Merge tag 's390-6.9-2' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull more s390 updates from Heiko Carstens:

 - Various virtual vs physical address usage fixes

 - Add new bitwise types and helper functions and use them in s390
   specific drivers and code to make it easier to find virtual vs
   physical address usage bugs.

   Right now virtual and physical addresses are identical for s390,
   except for module, vmalloc, and similar areas. This will be changed,
   hopefully with the next merge window, so that e.g. the kernel image
   and modules will be located close to each other, allowing for direct
   branches and also for some other simplifications.

   As a prerequisite this requires to fix all misuses of virtual and
   physical addresses. As it turned out people are so used to the
   concept that virtual and physical addresses are the same, that new
   bugs got added to code which was already fixed. In order to avoid
   that even more code gets merged which adds such bugs add and use new
   bitwise types, so that sparse can be used to find such usage bugs.

   Most likely the new types can go away again after some time

 - Provide a simple ARCH_HAS_DEBUG_VIRTUAL implementation

 - Fix kprobe branch handling: if an out-of-line single stepped relative
   branch instruction has a target address within a certain address area
   in the entry code, the program check handler may incorrectly execute
   cleanup code as if KVM code was executed, leading to crashes

 - Fix reference counting of zcrypt card objects

 - Various other small fixes and cleanups

* tag 's390-6.9-2' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (41 commits)
  s390/entry: compare gmap asce to determine guest/host fault
  s390/entry: remove OUTSIDE macro
  s390/entry: add CIF_SIE flag and remove sie64a() address check
  s390/cio: use while (i--) pattern to clean up
  s390/raw3270: make class3270 constant
  s390/raw3270: improve raw3270_init() readability
  s390/tape: make tape_class constant
  s390/vmlogrdr: make vmlogrdr_class constant
  s390/vmur: make vmur_class constant
  s390/zcrypt: make zcrypt_class constant
  s390/mm: provide simple ARCH_HAS_DEBUG_VIRTUAL support
  s390/vfio_ccw_cp: use new address translation helpers
  s390/iucv: use new address translation helpers
  s390/ctcm: use new address translation helpers
  s390/lcs: use new address translation helpers
  s390/qeth: use new address translation helpers
  s390/zfcp: use new address translation helpers
  s390/tape: fix virtual vs physical address confusion
  s390/3270: use new address translation helpers
  s390/3215: use new address translation helpers
  ...

Author: torvalds

arch/s390/Kconfig

@@ -63,6 +63,7 @@ config S390
 	select ARCH_ENABLE_MEMORY_HOTREMOVE
 	select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
 	select ARCH_HAS_CURRENT_STACK_POINTER
+	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEBUG_VM_PGTABLE
 	select ARCH_HAS_DEBUG_WX
 	select ARCH_HAS_DEVMEM_IS_ALLOWED

arch/s390/Makefile

@@ -29,6 +29,7 @@ KBUILD_AFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),$(aflags_dwarf))
 endif
 KBUILD_CFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -O2 -mpacked-stack
 KBUILD_CFLAGS_DECOMPRESSOR += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
+KBUILD_CFLAGS_DECOMPRESSOR += -D__DECOMPRESSOR
 KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float -mbackchain
 KBUILD_CFLAGS_DECOMPRESSOR += -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS_DECOMPRESSOR += -ffreestanding

arch/s390/configs/debug_defconfig

@@ -810,6 +810,7 @@ CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_VM=y
 CONFIG_DEBUG_VM_PGFLAGS=y
+CONFIG_DEBUG_VIRTUAL=y
 CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m
 CONFIG_DEBUG_PER_CPU_MAPS=y

arch/s390/include/asm/ccwdev.h

@@ -217,7 +217,8 @@ extern void ccw_device_destroy_console(struct ccw_device *);
 extern int ccw_device_enable_console(struct ccw_device *);
 extern void ccw_device_wait_idle(struct ccw_device *);
 
-extern void *ccw_device_dma_zalloc(struct ccw_device *cdev, size_t size);
+extern void *ccw_device_dma_zalloc(struct ccw_device *cdev, size_t size,
+				   dma32_t *dma_handle);
 extern void ccw_device_dma_free(struct ccw_device *cdev,
 				void *cpu_addr, size_t size);
 

arch/s390/include/asm/cio.h

@@ -7,6 +7,7 @@
 
 #include <linux/bitops.h>
 #include <linux/genalloc.h>
+#include <asm/dma-types.h>
 #include <asm/types.h>
 #include <asm/tpi.h>
 
@@ -32,7 +33,7 @@ struct ccw1 {
 	__u8  cmd_code;
 	__u8  flags;
 	__u16 count;
-	__u32 cda;
+	dma32_t cda;
 } __attribute__ ((packed,aligned(8)));
 
 /**
@@ -152,8 +153,8 @@ struct sublog {
 struct esw0 {
 	struct sublog sublog;
 	struct erw erw;
-	__u32  faddr[2];
-	__u32  saddr;
+	dma32_t faddr[2];
+	dma32_t saddr;
 } __attribute__ ((packed));
 
