Merge tag 's390-5.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Heiko Carstens:
 "Besides all the small improvements and cleanups the most notable part
  is the fast vector/SIMD implementation of the ChaCha20 stream cipher,
  which is an adaptation of Andy Polyakov's code for the kernel.

  Summary:

   - add fast vector/SIMD implementation of the ChaCha20 stream cipher,
     which mainly adapts Andy Polyakov's code for the kernel

   - add status attribute to AP queue device so users can easily figure
     out its status

   - fix race in page table release code, and and lots of documentation

   - remove uevent suppress from cio device driver, since it turned out
     that it generated more problems than it solved problems

   - quite a lot of virtual vs physical address confusion fixes

   - various other small improvements and cleanups all over the place"

* tag 's390-5.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (39 commits)
  s390/dasd: use default_groups in kobj_type
  s390/sclp_sd: use default_groups in kobj_type
  s390/pci: simplify __pciwb_mio() inline asm
  s390: remove unused TASK_SIZE_OF
  s390/crash_dump: fix virtual vs physical address handling
  s390/crypto: fix compile error for ChaCha20 module
  s390/mm: check 2KB-fragment page on release
  s390/mm: better annotate 2KB pagetable fragments handling
  s390/mm: fix 2KB pgtable release race
  s390/sclp: release SCLP early buffer after kernel initialization
  s390/nmi: disable interrupts on extended save area update
  s390/zcrypt: CCA control CPRB sending
  s390/disassembler: update opcode table
  s390/uv: fix memblock virtual vs physical address confusion
  s390/smp: fix memblock_phys_free() vs memblock_free() confusion
  s390/sclp: fix memblock_phys_free() vs memblock_free() confusion
  s390/exit: remove dead reference to do_exit from copy_thread
  s390/ap: add missing virt_to_phys address conversion
  s390/pgalloc: use pointers instead of unsigned long values
  s390/pgalloc: add virt/phys address handling to base asce functions
  ...

7 files changed, 155 insertions, 33 deletions

diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h
index 3afbee21dc1f..c0c8a1f6c35d 100644
--- a/arch/s390/include/asm/ap.h
+++ b/arch/s390/include/asm/ap.h
@@ -12,6 +12,8 @@
 #ifndef _ASM_S390_AP_H_
 #define _ASM_S390_AP_H_
 
+#include <linux/io.h>
+
 /**
  * The ap_qid_t identifier of an ap queue.
  * If the AP facilities test (APFT) facility is available,
@@ -238,7 +240,7 @@ static inline struct ap_queue_status ap_aqic(ap_qid_t qid,
 		struct ap_qirq_ctrl qirqctrl;
 		struct ap_queue_status status;
 	} reg1;
-	void *reg2 = ind;
+	unsigned long reg2 = virt_to_phys(ind);
 
 	reg1.qirqctrl = qirqctrl;
 
diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h
index b3a8cb4daed6..bdcd64f0c1d7 100644
--- a/arch/s390/include/asm/diag.h
+++ b/arch/s390/include/asm/diag.h
@@ -47,8 +47,8 @@ static inline void diag10_range(unsigned long start_pfn, unsigned long num_pfn)
 {
 	unsigned long start_addr, end_addr;
 
-	start_addr = start_pfn << PAGE_SHIFT;
-	end_addr = (start_pfn + num_pfn - 1) << PAGE_SHIFT;
+	start_addr = pfn_to_phys(start_pfn);
+	end_addr = pfn_to_phys(start_pfn + num_pfn - 1);
 
 	diag_stat_inc(DIAG_STAT_X010);
 	asm volatile(
diff --git a/arch/s390/include/asm/nmi.h b/arch/s390/include/asm/nmi.h
index 2db45d7e68aa..55c9051dddfd 100644
--- a/arch/s390/include/asm/nmi.h
+++ b/arch/s390/include/asm/nmi.h
@@ -98,9 +98,9 @@ struct mcesa {
 
 struct pt_regs;
 
-void nmi_alloc_boot_cpu(struct lowcore *lc);
-int nmi_alloc_per_cpu(struct lowcore *lc);
-void nmi_free_per_cpu(struct lowcore *lc);
+void nmi_alloc_mcesa_early(u64 *mcesad);
+int nmi_alloc_mcesa(u64 *mcesad);
+void nmi_free_mcesa(u64 *mcesad);
 
 void s390_handle_mcck(void);
 void __s390_handle_mcck(void);
diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h
index 3b8e89d4578a..91e63426bdc5 100644
--- a/arch/s390/include/asm/pci_dma.h
+++ b/arch/s390/include/asm/pci_dma.h
@@ -97,23 +97,23 @@ static inline unsigned int calc_px(dma_addr_t ptr)
 	return ((unsigned long) ptr >> PAGE_SHIFT) & ZPCI_PT_MASK;
 }
 
