Merge branch 'x86/boot' into x86/mm, to pick up interacting changes

The SME patches we are about to apply add some E820 logic, so merge in
pending E820 code changes first, to have a single code base.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

16 files changed, 23 insertions, 295 deletions

diff --git a/arch/ia64/hp/sim/simserial.c b/arch/ia64/hp/sim/simserial.c
index de8cba121013..70d52e9bb575 100644
--- a/arch/ia64/hp/sim/simserial.c
+++ b/arch/ia64/hp/sim/simserial.c
@@ -387,19 +387,6 @@ static int activate(struct tty_port *port, struct tty_struct *tty)
 	}
 
 	state->xmit.head = state->xmit.tail = 0;
-
-	/*
-	 * Set up the tty->alt_speed kludge
-	 */
-	if ((port->flags & ASYNC_SPD_MASK) == ASYNC_SPD_HI)
-		tty->alt_speed = 57600;
-	if ((port->flags & ASYNC_SPD_MASK) == ASYNC_SPD_VHI)
-		tty->alt_speed = 115200;
-	if ((port->flags & ASYNC_SPD_MASK) == ASYNC_SPD_SHI)
-		tty->alt_speed = 230400;
-	if ((port->flags & ASYNC_SPD_MASK) == ASYNC_SPD_WARP)
-		tty->alt_speed = 460800;
-
 errout:
 	local_irq_restore(flags);
 	return retval;
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index 502a91d8dbbd..1d7641f891e1 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -1,8 +1,6 @@
-
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += irq_work.h
-generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += preempt.h
diff --git a/arch/ia64/include/asm/dma-mapping.h b/arch/ia64/include/asm/dma-mapping.h
index 73ec3c6f4cfe..3ce5ab4339f3 100644
--- a/arch/ia64/include/asm/dma-mapping.h
+++ b/arch/ia64/include/asm/dma-mapping.h
@@ -12,8 +12,6 @@
 
 #define ARCH_HAS_DMA_GET_REQUIRED_MASK
 
-#define DMA_ERROR_CODE 0
-
 extern const struct dma_map_ops *dma_ops;
 extern struct ia64_machine_vector ia64_mv;
 extern void set_iommu_machvec(void);
diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h
index 5de673ac9cb1..a2540e21f919 100644
--- a/arch/ia64/include/asm/io.h
+++ b/arch/ia64/include/asm/io.h
@@ -117,7 +117,7 @@ extern int valid_mmap_phys_addr_range (unsigned long pfn, size_t count);
  * following the barrier will arrive after all previous writes.  For most
  * ia64 platforms, this is a simple 'mf.a' instruction.
  *
- * See Documentation/DocBook/deviceiobook.tmpl for more information.
+ * See Documentation/driver-api/device-io.rst for more information.
  */
 static inline void ___ia64_mmiowb(void)
 {
diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h
index 82a7646c4416..0890ded638f0 100644
--- a/arch/ia64/include/asm/uaccess.h
+++ b/arch/ia64/include/asm/uaccess.h
@@ -87,42 +87,6 @@ static inline int __access_ok(const void __user *p, unsigned long size)
 #define __put_user(x, ptr)	__put_user_nocheck((__typeof__(*(ptr))) (x), (ptr), sizeof(*(ptr)))
 #define __get_user(x, ptr)	__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
 
-extern long __put_user_unaligned_unknown (void);
-
-#define __put_user_unaligned(x, ptr)								\
-({												\
-	long __ret;										\
-	switch (sizeof(*(ptr))) {								\
-		case 1: __ret = __put_user((x), (ptr)); break;					\
-		case 2: __ret = (__put_user((x), (u8 __user *)(ptr)))				\
-			| (__put_user((x) >> 8, ((u8 __user *)(ptr) + 1))); break;		\
-		case 4: __ret = (__put_user((x), (u16 __user *)(ptr)))				\
-			| (__put_user((x) >> 16, ((u16 __user *)(ptr) + 1))); break;		\
-		case 8: __ret = (__put_user((x), (u32 __user *)(ptr)))				\
-			| (__put_user((x) >> 32, ((u32 __user *)(ptr) + 1))); break;		\
-		default: __ret = __put_user_unaligned_unknown();				\
-	}											\
-	__ret;											\
-})
-
-extern long __get_user_unaligned_unknown (void);
-
-#define __get_user_unaligned(x, ptr)								\
-({												\
-	long __ret;										\
-	switch (sizeof(*(ptr))) {								\
-		case 1: __ret = __get_user((x), (ptr)); break;					\
-		case 2: __ret = (__get_user((x), (u8 __user *)(ptr)))				\
-			| (__get_user((x) >> 8, ((u8 __user *)(ptr) + 1))); break;		\
-		case 4: __ret = (__get_user((x), (u16 __user *)(ptr)))				\
-			| (__get_user((x) >> 16, ((u16 __user *)(ptr) + 1))); break;		\
-		case 8: __ret = (__get_user((x), (u32 __user *)(ptr)))				\
-			| (__get_user((x) >> 32, ((u32 __user *)(ptr) + 1))); break;		\
-		default: __ret = __get_user_unaligned_unknown();				\
-	}											\
-	__ret;											\
-})
-
 #ifdef ASM_SUPPORTED
   struct __large_struct { unsigned long buf[100]; };
 # define __m(x) (*(struct __large_struct __user *)(x))
@@ -277,18 +241,6 @@ extern long __must_check __strncpy_from_user (char *to, const char __user *from,
 	__sfu_ret;							\
 })
 
