Merge branch 'parisc-5.12-1' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux

Pull parisc updates from Helge Deller:

 - Optimize parisc page table locks by using the existing
   page_table_lock

 - Export argv0-preserve flag in binfmt_misc for usage in qemu-user

 - Fix interrupt table (IVT) checksum so firmware will call crash
   handler (HPMC)

 - Increase IRQ stack to 64kb on 64-bit kernel

 - Switch to common devmem_is_allowed() implementation

 - Minor fix to get_whan()

* 'parisc-5.12-1' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux:
  binfmt_misc: pass binfmt_misc flags to the interpreter
  parisc: Optimize per-pagetable spinlocks
  parisc: Replace test_ti_thread_flag() with test_tsk_thread_flag()
  parisc: Bump 64-bit IRQ stack size to 64 KB
  parisc: Fix IVT checksum calculation wrt HPMC
  parisc: Use the generic devmem_is_allowed()
  parisc: Drop out of get_whan() if task is running again

arch/parisc/Kconfig

@@ -34,6 +34,7 @@ config PARISC
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_CPU_DEVICES
 	select GENERIC_STRNCPY_FROM_USER
+	select GENERIC_LIB_DEVMEM_IS_ALLOWED
 	select SYSCTL_ARCH_UNALIGN_ALLOW
 	select SYSCTL_EXCEPTION_TRACE
 	select HAVE_MOD_ARCH_SPECIFIC
@@ -310,6 +311,16 @@ config IRQSTACKS
 	  for handling hard and soft interrupts.  This can help avoid
 	  overflowing the process kernel stacks.
 
+config TLB_PTLOCK
+	bool "Use page table locks in TLB fault handler"
+	depends on SMP
+	default n
+	help
+	  Select this option to enable page table locking in the TLB
+	  fault handler. This ensures that page table entries are
+	  updated consistently on SMP machines at the expense of some
+	  loss in performance.
+
 config HOTPLUG_CPU
 	bool
 	default y if SMP

arch/parisc/include/asm/compat.h

@@ -179,7 +179,7 @@ static __inline__ void __user *arch_compat_alloc_user_space(long len)
 
 static inline int __is_compat_task(struct task_struct *t)
 {
-	return test_ti_thread_flag(task_thread_info(t), TIF_32BIT);
+	return test_tsk_thread_flag(t, TIF_32BIT);
 }
 
 static inline int is_compat_task(void)

arch/parisc/include/asm/io.h

@@ -321,4 +321,6 @@ extern void iowrite64be(u64 val, void __iomem *addr);
  */
 #define xlate_dev_kmem_ptr(p)	p
 
+extern int devmem_is_allowed(unsigned long pfn);
+
 #endif

arch/parisc/include/asm/mmu_context.h

@@ -5,6 +5,7 @@
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/atomic.h>
+#include <linux/spinlock.h>
 #include <asm-generic/mm_hooks.h>
 
 /* on PA-RISC, we actually have enough contexts to justify an allocator
@@ -50,6 +51,12 @@ static inline void switch_mm_irqs_off(struct mm_struct *prev,
 		struct mm_struct *next, struct task_struct *tsk)
 {
 	if (prev != next) {
+#ifdef CONFIG_TLB_PTLOCK
+		/* put physical address of page_table_lock in cr28 (tr4)
+		   for TLB faults */
+		spinlock_t *pgd_lock = &next->page_table_lock;
+		mtctl(__pa(__ldcw_align(&pgd_lock->rlock.raw_lock)), 28);
+#endif
 		mtctl(__pa(next->pgd), 25);
 		load_context(next->context);
 	}

arch/parisc/include/asm/page.h

@@ -112,7 +112,7 @@ extern int npmem_ranges;
 #else
 #define BITS_PER_PTE_ENTRY	2
 #define BITS_PER_PMD_ENTRY	2
-#define BITS_PER_PGD_ENTRY	BITS_PER_PMD_ENTRY
+#define BITS_PER_PGD_ENTRY	2
 #endif
 #define PGD_ENTRY_SIZE	(1UL << BITS_PER_PGD_ENTRY)
 #define PMD_ENTRY_SIZE	(1UL << BITS_PER_PMD_ENTRY)

arch/parisc/include/asm/pgalloc.h

@@ -15,47 +15,23 @@
 #define __HAVE_ARCH_PGD_FREE
 #include <asm-generic/pgalloc.h>
 