-static inline void set_pt_pfaa(unsigned long *entry, void *pfaa)
+static inline void set_pt_pfaa(unsigned long *entry, phys_addr_t pfaa)
 {
 	*entry &= ZPCI_PTE_FLAG_MASK;
-	*entry |= ((unsigned long) pfaa & ZPCI_PTE_ADDR_MASK);
+	*entry |= (pfaa & ZPCI_PTE_ADDR_MASK);
 }
 
-static inline void set_rt_sto(unsigned long *entry, void *sto)
+static inline void set_rt_sto(unsigned long *entry, phys_addr_t sto)
 {
 	*entry &= ZPCI_RTE_FLAG_MASK;
-	*entry |= ((unsigned long) sto & ZPCI_RTE_ADDR_MASK);
+	*entry |= (sto & ZPCI_RTE_ADDR_MASK);
 	*entry |= ZPCI_TABLE_TYPE_RTX;
 }
 
-static inline void set_st_pto(unsigned long *entry, void *pto)
+static inline void set_st_pto(unsigned long *entry, phys_addr_t pto)
 {
 	*entry &= ZPCI_STE_FLAG_MASK;
-	*entry |= ((unsigned long) pto & ZPCI_STE_ADDR_MASK);
+	*entry |= (pto & ZPCI_STE_ADDR_MASK);
 	*entry |= ZPCI_TABLE_TYPE_SX;
 }
 
@@ -169,16 +169,19 @@ static inline int pt_entry_isvalid(unsigned long entry)
 
 static inline unsigned long *get_rt_sto(unsigned long entry)
 {
-	return ((entry & ZPCI_TABLE_TYPE_MASK) == ZPCI_TABLE_TYPE_RTX)
-		? (unsigned long *) (entry & ZPCI_RTE_ADDR_MASK)
-		: NULL;
+	if ((entry & ZPCI_TABLE_TYPE_MASK) == ZPCI_TABLE_TYPE_RTX)
+		return phys_to_virt(entry & ZPCI_RTE_ADDR_MASK);
+	else
+		return NULL;
+
 }
 
 static inline unsigned long *get_st_pto(unsigned long entry)
 {
-	return ((entry & ZPCI_TABLE_TYPE_MASK) == ZPCI_TABLE_TYPE_SX)
-		? (unsigned long *) (entry & ZPCI_STE_ADDR_MASK)
-		: NULL;
+	if ((entry & ZPCI_TABLE_TYPE_MASK) == ZPCI_TABLE_TYPE_SX)
+		return phys_to_virt(entry & ZPCI_STE_ADDR_MASK);
+	else
+		return NULL;
 }
 
 /* Prototypes */
@@ -186,7 +189,7 @@ void dma_free_seg_table(unsigned long);
 unsigned long *dma_alloc_cpu_table(void);
 void dma_cleanup_tables(unsigned long *);
 unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr);
-void dma_update_cpu_trans(unsigned long *entry, void *page_addr, int flags);
+void dma_update_cpu_trans(unsigned long *entry, phys_addr_t page_addr, int flags);
 
 extern const struct dma_map_ops s390_pci_dma_ops;
 
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index f54c152bf2bf..5581b64a4236 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -88,11 +88,10 @@ extern void __bpon(void);
  * User space process size: 2GB for 31 bit, 4TB or 8PT for 64 bit.
  */
 
-#define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_31BIT) ? \
+#define TASK_SIZE		(test_thread_flag(TIF_31BIT) ? \
 					_REGION3_SIZE : TASK_SIZE_MAX)
 #define TASK_UNMAPPED_BASE	(test_thread_flag(TIF_31BIT) ? \
 					(_REGION3_SIZE >> 1) : (_REGION2_SIZE >> 1))
-#define TASK_SIZE		TASK_SIZE_OF(current)
 #define TASK_SIZE_MAX		(-PAGE_SIZE)
 
 #define STACK_TOP		(test_thread_flag(TIF_31BIT) ? \
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index 4b9b14b20984..54ae2dc65e3b 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -18,7 +18,6 @@
 #define QDIO_MAX_BUFFERS_MASK		(QDIO_MAX_BUFFERS_PER_Q - 1)
 #define QDIO_BUFNR(num)			((num) & QDIO_MAX_BUFFERS_MASK)
 #define QDIO_MAX_ELEMENTS_PER_BUFFER	16
-#define QDIO_SBAL_SIZE			256
 