-/* Returns: 0 if bad, string length+1 (memory size) of string if ok */
-extern unsigned long __strlen_user (const char __user *);
-
-#define strlen_user(str)				\
-({							\
-	const char __user *__su_str = (str);		\
-	unsigned long __su_ret = 0;			\
-	if (__access_ok(__su_str, 0))			\
-		__su_ret = __strlen_user(__su_str);	\
-	__su_ret;					\
-})
-
 /*
  * Returns: 0 if exception before NUL or reaching the supplied limit
  * (N), a value greater than N if the limit would be exceeded, else
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index 2c3f4b48042a..5dd5c5d0d642 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -107,4 +107,8 @@
 
 #define SO_COOKIE		57
 
+#define SCM_TIMESTAMPING_PKTINFO	58
+
+#define SO_PEERGROUPS		59
+
 #endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/ia64/kernel/Makefile.gate b/arch/ia64/kernel/Makefile.gate
index a32903ada016..7da7c65a9bb1 100644
--- a/arch/ia64/kernel/Makefile.gate
+++ b/arch/ia64/kernel/Makefile.gate
@@ -1,8 +1,8 @@
 # The gate DSO image is built using a special linker script.
 
-targets += gate.so gate-syms.o
+targets += gate.so gate.lds gate.o gate-dummy.o
 
-extra-y += gate.so gate-syms.o gate.lds gate.o
+obj-y += gate-syms.o
 
 CPPFLAGS_gate.lds := -P -C -U$(ARCH)
 
@@ -14,13 +14,14 @@ GATECFLAGS_gate.so = -shared -s -Wl,-soname=linux-gate.so.1 \
 $(obj)/gate.so: $(obj)/gate.lds $(obj)/gate.o FORCE
 	$(call if_changed,gate)
 
-$(obj)/built-in.o: $(obj)/gate-syms.o
-$(obj)/built-in.o: ld_flags += -R $(obj)/gate-syms.o
-
-GATECFLAGS_gate-syms.o = -r
-$(obj)/gate-syms.o: $(obj)/gate.lds $(obj)/gate.o FORCE
+GATECFLAGS_gate-dummy.o = -r
+$(obj)/gate-dummy.o: $(obj)/gate.lds $(obj)/gate.o FORCE
 	$(call if_changed,gate)
 
+LDFLAGS_gate-syms.o := -r -R
+$(obj)/gate-syms.o: $(obj)/gate-dummy.o FORCE
+	$(call if_changed,ld)
+
 # gate-data.o contains the gate DSO image as data in section .data..gate.
 # We must build gate.so before we can assemble it.
 # Note: kbuild does not track this dependency due to usage of .incbin
diff --git a/arch/ia64/kernel/machine_kexec.c b/arch/ia64/kernel/machine_kexec.c
index 599507bcec91..c14815dca747 100644
--- a/arch/ia64/kernel/machine_kexec.c
+++ b/arch/ia64/kernel/machine_kexec.c
@@ -163,8 +163,3 @@ void arch_crash_save_vmcoreinfo(void)
 #endif
 }
 
-phys_addr_t paddr_vmcoreinfo_note(void)
-{
-	return ia64_tpa((unsigned long)(char *)&vmcoreinfo_note);
-}
-
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 79c7c46d7dc1..555b11180156 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -334,7 +334,7 @@ static void ia64_mlogbuf_dump_from_init(void)
 	ia64_mlogbuf_dump();
 }
 
