
 {
 #ifdef CONFIG_CRASH_DUMP
-	if (!OLDMEM_BASE && ipl_block_valid &&
-	    ipl_block.pb0_hdr.pbt == IPL_PBT_FCP &&
-	    ipl_block.fcp.opt == IPL_PB0_FCP_OPT_DUMP) {
+	if (OLDMEM_BASE) {
+		kaslr_enabled = 0;
+	} else if (ipl_block_valid &&
+		   ipl_block.pb0_hdr.pbt == IPL_PBT_FCP &&
+		   ipl_block.fcp.opt == IPL_PB0_FCP_OPT_DUMP) {
+		kaslr_enabled = 0;
 		if (!sclp_early_get_hsa_size(&memory_end) && memory_end)
 			memory_end_set = 1;
 	}
diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c
new file mode 100644
index 000000000000..3bdd8132e56b
--- /dev/null
+++ b/arch/s390/boot/kaslr.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 2019
+ */
+#include <asm/mem_detect.h>
+#include <asm/cpacf.h>
+#include <asm/timex.h>
+#include <asm/sclp.h>
+#include "compressed/decompressor.h"
+
+#define PRNG_MODE_TDES	 1
+#define PRNG_MODE_SHA512 2
+#define PRNG_MODE_TRNG	 3
+
+struct prno_parm {
+	u32 res;
+	u32 reseed_counter;
+	u64 stream_bytes;
+	u8  V[112];
+	u8  C[112];
+};
+
+struct prng_parm {
+	u8  parm_block[32];
+	u32 reseed_counter;
+	u64 byte_counter;
+};
+
+static int check_prng(void)
+{
+	if (!cpacf_query_func(CPACF_KMC, CPACF_KMC_PRNG)) {
+		sclp_early_printk("KASLR disabled: CPU has no PRNG\n");
+		return 0;
+	}
+	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG))
+		return PRNG_MODE_TRNG;
+	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_SHA512_DRNG_GEN))
+		return PRNG_MODE_SHA512;
+	else
+		return PRNG_MODE_TDES;
+}
+
+static unsigned long get_random(unsigned long limit)
+{
+	struct prng_parm prng = {
+		/* initial parameter block for tdes mode, copied from libica */
+		.parm_block = {
+			0x0F, 0x2B, 0x8E, 0x63, 0x8C, 0x8E, 0xD2, 0x52,
+			0x64, 0xB7, 0xA0, 0x7B, 0x75, 0x28, 0xB8, 0xF4,
+			0x75, 0x5F, 0xD2, 0xA6, 0x8D, 0x97, 0x11, 0xFF,
+			0x49, 0xD8, 0x23, 0xF3, 0x7E, 0x21, 0xEC, 0xA0
+		},
+	};
+	unsigned long seed, random;
+	struct prno_parm prno;
+	__u64 entropy[4];
+	int mode, i;
+
+	mode = check_prng();
+	seed = get_tod_clock_fast();
+	switch (mode) {
+	case PRNG_MODE_TRNG:
+		cpacf_trng(NULL, 0, (u8 *) &random, sizeof(random));
+		break;
+	case PRNG_MODE_SHA512:
+		cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED, &prno, NULL, 0,
+			   (u8 *) &seed, sizeof(seed));
+		cpacf_prno(CPACF_PRNO_SHA512_DRNG_GEN, &prno, (u8 *) &random,
+			   sizeof(random), NULL, 0);
+		break;
+	case PRNG_MODE_TDES:
+		/* add entropy */
+		*(unsigned long *) prng.parm_block ^= seed;
+		for (i = 0; i < 16; i++) {
+			cpacf_kmc(CPACF_KMC_PRNG, prng.parm_block,
+				  (char *) entropy, (char *) entropy,
+				  sizeof(entropy));
+			memcpy(prng.parm_block, entropy, sizeof(entropy));
+		}
+		random = seed;
+		cpacf_kmc(CPACF_KMC_PRNG, prng.parm_block, (u8 *) &random,
+			  (u8 *) &random, sizeof(random));
+		break;
+	default:
+		random = 0;
+	}
+	return random % limit;
+}
+
+unsigned long get_random_base(unsigned long safe_addr)
+{
+	unsigned long base, start, end, kernel_size;
+	unsigned long block_sum, offset;
+	int i;
+
+	if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE) {
+		if (safe_addr < INITRD_START + INITRD_SIZE)
+			safe_addr = INITRD_START + INITRD_SIZE;
+	}
+	safe_addr = ALIGN(safe_addr, THREAD_SIZE);
+
+	kernel_size = vmlinux.image_size + vmlinux.bss_size;
+	block_sum = 0;
+	for_each_mem_detect_block(i, &start, &end) {
+		if (memory_end_set) {
+			if (start >= memory_end)
+				break;
+			if (end > memory_end)
+				end = memory_end;
+		}
+		if (end - start < kernel_size)
+			continue;
+		block_sum += end - start - kernel_size;
+	}
+	if (!block_sum) {
+		sclp_early_printk("KASLR disabled: not enough memory\n");
+		return 0;
+	}
+
+	base = get_random(block_sum);
+	if (base == 0)
+		return 0;
+	if (base < safe_addr)
+		base = safe_addr;
+	block_sum = offset = 0;
+	for_each_mem_detect_block(i, &start, &end) {
+		if (memory_end_set) {
+			if (start >= memory_end)
+				break;
+			if (end > memory_end)
+				end = memory_end;
+		}
+		if (end - start < kernel_size)
+			continue;
+		block_sum += end - start - kernel_size;
+		if (base <= block_sum) {
+			base = start + base - offset;
+			base = ALIGN_DOWN(base, THREAD_SIZE);
+			break;
+		}
+		offset = block_sum;
+	}
+	return base;
+}
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index e3f339d248ce..4401e992bda1 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -12,6 +12,7 @@
 