-/* Allocate the top level pgd (page directory)
+/* Allocate the top level pgd (page directory) */
- *
- * Here (for 64 bit kernels) we implement a Hybrid L2/L3 scheme: we
- * allocate the first pmd adjacent to the pgd.  This means that we can
- * subtract a constant offset to get to it.  The pmd and pgd sizes are
- * arranged so that a single pmd covers 4GB (giving a full 64-bit
- * process access to 8TB) so our lookups are effectively L2 for the
- * first 4GB of the kernel (i.e. for all ILP32 processes and all the
- * kernel for machines with under 4GB of memory) */
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	pgd_t *pgd = (pgd_t *)__get_free_pages(GFP_KERNEL,
+	pgd_t *pgd;
-					       PGD_ALLOC_ORDER);
-	pgd_t *actual_pgd = pgd;
 
-	if (likely(pgd != NULL)) {
+	pgd = (pgd_t *) __get_free_pages(GFP_KERNEL, PGD_ORDER);
-		memset(pgd, 0, PAGE_SIZE<<PGD_ALLOC_ORDER);
+	if (unlikely(pgd == NULL))
-#if CONFIG_PGTABLE_LEVELS == 3
+		return NULL;
-		actual_pgd += PTRS_PER_PGD;
+
-		/* Populate first pmd with allocated memory.  We mark it
+	memset(pgd, 0, PAGE_SIZE << PGD_ORDER);
-		 * with PxD_FLAG_ATTACHED as a signal to the system that this
+
-		 * pmd entry may not be cleared. */
+	return pgd;
-		set_pgd(actual_pgd, __pgd((PxD_FLAG_PRESENT |
-				        PxD_FLAG_VALID |
-					PxD_FLAG_ATTACHED)
-			+ (__u32)(__pa((unsigned long)pgd) >> PxD_VALUE_SHIFT)));
-		/* The first pmd entry also is marked with PxD_FLAG_ATTACHED as
-		 * a signal that this pmd may not be freed */
-		set_pgd(pgd, __pgd(PxD_FLAG_ATTACHED));
-#endif
-	}
-	spin_lock_init(pgd_spinlock(actual_pgd));
-	return actual_pgd;
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
-#if CONFIG_PGTABLE_LEVELS == 3
+	free_pages((unsigned long)pgd, PGD_ORDER);
-	pgd -= PTRS_PER_PGD;
-#endif
-	free_pages((unsigned long)pgd, PGD_ALLOC_ORDER);
 }
 
 #if CONFIG_PGTABLE_LEVELS == 3
@@ -70,41 +46,25 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-	return (pmd_t *)__get_free_pages(GFP_PGTABLE_KERNEL, PMD_ORDER);
+	pmd_t *pmd;
+
+	pmd = (pmd_t *)__get_free_pages(GFP_PGTABLE_KERNEL, PMD_ORDER);
+	if (likely(pmd))
+		memset ((void *)pmd, 0, PAGE_SIZE << PMD_ORDER);
+	return pmd;
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
-	if (pmd_flag(*pmd) & PxD_FLAG_ATTACHED) {
-		/*
-		 * This is the permanent pmd attached to the pgd;
-		 * cannot free it.
-		 * Increment the counter to compensate for the decrement
-		 * done by generic mm code.
-		 */
-		mm_inc_nr_pmds(mm);
-		return;
-	}
 	free_pages((unsigned long)pmd, PMD_ORDER);
 }
-
 #endif
 
 static inline void
 pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
 {
-#if CONFIG_PGTABLE_LEVELS == 3
+	set_pmd(pmd, __pmd((PxD_FLAG_PRESENT | PxD_FLAG_VALID)
-	/* preserve the gateway marker if this is the beginning of
+		+ (__u32)(__pa((unsigned long)pte) >> PxD_VALUE_SHIFT)));
-	 * the permanent pmd */
-	if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
-		set_pmd(pmd, __pmd((PxD_FLAG_PRESENT |
-				PxD_FLAG_VALID |
-				PxD_FLAG_ATTACHED)
-			+ (__u32)(__pa((unsigned long)pte) >> PxD_VALUE_SHIFT)));
-	else
-#endif
-		set_pmd(pmd, __pmd((PxD_FLAG_PRESENT | PxD_FLAG_VALID)
-			+ (__u32)(__pa((unsigned long)pte) >> PxD_VALUE_SHIFT)));
 }
 