-static void inline
+static inline void
 ia64_mca_spin(const char *func)
 {
 	if (monarch_cpu == smp_processor_id())
diff --git a/arch/ia64/lib/Makefile b/arch/ia64/lib/Makefile
index 0a40b14407b1..1a36a3a39624 100644
--- a/arch/ia64/lib/Makefile
+++ b/arch/ia64/lib/Makefile
@@ -5,7 +5,7 @@
 lib-y := io.o __divsi3.o __udivsi3.o __modsi3.o __umodsi3.o		\
 	__divdi3.o __udivdi3.o __moddi3.o __umoddi3.o			\
 	checksum.o clear_page.o csum_partial_copy.o			\
-	clear_user.o strncpy_from_user.o strlen_user.o strnlen_user.o	\
+	clear_user.o strncpy_from_user.o strnlen_user.o			\
 	flush.o ip_fast_csum.o do_csum.o				\
 	memset.o strlen.o xor.o
 
diff --git a/arch/ia64/lib/strlen_user.S b/arch/ia64/lib/strlen_user.S
deleted file mode 100644
index 9d257684e733..000000000000
--- a/arch/ia64/lib/strlen_user.S
+++ /dev/null
@@ -1,200 +0,0 @@
-/*
- * Optimized version of the strlen_user() function
- *
- * Inputs:
- *	in0	address of buffer
- *
- * Outputs:
- *	ret0	0 in case of fault, strlen(buffer)+1 otherwise
- *
- * Copyright (C) 1998, 1999, 2001 Hewlett-Packard Co
- *	David Mosberger-Tang <davidm@hpl.hp.com>
- *	Stephane Eranian <eranian@hpl.hp.com>
- *
- * 01/19/99 S.Eranian heavily enhanced version (see details below)
- * 09/24/99 S.Eranian added speculation recovery code
- */
-
-#include <asm/asmmacro.h>
-#include <asm/export.h>
-
-//
-// int strlen_user(char *)
-// ------------------------
-// Returns:
-//	- length of string + 1
-//	- 0 in case an exception is raised
-//
-// This is an enhanced version of the basic strlen_user. it includes a
-// combination of compute zero index (czx), parallel comparisons, speculative
-// loads and loop unroll using rotating registers.
-//
-// General Ideas about the algorithm:
-//	  The goal is to look at the string in chunks of 8 bytes.
-//	  so we need to do a few extra checks at the beginning because the
-//	  string may not be 8-byte aligned. In this case we load the 8byte
-//	  quantity which includes the start of the string and mask the unused
-//	  bytes with 0xff to avoid confusing czx.
-//	  We use speculative loads and software pipelining to hide memory
-//	  latency and do read ahead safely. This way we defer any exception.
-//
-//	  Because we don't want the kernel to be relying on particular
-//	  settings of the DCR register, we provide recovery code in case
-//	  speculation fails. The recovery code is going to "redo" the work using
-//	  only normal loads. If we still get a fault then we return an
-//	  error (ret0=0). Otherwise we return the strlen+1 as usual.
-//	  The fact that speculation may fail can be caused, for instance, by
-//	  the DCR.dm bit being set. In this case TLB misses are deferred, i.e.,
-//	  a NaT bit will be set if the translation is not present. The normal
-//	  load, on the other hand, will cause the translation to be inserted
-//	  if the mapping exists.
-//
-//	  It should be noted that we execute recovery code only when we need
-//	  to use the data that has been speculatively loaded: we don't execute
-//	  recovery code on pure read ahead data.
-//
-// Remarks:
-//	- the cmp r0,r0 is used as a fast way to initialize a predicate
-//	  register to 1. This is required to make sure that we get the parallel
-//	  compare correct.
-//
-//	- we don't use the epilogue counter to exit the loop but we need to set
-//	  it to zero beforehand.
-//
-//	- after the loop we must test for Nat values because neither the
-//	  czx nor cmp instruction raise a NaT consumption fault. We must be
-//	  careful not to look too far for a Nat for which we don't care.
-//	  For instance we don't need to look at a NaT in val2 if the zero byte
-//	  was in val1.
-//
-//	- Clearly performance tuning is required.
-//
-
-#define saved_pfs	r11
-#define	tmp		r10
-#define base		r16
-#define orig		r17
-#define saved_pr	r18
-#define src		r19
-#define mask		r20
-#define val		r21
-#define val1		r22
-#define val2		r23
-
-GLOBAL_ENTRY(__strlen_user)
-	.prologue
-	.save ar.pfs, saved_pfs
-	alloc saved_pfs=ar.pfs,11,0,0,8