 #define QDIO_QETH_QFMT			0
 #define QDIO_ZFCP_QFMT			1
@@ -92,8 +91,8 @@ struct qdr {
  * @pfmt: implementation dependent parameter format
  * @rflags: QEBSM
  * @ac: adapter characteristics
- * @isliba: absolute address of first input SLIB
- * @osliba: absolute address of first output SLIB
+ * @isliba: logical address of first input SLIB
+ * @osliba: logical address of first output SLIB
  * @ebcnam: adapter identifier in EBCDIC
  * @parm: implementation dependent parameters
  */
@@ -313,7 +312,7 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int,
  * @qib_rflags: rflags to set
  * @no_input_qs: number of input queues
  * @no_output_qs: number of output queues
- * @input_handler: handler to be called for input queues
+ * @input_handler: handler to be called for input queues, and device-wide errors
  * @output_handler: handler to be called for output queues
  * @irq_poll: Data IRQ polling handler
  * @scan_threshold: # of in-use buffers that triggers scan on output queue
@@ -337,9 +336,6 @@ struct qdio_initialize {
 	struct qdio_buffer ***output_sbal_addr_array;
 };
 
-#define QDIO_FLAG_SYNC_INPUT		0x01
-#define QDIO_FLAG_SYNC_OUTPUT		0x02
-
 int qdio_alloc_buffers(struct qdio_buffer **buf, unsigned int count);
 void qdio_free_buffers(struct qdio_buffer **buf, unsigned int count);
 void qdio_reset_buffers(struct qdio_buffer **buf, unsigned int count);
@@ -349,13 +345,18 @@ extern int qdio_allocate(struct ccw_device *cdev, unsigned int no_input_qs,
 extern int qdio_establish(struct ccw_device *cdev,
 			  struct qdio_initialize *init_data);
 extern int qdio_activate(struct ccw_device *);
-extern int do_QDIO(struct ccw_device *cdev, unsigned int callflags, int q_nr,
-		   unsigned int bufnr, unsigned int count, struct qaob *aob);
 extern int qdio_start_irq(struct ccw_device *cdev);
 extern int qdio_stop_irq(struct ccw_device *cdev);
-extern int qdio_inspect_queue(struct ccw_device *cdev, unsigned int nr,
-			      bool is_input, unsigned int *bufnr,
-			      unsigned int *error);
+extern int qdio_inspect_input_queue(struct ccw_device *cdev, unsigned int nr,
+				    unsigned int *bufnr, unsigned int *error);
+extern int qdio_inspect_output_queue(struct ccw_device *cdev, unsigned int nr,
+				     unsigned int *bufnr, unsigned int *error);
+extern int qdio_add_bufs_to_input_queue(struct ccw_device *cdev,
+					unsigned int q_nr, unsigned int bufnr,
+					unsigned int count);
+extern int qdio_add_bufs_to_output_queue(struct ccw_device *cdev,
+					 unsigned int q_nr, unsigned int bufnr,
+					 unsigned int count, struct qaob *aob);
 extern int qdio_shutdown(struct ccw_device *, int);
 extern int qdio_free(struct ccw_device *);
 extern int qdio_get_ssqd_desc(struct ccw_device *, struct qdio_ssqd_desc *);
diff --git a/arch/s390/include/asm/vx-insn.h b/arch/s390/include/asm/vx-insn.h
index 0c05a673811c..87e6cc2aeba4 100644
--- a/arch/s390/include/asm/vx-insn.h
+++ b/arch/s390/include/asm/vx-insn.h
@@ -372,6 +372,16 @@
 	MRXBOPC	\hint, 0x36, v1, v3
 .endm
 
+/* VECTOR STORE */
+.macro	VST	vr1, disp, index="%r0", base
+	VX_NUM	v1, \vr1
+	GR_NUM	x2, \index
+	GR_NUM	b2, \base	    /* Base register */
+	.word	0xE700 | ((v1&15) << 4) | (x2&15)
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC	0, 0x0E, v1
+.endm
+
 /* VECTOR STORE MULTIPLE */
 .macro	VSTM	vfrom, vto, disp, base, hint=3
 	VX_NUM	v1, \vfrom
@@ -411,6 +421,81 @@
 	VUPLL	\vr1, \vr2, 2
 .endm
 