 #define pmd_populate(mm, pmd, pte_page) \

arch/parisc/include/asm/pgtable.h

@@ -23,8 +23,6 @@
 #include <asm/processor.h>
 #include <asm/cache.h>
 
-static inline spinlock_t *pgd_spinlock(pgd_t *);
-
 /*
  * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel
  * memory.  For the return value to be meaningful, ADDR must be >=
@@ -42,12 +40,8 @@ static inline spinlock_t *pgd_spinlock(pgd_t *);
 
 /* This is for the serialization of PxTLB broadcasts. At least on the N class
  * systems, only one PxTLB inter processor broadcast can be active at any one
- * time on the Merced bus.
+ * time on the Merced bus. */
-
- * PTE updates are protected by locks in the PMD.
- */
 extern spinlock_t pa_tlb_flush_lock;
-extern spinlock_t pa_swapper_pg_lock;
 #if defined(CONFIG_64BIT) && defined(CONFIG_SMP)
 extern int pa_serialize_tlb_flushes;
 #else
@@ -86,18 +80,16 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
  * within a page table are directly modified.  Thus, the following
  * hook is made available.
  */
-#define set_pte(pteptr, pteval)                                 \
+#define set_pte(pteptr, pteval)			\
-        do{                                                     \
+	do {					\
-                *(pteptr) = (pteval);                           \
+		*(pteptr) = (pteval);		\
-        } while(0)
+		barrier();			\
+	} while(0)
 
-#define set_pte_at(mm, addr, ptep, pteval)			\
+#define set_pte_at(mm, addr, pteptr, pteval)	\
-	do {							\
+	do {					\
-		unsigned long flags;				\
+		*(pteptr) = (pteval);		\
-		spin_lock_irqsave(pgd_spinlock((mm)->pgd), flags);\
+		purge_tlb_entries(mm, addr);	\
-		set_pte(ptep, pteval);				\
-		purge_tlb_entries(mm, addr);			\
-		spin_unlock_irqrestore(pgd_spinlock((mm)->pgd), flags);\
 	} while (0)
 
 #endif /* !__ASSEMBLY__ */
@@ -120,12 +112,10 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 #define KERNEL_INITIAL_SIZE	(1 << KERNEL_INITIAL_ORDER)
 
 #if CONFIG_PGTABLE_LEVELS == 3
-#define PGD_ORDER	1 /* Number of pages per pgd */
+#define PMD_ORDER	1
-#define PMD_ORDER	1 /* Number of pages per pmd */
+#define PGD_ORDER	0
-#define PGD_ALLOC_ORDER	(2 + 1) /* first pgd contains pmd */
 #else
-#define PGD_ORDER	1 /* Number of pages per pgd */
+#define PGD_ORDER	1
-#define PGD_ALLOC_ORDER	(PGD_ORDER + 1)
 #endif
 
 /* Definitions for 3rd level (we use PLD here for Page Lower directory
@@ -240,11 +230,9 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
  * able to effectively address 40/42/44-bits of physical address space
  * depending on 4k/16k/64k PAGE_SIZE */
 #define _PxD_PRESENT_BIT   31
-#define _PxD_ATTACHED_BIT  30
+#define _PxD_VALID_BIT     30
-#define _PxD_VALID_BIT     29
 
 #define PxD_FLAG_PRESENT  (1 << xlate_pabit(_PxD_PRESENT_BIT))
-#define PxD_FLAG_ATTACHED (1 << xlate_pabit(_PxD_ATTACHED_BIT))
 #define PxD_FLAG_VALID    (1 << xlate_pabit(_PxD_VALID_BIT))
 #define PxD_FLAG_MASK     (0xf)
 #define PxD_FLAG_SHIFT    (4)
@@ -326,23 +314,10 @@ extern unsigned long *empty_zero_page;
 #define pgd_flag(x)	(pgd_val(x) & PxD_FLAG_MASK)
 #define pgd_address(x)	((unsigned long)(pgd_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT)
 
-#if CONFIG_PGTABLE_LEVELS == 3
-/* The first entry of the permanent pmd is not there if it contains
- * the gateway marker */
-#define pmd_none(x)	(!pmd_val(x) || pmd_flag(x) == PxD_FLAG_ATTACHED)
-#else
 #define pmd_none(x)	(!pmd_val(x))
-#endif
 #define pmd_bad(x)	(!(pmd_flag(x) & PxD_FLAG_VALID))
 #define pmd_present(x)	(pmd_flag(x) & PxD_FLAG_PRESENT)
 static inline void pmd_clear(pmd_t *pmd) {
-#if CONFIG_PGTABLE_LEVELS == 3
-	if (pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
-		/* This is the entry pointing to the permanent pmd
-		 * attached to the pgd; cannot clear it */
-		set_pmd(pmd, __pmd(PxD_FLAG_ATTACHED));
-	else
-#endif
 		set_pmd(pmd,  __pmd(0));
 }
 