-
-	.rotr v[2], w[2]	// declares our 4 aliases
-
-	extr.u tmp=in0,0,3	// tmp=least significant 3 bits
-	mov orig=in0		// keep trackof initial byte address
-	dep src=0,in0,0,3	// src=8byte-aligned in0 address
-	.save pr, saved_pr
-	mov saved_pr=pr		// preserve predicates (rotation)
-	;;
-
-	.body
-
-	ld8.s v[1]=[src],8	// load the initial 8bytes (must speculate)
-	shl tmp=tmp,3		// multiply by 8bits/byte
-	mov mask=-1		// our mask
-	;;
-	ld8.s w[1]=[src],8	// load next 8 bytes in 2nd pipeline
-	cmp.eq p6,p0=r0,r0	// sets p6 (required because of // cmp.and)
-	sub tmp=64,tmp		// how many bits to shift our mask on the right
-	;;
-	shr.u	mask=mask,tmp	// zero enough bits to hold v[1] valuable part
-	mov ar.ec=r0		// clear epilogue counter (saved in ar.pfs)
-	;;
-	add base=-16,src	// keep track of aligned base
-	chk.s v[1], .recover	// if already NaT, then directly skip to recover
-	or v[1]=v[1],mask	// now we have a safe initial byte pattern
-	;;
-1:
-	ld8.s v[0]=[src],8	// speculatively load next
-	czx1.r val1=v[1]	// search 0 byte from right
-	czx1.r val2=w[1]	// search 0 byte from right following 8bytes
-	;;
-	ld8.s w[0]=[src],8	// speculatively load next to next
-	cmp.eq.and p6,p0=8,val1	// p6 = p6 and val1==8
-	cmp.eq.and p6,p0=8,val2	// p6 = p6 and mask==8
-(p6)	br.wtop.dptk.few 1b	// loop until p6 == 0
-	;;
-	//
-	// We must return try the recovery code iff
-	// val1_is_nat || (val1==8 && val2_is_nat)
-	//
-	// XXX Fixme
-	//	- there must be a better way of doing the test
-	//
-	cmp.eq  p8,p9=8,val1	// p6 = val1 had zero (disambiguate)
-	tnat.nz p6,p7=val1	// test NaT on val1
-(p6)	br.cond.spnt .recover	// jump to recovery if val1 is NaT
-	;;
-	//
-	// if we come here p7 is true, i.e., initialized for // cmp
-	//
-	cmp.eq.and  p7,p0=8,val1// val1==8?
-	tnat.nz.and p7,p0=val2	// test NaT if val2
-(p7)	br.cond.spnt .recover	// jump to recovery if val2 is NaT
-	;;
-(p8)	mov val1=val2		// val2 contains the value
-(p8)	adds src=-16,src	// correct position when 3 ahead
-(p9)	adds src=-24,src	// correct position when 4 ahead
-	;;
-	sub ret0=src,orig	// distance from origin
-	sub tmp=7,val1		// 7=8-1 because this strlen returns strlen+1
-	mov pr=saved_pr,0xffffffffffff0000
-	;;
-	sub ret0=ret0,tmp	// length=now - back -1
-	mov ar.pfs=saved_pfs	// because of ar.ec, restore no matter what
-	br.ret.sptk.many rp	// end of normal execution
-
-	//
-	// Outlined recovery code when speculation failed
-	//
-	// This time we don't use speculation and rely on the normal exception
-	// mechanism. that's why the loop is not as good as the previous one
-	// because read ahead is not possible
-	//
-	// XXX Fixme
-	//	- today we restart from the beginning of the string instead
-	//	  of trying to continue where we left off.
-	//
-.recover:
-	EX(.Lexit1, ld8 val=[base],8)	// load the initial bytes
-	;;
-	or val=val,mask			// remask first bytes
-	cmp.eq p0,p6=r0,r0		// nullify first ld8 in loop
-	;;
-	//
-	// ar.ec is still zero here
-	//
-2:
-	EX(.Lexit1, (p6) ld8 val=[base],8)
-	;;
-	czx1.r val1=val		// search 0 byte from right
-	;;
-	cmp.eq p6,p0=8,val1	// val1==8 ?
-(p6)	br.wtop.dptk.few 2b	// loop until p6 == 0
-	;;
-	sub ret0=base,orig	// distance from base
-	sub tmp=7,val1		// 7=8-1 because this strlen returns strlen+1
-	mov pr=saved_pr,0xffffffffffff0000
-	;;
-	sub ret0=ret0,tmp	// length=now - back -1
-	mov ar.pfs=saved_pfs	// because of ar.ec, restore no matter what
-	br.ret.sptk.many rp	// end of successful recovery code
-
-	//
-	// We failed even on the normal load (called from exception handler)
-	//
-.Lexit1:
-	mov ret0=0
-	mov pr=saved_pr,0xffffffffffff0000
-	mov ar.pfs=saved_pfs	// because of ar.ec, restore no matter what
-	br.ret.sptk.many rp
-END(__strlen_user)
-EXPORT_SYMBOL(__strlen_user)
diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c
index 85de86d36fdf..ae35140332f7 100644
--- a/arch/ia64/mm/hugetlbpage.c
+++ b/arch/ia64/mm/hugetlbpage.c
@@ -44,7 +44,7 @@ huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
 }
 