 /**
@@ -364,6 +365,8 @@ extern struct device *cio_get_dma_css_dev(void);
 
 void *cio_gp_dma_zalloc(struct gen_pool *gp_dma, struct device *dma_dev,
 			size_t size);
+void *__cio_gp_dma_zalloc(struct gen_pool *gp_dma, struct device *dma_dev,
+			  size_t size, dma32_t *dma_handle);
 void cio_gp_dma_free(struct gen_pool *gp_dma, void *cpu_addr, size_t size);
 void cio_gp_dma_destroy(struct gen_pool *gp_dma, struct device *dma_dev);
 struct gen_pool *cio_gp_dma_create(struct device *dma_dev, int nr_pages);

arch/s390/include/asm/dma-types.h

@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_S390_DMA_TYPES_H_
+#define _ASM_S390_DMA_TYPES_H_
+
+#include <linux/types.h>
+#include <linux/io.h>
+
+/*
+ * typedef dma32_t
+ * Contains a 31 bit absolute address to a DMA capable piece of storage.
+ *
+ * For CIO, DMA addresses are always absolute addresses. These addresses tend
+ * to be used in architectured memory blocks (like ORB, IDAW, MIDAW). Under
+ * certain circumstances 31 bit wide addresses must be used because the
+ * address must fit in 31 bits.
+ *
+ * This type is to be used when such fields can be modelled as 32 bit wide.
+ */
+typedef u32 __bitwise dma32_t;
+
+/*
+ * typedef dma64_t
+ * Contains a 64 bit absolute address to a DMA capable piece of storage.
+ *
+ * For CIO, DMA addresses are always absolute addresses. These addresses tend
+ * to be used in architectured memory blocks (like ORB, IDAW, MIDAW).
+ *
+ * This type is to be used to model such 64 bit wide fields.
+ */
+typedef u64 __bitwise dma64_t;
+
+/*
+ * Although DMA addresses should be obtained using the DMA API, in cases when
+ * it is known that the first argument holds a virtual address that points to
+ * DMA-able 31 bit addressable storage, then this function can be safely used.
+ */
+static inline dma32_t virt_to_dma32(void *ptr)
+{
+	return (__force dma32_t)__pa32(ptr);
+}
+
+static inline void *dma32_to_virt(dma32_t addr)
+{
+	return __va((__force unsigned long)addr);
+}
+
+static inline dma32_t u32_to_dma32(u32 addr)
+{
+	return (__force dma32_t)addr;
+}
+
+static inline u32 dma32_to_u32(dma32_t addr)
+{
+	return (__force u32)addr;
+}
+
+static inline dma32_t dma32_add(dma32_t a, u32 b)
+{
+	return (__force dma32_t)((__force u32)a + b);
+}
+
+static inline dma32_t dma32_and(dma32_t a, u32 b)
+{
+	return (__force dma32_t)((__force u32)a & b);
+}
+
+/*
+ * Although DMA addresses should be obtained using the DMA API, in cases when
+ * it is known that the first argument holds a virtual address that points to
+ * DMA-able storage, then this function can be safely used.
+ */
+static inline dma64_t virt_to_dma64(void *ptr)
+{
+	return (__force dma64_t)__pa(ptr);
+}
+
+static inline void *dma64_to_virt(dma64_t addr)
+{
+	return __va((__force unsigned long)addr);
+}
+
+static inline dma64_t u64_to_dma64(u64 addr)
+{
+	return (__force dma64_t)addr;
+}
+
+static inline u64 dma64_to_u64(dma64_t addr)
+{
+	return (__force u64)addr;
+}
+
+static inline dma64_t dma64_add(dma64_t a, u64 b)
+{
+	return (__force dma64_t)((__force u64)a + b);
+}
+
+static inline dma64_t dma64_and(dma64_t a, u64 b)
+{
+	return (__force dma64_t)((__force u64)a & b);
+}
+
+#endif /* _ASM_S390_DMA_TYPES_H_ */

arch/s390/include/asm/eadm.h

@@ -5,6 +5,7 @@
 #include <linux/types.h>
 #include <linux/device.h>
 #include <linux/blk_types.h>
+#include <asm/dma-types.h>
 
 struct arqb {
 	u64 data;
@@ -45,7 +46,7 @@ struct msb {
 	u16:12;
 	u16 bs:4;
 	u32 blk_count;
-	u64 data_addr;
+	dma64_t data_addr;
 	u64 scm_addr;
 	u64:64;
 } __packed;
@@ -54,7 +55,7 @@ struct aidaw {
 	u8 flags;
 	u32 :24;
 	u32 :32;
-	u64 data_addr;
+	dma64_t data_addr;
 } __packed;
 
 #define MSB_OC_CLEAR	0

arch/s390/include/asm/fcx.h

@@ -10,6 +10,7 @@
 #define _ASM_S390_FCX_H
 
 #include <linux/types.h>
+#include <asm/dma-types.h>
 
 #define TCW_FORMAT_DEFAULT		0
 #define TCW_TIDAW_FORMAT_DEFAULT	0
@@ -43,16 +44,16 @@ struct tcw {
 	u32 r:1;
 	u32 w:1;
 	u32 :16;
-	u64 output;
-	u64 input;
-	u64 tsb;
-	u64 tccb;
+	dma64_t output;
+	dma64_t input;
+	dma64_t tsb;
+	dma64_t tccb;
 	u32 output_count;
 	u32 input_count;
 	u32 :32;
 	u32 :32;
 	u32 :32;
-	u32 intrg;
+	dma32_t intrg;
 } __attribute__ ((packed, aligned(64)));
 
 #define TIDAW_FLAGS_LAST		(1 << (7 - 0))
@@ -73,7 +74,7 @@ struct tidaw {
 	u32 flags:8;
 	u32 :24;
 	u32 count;
-	u64 addr;
+	dma64_t addr;
 } __attribute__ ((packed, aligned(16)));
 
 /**