@@ -358,12 +333,6 @@ static inline void pmd_clear(pmd_t *pmd) {
 #define pud_bad(x)      (!(pud_flag(x) & PxD_FLAG_VALID))
 #define pud_present(x)  (pud_flag(x) & PxD_FLAG_PRESENT)
 static inline void pud_clear(pud_t *pud) {
-#if CONFIG_PGTABLE_LEVELS == 3
-	if(pud_flag(*pud) & PxD_FLAG_ATTACHED)
-		/* This is the permanent pmd attached to the pud; cannot
-		 * free it */
-		return;
-#endif
 	set_pud(pud, __pud(0));
 }
 #endif
@@ -456,32 +425,18 @@ extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *);
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val })
 
-
-static inline spinlock_t *pgd_spinlock(pgd_t *pgd)
-{
-	if (unlikely(pgd == swapper_pg_dir))
-		return &pa_swapper_pg_lock;
-	return (spinlock_t *)((char *)pgd + (PAGE_SIZE << (PGD_ALLOC_ORDER - 1)));
-}
-
-
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
-	unsigned long flags;
 
 	if (!pte_young(*ptep))
 		return 0;
 
-	spin_lock_irqsave(pgd_spinlock(vma->vm_mm->pgd), flags);
 	pte = *ptep;
 	if (!pte_young(pte)) {
-		spin_unlock_irqrestore(pgd_spinlock(vma->vm_mm->pgd), flags);
 		return 0;
 	}
-	set_pte(ptep, pte_mkold(pte));
+	set_pte_at(vma->vm_mm, addr, ptep, pte_mkold(pte));
-	purge_tlb_entries(vma->vm_mm, addr);
-	spin_unlock_irqrestore(pgd_spinlock(vma->vm_mm->pgd), flags);
 	return 1;
 }
 
@@ -489,24 +444,16 @@ struct mm_struct;
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	pte_t old_pte;
-	unsigned long flags;
 
-	spin_lock_irqsave(pgd_spinlock(mm->pgd), flags);
 	old_pte = *ptep;
-	set_pte(ptep, __pte(0));
+	set_pte_at(mm, addr, ptep, __pte(0));
-	purge_tlb_entries(mm, addr);
-	spin_unlock_irqrestore(pgd_spinlock(mm->pgd), flags);
 
 	return old_pte;
 }
 
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
-	unsigned long flags;
+	set_pte_at(mm, addr, ptep, pte_wrprotect(*ptep));
-	spin_lock_irqsave(pgd_spinlock(mm->pgd), flags);
-	set_pte(ptep, pte_wrprotect(*ptep));
-	purge_tlb_entries(mm, addr);
-	spin_unlock_irqrestore(pgd_spinlock(mm->pgd), flags);
 }
 
 #define pte_same(A,B)	(pte_val(A) == pte_val(B))

arch/parisc/kernel/asm-offsets.c

@@ -268,7 +268,6 @@ int main(void)
 	DEFINE(ASM_BITS_PER_PGD, BITS_PER_PGD);
 	DEFINE(ASM_BITS_PER_PMD, BITS_PER_PMD);
 	DEFINE(ASM_BITS_PER_PTE, BITS_PER_PTE);
-	DEFINE(ASM_PGD_PMD_OFFSET, -(PAGE_SIZE << PGD_ORDER));
 	DEFINE(ASM_PMD_ENTRY, ((PAGE_OFFSET & PMD_MASK) >> PMD_SHIFT));
 	DEFINE(ASM_PGD_ENTRY, PAGE_OFFSET >> PGDIR_SHIFT);
 	DEFINE(ASM_PGD_ENTRY_SIZE, PGD_ENTRY_SIZE);

arch/parisc/kernel/entry.S

@@ -35,10 +35,9 @@
 	.level 2.0
 #endif
 
-	.import		pa_tlb_lock,data
+	/* Get aligned page_table_lock address for this mm from cr28/tr4 */
-	.macro  load_pa_tlb_lock reg
+	.macro  get_ptl reg
-	mfctl		%cr25,\reg
+	mfctl	%cr28,\reg
-	addil		L%(PAGE_SIZE << (PGD_ALLOC_ORDER - 1)),\reg
 	.endm
 