 pte_t *
-huge_pte_offset (struct mm_struct *mm, unsigned long addr)
+huge_pte_offset (struct mm_struct *mm, unsigned long addr, unsigned long sz)
 {
 	unsigned long taddr = htlbpage_to_page(addr);
 	pgd_t *pgd;
@@ -92,7 +92,7 @@ struct page *follow_huge_addr(struct mm_struct *mm, unsigned long addr, int writ
 	if (REGION_NUMBER(addr) != RGN_HPAGE)
 		return ERR_PTR(-EINVAL);
 
-	ptep = huge_pte_offset(mm, addr);
+	ptep = huge_pte_offset(mm, addr, HPAGE_SIZE);
 	if (!ptep || pte_none(*ptep))
 		return NULL;
 	page = pte_page(*ptep);
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 8f3efa682ee8..a4e8d6bd9cfa 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -646,20 +646,13 @@ mem_init (void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
+int arch_add_memory(int nid, u64 start, u64 size, bool want_memblock)
 {
-	pg_data_t *pgdat;
-	struct zone *zone;
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
-	pgdat = NODE_DATA(nid);
-
-	zone = pgdat->node_zones +
-		zone_for_memory(nid, start, size, ZONE_NORMAL, for_device);
-	ret = __add_pages(nid, zone, start_pfn, nr_pages);
-
+	ret = __add_pages(nid, start_pfn, nr_pages, want_memblock);
 	if (ret)
 		printk("%s: Problem encountered in __add_pages() as ret=%d\n",
 		       __func__,  ret);
diff --git a/arch/ia64/sn/kernel/iomv.c b/arch/ia64/sn/kernel/iomv.c
index c77ebdf98119..2b22a71663c1 100644
--- a/arch/ia64/sn/kernel/iomv.c
+++ b/arch/ia64/sn/kernel/iomv.c
@@ -63,7 +63,7 @@ EXPORT_SYMBOL(sn_io_addr);
 /**
  * __sn_mmiowb - I/O space memory barrier
  *
- * See arch/ia64/include/asm/io.h and Documentation/DocBook/deviceiobook.tmpl
+ * See arch/ia64/include/asm/io.h and Documentation/driver-api/device-io.rst
  * for details.
  *
  * On SN2, we wait for the PIO_WRITE_STATUS SHub register to clear.
diff --git a/arch/ia64/sn/pci/pcibr/pcibr_ate.c b/arch/ia64/sn/pci/pcibr/pcibr_ate.c
index 5bc34eac9e01..b67bb4cb73ff 100644
--- a/arch/ia64/sn/pci/pcibr/pcibr_ate.c
+++ b/arch/ia64/sn/pci/pcibr/pcibr_ate.c
@@ -140,7 +140,7 @@ static inline u64 __iomem *pcibr_ate_addr(struct pcibus_info *pcibus_info,
 /*
  * Update the ate.
  */
-void inline
+inline void
 ate_write(struct pcibus_info *pcibus_info, int ate_index, int count,
 	  volatile u64 ate)
 {
diff --git a/arch/ia64/sn/pci/tioce_provider.c b/arch/ia64/sn/pci/tioce_provider.c
index 46d3df4b03a1..3bd9abc35485 100644
--- a/arch/ia64/sn/pci/tioce_provider.c
+++ b/arch/ia64/sn/pci/tioce_provider.c
@@ -52,7 +52,7 @@
  * All registers defined in struct tioce will meet that criteria.
  */
 
-static void inline
+static inline void
 tioce_mmr_war_pre(struct tioce_kernel *kern, void __iomem *mmr_addr)
 {
 	u64 mmr_base;
@@ -78,7 +78,7 @@ tioce_mmr_war_pre(struct tioce_kernel *kern, void __iomem *mmr_addr)
 	}
 }
 
-static void inline
+static inline void
 tioce_mmr_war_post(struct tioce_kernel *kern, void __iomem *mmr_addr)
 {
 	u64 mmr_base;