+/* VECTOR PERMUTE DOUBLEWORD IMMEDIATE */
+.macro	VPDI	vr1, vr2, vr3, m4
+	VX_NUM	v1, \vr1
+	VX_NUM	v2, \vr2
+	VX_NUM	v3, \vr3
+	.word	0xE700 | ((v1&15) << 4) | (v2&15)
+	.word	((v3&15) << 12)
+	MRXBOPC	\m4, 0x84, v1, v2, v3
+.endm
+
+/* VECTOR REPLICATE */
+.macro	VREP	vr1, vr3, imm2, m4
+	VX_NUM	v1, \vr1
+	VX_NUM	v3, \vr3
+	.word	0xE700 | ((v1&15) << 4) | (v3&15)
+	.word	\imm2
+	MRXBOPC	\m4, 0x4D, v1, v3
+.endm
+.macro	VREPB	vr1, vr3, imm2
+	VREP	\vr1, \vr3, \imm2, 0
+.endm
+.macro	VREPH	vr1, vr3, imm2
+	VREP	\vr1, \vr3, \imm2, 1
+.endm
+.macro	VREPF	vr1, vr3, imm2
+	VREP	\vr1, \vr3, \imm2, 2
+.endm
+.macro	VREPG	vr1, vr3, imm2
+	VREP	\vr1, \vr3, \imm2, 3
+.endm
+
+/* VECTOR MERGE HIGH */
+.macro	VMRH	vr1, vr2, vr3, m4
+	VX_NUM	v1, \vr1
+	VX_NUM	v2, \vr2
+	VX_NUM	v3, \vr3
+	.word	0xE700 | ((v1&15) << 4) | (v2&15)
+	.word	((v3&15) << 12)
+	MRXBOPC	\m4, 0x61, v1, v2, v3
+.endm
+.macro	VMRHB	vr1, vr2, vr3
+	VMRH	\vr1, \vr2, \vr3, 0
+.endm
+.macro	VMRHH	vr1, vr2, vr3
+	VMRH	\vr1, \vr2, \vr3, 1
+.endm
+.macro	VMRHF	vr1, vr2, vr3
+	VMRH	\vr1, \vr2, \vr3, 2
+.endm
+.macro	VMRHG	vr1, vr2, vr3
+	VMRH	\vr1, \vr2, \vr3, 3
+.endm
+
+/* VECTOR MERGE LOW */
+.macro	VMRL	vr1, vr2, vr3, m4
+	VX_NUM	v1, \vr1
+	VX_NUM	v2, \vr2
+	VX_NUM	v3, \vr3
+	.word	0xE700 | ((v1&15) << 4) | (v2&15)
+	.word	((v3&15) << 12)
+	MRXBOPC	\m4, 0x60, v1, v2, v3
+.endm
+.macro	VMRLB	vr1, vr2, vr3
+	VMRL	\vr1, \vr2, \vr3, 0
+.endm
+.macro	VMRLH	vr1, vr2, vr3
+	VMRL	\vr1, \vr2, \vr3, 1
+.endm
+.macro	VMRLF	vr1, vr2, vr3
+	VMRL	\vr1, \vr2, \vr3, 2
+.endm
+.macro	VMRLG	vr1, vr2, vr3
+	VMRL	\vr1, \vr2, \vr3, 3
+.endm
+
 
 /* Vector integer instructions */
 
@@ -557,5 +642,37 @@
 	VESRAV	\vr1, \vr2, \vr3, 3
 .endm
 
+/* VECTOR ELEMENT ROTATE LEFT LOGICAL */
+.macro	VERLL	vr1, vr3, disp, base="%r0", m4
+	VX_NUM	v1, \vr1
+	VX_NUM	v3, \vr3
+	GR_NUM	b2, \base
+	.word	0xE700 | ((v1&15) << 4) | (v3&15)
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC	\m4, 0x33, v1, v3
+.endm
+.macro	VERLLB	vr1, vr3, disp, base="%r0"
+	VERLL	\vr1, \vr3, \disp, \base, 0
+.endm
+.macro	VERLLH	vr1, vr3, disp, base="%r0"
+	VERLL	\vr1, \vr3, \disp, \base, 1
+.endm
+.macro	VERLLF	vr1, vr3, disp, base="%r0"
+	VERLL	\vr1, \vr3, \disp, \base, 2
+.endm
+.macro	VERLLG	vr1, vr3, disp, base="%r0"
+	VERLL	\vr1, \vr3, \disp, \base, 3
+.endm
+
+/* VECTOR SHIFT LEFT DOUBLE BY BYTE */
+.macro	VSLDB	vr1, vr2, vr3, imm4
+	VX_NUM	v1, \vr1
+	VX_NUM	v2, \vr2
+	VX_NUM	v3, \vr3
+	.word	0xE700 | ((v1&15) << 4) | (v2&15)
+	.word	((v3&15) << 12) | (\imm4)
+	MRXBOPC	0, 0x77, v1, v2, v3
+.endm
+
 #endif	/* __ASSEMBLY__ */
 #endif	/* __ASM_S390_VX_INSN_H */