 	/* space_to_prot macro creates a prot id from a space id */
@@ -407,7 +406,9 @@
 # endif
 #endif
 	dep             %r0,31,PAGE_SHIFT,\pmd  /* clear offset */
+#if CONFIG_PGTABLE_LEVELS < 3
 	copy		%r0,\pte
+#endif
 	ldw,s		\index(\pmd),\pmd
 	bb,>=,n		\pmd,_PxD_PRESENT_BIT,\fault
 	dep		%r0,31,PxD_FLAG_SHIFT,\pmd /* clear flags */
@@ -417,38 +418,23 @@
 	shladd		\index,BITS_PER_PTE_ENTRY,\pmd,\pmd /* pmd is now pte */
 	.endm
 
-	/* Look up PTE in a 3-Level scheme.
+	/* Look up PTE in a 3-Level scheme. */
-	 *
-	 * Here we implement a Hybrid L2/L3 scheme: we allocate the
-	 * first pmd adjacent to the pgd.  This means that we can
-	 * subtract a constant offset to get to it.  The pmd and pgd
-	 * sizes are arranged so that a single pmd covers 4GB (giving
-	 * a full LP64 process access to 8TB) so our lookups are
-	 * effectively L2 for the first 4GB of the kernel (i.e. for
-	 * all ILP32 processes and all the kernel for machines with
-	 * under 4GB of memory) */
 	.macro		L3_ptep pgd,pte,index,va,fault
-#if CONFIG_PGTABLE_LEVELS == 3 /* we might have a 2-Level scheme, e.g. with 16kb page size */
+#if CONFIG_PGTABLE_LEVELS == 3
+	copy		%r0,\pte
 	extrd,u		\va,63-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index
-	extrd,u,*=	\va,63-ASM_PGDIR_SHIFT,64-ASM_PGDIR_SHIFT,%r0
 	ldw,s		\index(\pgd),\pgd
-	extrd,u,*=	\va,63-ASM_PGDIR_SHIFT,64-ASM_PGDIR_SHIFT,%r0
 	bb,>=,n		\pgd,_PxD_PRESENT_BIT,\fault
-	extrd,u,*=	\va,63-ASM_PGDIR_SHIFT,64-ASM_PGDIR_SHIFT,%r0
+	shld		\pgd,PxD_VALUE_SHIFT,\pgd
-	shld		\pgd,PxD_VALUE_SHIFT,\index
-	extrd,u,*=	\va,63-ASM_PGDIR_SHIFT,64-ASM_PGDIR_SHIFT,%r0
-	copy		\index,\pgd
-	extrd,u,*<>	\va,63-ASM_PGDIR_SHIFT,64-ASM_PGDIR_SHIFT,%r0
-	ldo		ASM_PGD_PMD_OFFSET(\pgd),\pgd
 #endif
 	L2_ptep		\pgd,\pte,\index,\va,\fault
 	.endm
 
-	/* Acquire pa_tlb_lock lock and check page is present. */
+	/* Acquire page_table_lock and check page is present. */
-	.macro		tlb_lock	spc,ptp,pte,tmp,tmp1,fault
+	.macro		ptl_lock	spc,ptp,pte,tmp,tmp1,fault
-#ifdef CONFIG_SMP
+#ifdef CONFIG_TLB_PTLOCK
 98:	cmpib,COND(=),n	0,\spc,2f
-	load_pa_tlb_lock \tmp
+	get_ptl		\tmp
 1:	LDCW		0(\tmp),\tmp1
 	cmpib,COND(=)	0,\tmp1,1b
 	nop
@@ -463,26 +449,26 @@
 3:
 	.endm
 
-	/* Release pa_tlb_lock lock without reloading lock address.
+	/* Release page_table_lock without reloading lock address.
 	   Note that the values in the register spc are limited to
 	   NR_SPACE_IDS (262144). Thus, the stw instruction always
 	   stores a nonzero value even when register spc is 64 bits.
 	   We use an ordered store to ensure all prior accesses are
 	   performed prior to releasing the lock. */
-	.macro		tlb_unlock0	spc,tmp
+	.macro		ptl_unlock0	spc,tmp
-#ifdef CONFIG_SMP
+#ifdef CONFIG_TLB_PTLOCK
 98:	or,COND(=)	%r0,\spc,%r0
 	stw,ma		\spc,0(\tmp)
 99:	ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP)
 #endif
 	.endm
 