 extern char __boot_data_start[], __boot_data_end[];
 extern char __boot_data_preserved_start[], __boot_data_preserved_end[];
+unsigned long __bootdata_preserved(__kaslr_offset);
 
 /*
  * Some code and data needs to stay below 2 GB, even when the kernel would be
@@ -113,6 +114,7 @@ static void handle_relocs(unsigned long offset)
 
 void startup_kernel(void)
 {
+	unsigned long random_lma;
 	unsigned long safe_addr;
 	void *img;
 
@@ -126,12 +128,37 @@ void startup_kernel(void)
 	parse_boot_command_line();
 	setup_memory_end();
 	detect_memory();
+
+	random_lma = __kaslr_offset = 0;
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_enabled) {
+		random_lma = get_random_base(safe_addr);
+		if (random_lma) {
+			__kaslr_offset = random_lma - vmlinux.default_lma;
+			img = (void *)vmlinux.default_lma;
+			vmlinux.default_lma += __kaslr_offset;
+			vmlinux.entry += __kaslr_offset;
+			vmlinux.bootdata_off += __kaslr_offset;
+			vmlinux.bootdata_preserved_off += __kaslr_offset;
+			vmlinux.rela_dyn_start += __kaslr_offset;
+			vmlinux.rela_dyn_end += __kaslr_offset;
+			vmlinux.dynsym_start += __kaslr_offset;
+		}
+	}
+
 	if (!IS_ENABLED(CONFIG_KERNEL_UNCOMPRESSED)) {
 		img = decompress_kernel();
 		memmove((void *)vmlinux.default_lma, img, vmlinux.image_size);
-	}
+	} else if (__kaslr_offset)
+		memcpy((void *)vmlinux.default_lma, img, vmlinux.image_size);
+
 	copy_bootdata();
 	if (IS_ENABLED(CONFIG_RELOCATABLE))
-		handle_relocs(0);
+		handle_relocs(__kaslr_offset);
+
+	if (__kaslr_offset) {
+		/* Clear non-relocated kernel */
+		if (IS_ENABLED(CONFIG_KERNEL_UNCOMPRESSED))
+			memset(img, 0, vmlinux.image_size);
+	}
 	vmlinux.entry();
 }
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index d202756d6291..925889d360c1 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -147,6 +147,12 @@ extern void (*_machine_restart)(char *command);
 extern void (*_machine_halt)(void);
 extern void (*_machine_power_off)(void);
 
+extern unsigned long __kaslr_offset;
+static inline unsigned long kaslr_offset(void)
+{
+	return __kaslr_offset;
+}
+
 #else /* __ASSEMBLY__ */
 
 #define IPL_DEVICE	(IPL_DEVICE_OFFSET)
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 4b998d639c32..e2ba7b7f574e 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -255,6 +255,7 @@ void arch_crash_save_vmcoreinfo(void)
 	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
 	vmcoreinfo_append_str("SDMA=%lx\n", __sdma);
 	vmcoreinfo_append_str("EDMA=%lx\n", __edma);
+	vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
 }
 
 void machine_shutdown(void)
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 4ccaf5ed96ee..64e4bc9dd130 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -108,6 +108,7 @@ unsigned long __bootdata_preserved(__stext_dma);
 unsigned long __bootdata_preserved(__etext_dma);
 unsigned long __bootdata_preserved(__sdma);
 unsigned long __bootdata_preserved(__edma);
+unsigned long __bootdata_preserved(__kaslr_offset);
 
 unsigned long VMALLOC_START;
 EXPORT_SYMBOL(VMALLOC_START);
-- 
cgit v1.2.3-59-g8ed1b


From c263a4e990b7296b074e33aa077239a0a28a818e Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 15 Apr 2019 10:35:51 +0200
Subject: s390: only build for new CPUs with clang

llvm does does not understand -march=z9-109 and older target
specifiers, so disable the respective Kconfig settings and
the logic to make the boot code work on old systems when
building with clang.

Part of the early boot code is normally compiled with -march=z900
for maximum compatibility. This also has to get changed with
clang to the oldest supported ISA, which is -march=z10 here.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
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/boot/Makefile | 18 ++++++++++++------
 2 files changed, 18 insertions(+), 6 deletions(-)

(limited to 'arch/s390/Kconfig')

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 8c15392ee985..380d13df4411 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -241,6 +241,7 @@ choice
 
 config MARCH_Z900
 	bool "IBM zSeries model z800 and z900"
+	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z900_FEATURES
 	help
 	  Select this to enable optimizations for model z800/z900 (2064 and
@@ -249,6 +250,7 @@ config MARCH_Z900
 
 config MARCH_Z990
 	bool "IBM zSeries model z890 and z990"
+	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z990_FEATURES
 	help
 	  Select this to enable optimizations for model z890/z990 (2084 and
@@ -257,6 +259,7 @@ config MARCH_Z990
 
 config MARCH_Z9_109
 	bool "IBM System z9"
+	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z9_109_FEATURES
 	help
 	  Select this to enable optimizations for IBM System z9 (2094 and
@@ -348,12 +351,15 @@ config TUNE_DEFAULT
 
 config TUNE_Z900
 	bool "IBM zSeries model z800 and z900"
+	depends on !CC_IS_CLANG
 
 config TUNE_Z990
 	bool "IBM zSeries model z890 and z990"
+	depends on !CC_IS_CLANG
 
 config TUNE_Z9_109
 	bool "IBM System z9"
+	depends on !CC_IS_CLANG
 
 config TUNE_Z10
 	bool "IBM System z10"
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index cb40317dc3f7..c51496bbac19 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -12,18 +12,24 @@ KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
 KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
 
 #
-# Use -march=z900 for als.c to be able to print an error
+# Use minimum architecture for als.c to be able to print an error
 # message if the kernel is started on a machine which is too old
 #
-ifneq ($(CC_FLAGS_MARCH),-march=z900)
+ifndef CONFIG_CC_IS_CLANG
+CC_FLAGS_MARCH_MINIMUM := -march=z900
+else
+CC_FLAGS_MARCH_MINIMUM := -march=z10
+endif
+
+ifneq ($(CC_FLAGS_MARCH),$(CC_FLAGS_MARCH_MINIMUM))
 AFLAGS_REMOVE_head.o		+= $(CC_FLAGS_MARCH)
-AFLAGS_head.o			+= -march=z900
+AFLAGS_head.o			+= $(CC_FLAGS_MARCH_MINIMUM)
 AFLAGS_REMOVE_mem.o		+= $(CC_FLAGS_MARCH)
-AFLAGS_mem.o			+= -march=z900
+AFLAGS_mem.o			+= $(CC_FLAGS_MARCH_MINIMUM)
 CFLAGS_REMOVE_als.o		+= $(CC_FLAGS_MARCH)
-CFLAGS_als.o			+= -march=z900
+CFLAGS_als.o			+= $(CC_FLAGS_MARCH_MINIMUM)
 CFLAGS_REMOVE_sclp_early_core.o	+= $(CC_FLAGS_MARCH)
-CFLAGS_sclp_early_core.o	+= -march=z900
+CFLAGS_sclp_early_core.o	+= $(CC_FLAGS_MARCH_MINIMUM)
 endif
 
 CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char
-- 
cgit v1.2.3-59-g8ed1b


From 964d06b4ed212d85ff589a9438baeb6c4fff3272 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 15 Apr 2019 10:35:53 +0200
Subject: s390: drop CONFIG_VIRT_TO_BUS

VIRT_TO_BUS is only used for legacy device PCI and ISA drivers using
virt_to_bus() instead of the streaming DMA mapping API, and the
remaining drivers generally don't work on 64-bit architectures.

Two of these drivers also cause a build warning on s390, so instead
of trying to fix that, let's just disable the option as we do on
most architectures now.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Kconfig | 1 -
 1 file changed, 1 deletion(-)

(limited to 'arch/s390/Kconfig')

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 380d13df4411..0ad0d204404a 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -189,7 +189,6 @@ config S390
 	select TTY
 	select VIRT_CPU_ACCOUNTING
 	select ARCH_HAS_SCALED_CPUTIME
-	select VIRT_TO_BUS
 	select HAVE_NMI
 
 
-- 
cgit v1.2.3-59-g8ed1b