-	/* Release pa_tlb_lock lock. */
+	/* Release page_table_lock. */
-	.macro		tlb_unlock1	spc,tmp
+	.macro		ptl_unlock1	spc,tmp
-#ifdef CONFIG_SMP
+#ifdef CONFIG_TLB_PTLOCK
-98:	load_pa_tlb_lock \tmp
+98:	get_ptl		\tmp
+	ptl_unlock0	\spc,\tmp
 99:	ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP)
-	tlb_unlock0	\spc,\tmp
 #endif
 	.endm
 
@@ -1165,14 +1151,14 @@ dtlb_miss_20w:
 
 	L3_ptep		ptp,pte,t0,va,dtlb_check_alias_20w
 
-	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_20w
+	ptl_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_20w
 	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot,t1
 	
 	idtlbt          pte,prot
 
-	tlb_unlock1	spc,t0
+	ptl_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1191,14 +1177,14 @@ nadtlb_miss_20w:
 
 	L3_ptep		ptp,pte,t0,va,nadtlb_check_alias_20w
 
-	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_20w
+	ptl_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_20w
 	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot,t1
 
 	idtlbt          pte,prot
 
-	tlb_unlock1	spc,t0
+	ptl_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1219,7 +1205,7 @@ dtlb_miss_11:
 
 	L2_ptep		ptp,pte,t0,va,dtlb_check_alias_11
 
-	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_11
+	ptl_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_11
 	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
@@ -1232,7 +1218,7 @@ dtlb_miss_11:
 
 	mtsp		t1, %sr1	/* Restore sr1 */
 
-	tlb_unlock1	spc,t0
+	ptl_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1252,7 +1238,7 @@ nadtlb_miss_11:
 
 	L2_ptep		ptp,pte,t0,va,nadtlb_check_alias_11
 
-	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_11
+	ptl_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_11
 	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
@@ -1265,7 +1251,7 @@ nadtlb_miss_11:
 
 	mtsp		t1, %sr1	/* Restore sr1 */
 
-	tlb_unlock1	spc,t0
+	ptl_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1285,7 +1271,7 @@ dtlb_miss_20:
 
 	L2_ptep		ptp,pte,t0,va,dtlb_check_alias_20
 
-	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_20
+	ptl_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_20
 	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot,t1
@@ -1294,7 +1280,7 @@ dtlb_miss_20:
 
 	idtlbt          pte,prot
 
-	tlb_unlock1	spc,t0
+	ptl_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1313,7 +1299,7 @@ nadtlb_miss_20:
 
 	L2_ptep		ptp,pte,t0,va,nadtlb_check_alias_20
 
-	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_20
+	ptl_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_20
 	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot,t1
@@ -1322,7 +1308,7 @@ nadtlb_miss_20:
 	
 	idtlbt		pte,prot
 
-	tlb_unlock1	spc,t0
+	ptl_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1422,14 +1408,14 @@ itlb_miss_20w:
 
 	L3_ptep		ptp,pte,t0,va,itlb_fault
 
-	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
+	ptl_lock	spc,ptp,pte,t0,t1,itlb_fault
 	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot,t1
 	
 	iitlbt          pte,prot
 
-	tlb_unlock1	spc,t0
+	ptl_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1446,14 +1432,14 @@ naitlb_miss_20w:
 
 	L3_ptep		ptp,pte,t0,va,naitlb_check_alias_20w
 
-	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_20w
+	ptl_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_20w
 	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot,t1
 
 	iitlbt          pte,prot
 
-	tlb_unlock1	spc,t0
+	ptl_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1474,7 +1460,7 @@ itlb_miss_11:
 
 	L2_ptep		ptp,pte,t0,va,itlb_fault
 
-	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
+	ptl_lock	spc,ptp,pte,t0,t1,itlb_fault
 	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
@@ -1487,7 +1473,7 @@ itlb_miss_11:
 
 	mtsp		t1, %sr1	/* Restore sr1 */
 
-	tlb_unlock1	spc,t0
+	ptl_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1498,7 +1484,7 @@ naitlb_miss_11:
 
 	L2_ptep		ptp,pte,t0,va,naitlb_check_alias_11
 
-	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_11
+	ptl_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_11
 	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
@@ -1511,7 +1497,7 @@ naitlb_miss_11:
 
 	mtsp		t1, %sr1	/* Restore sr1 */
 
-	tlb_unlock1	spc,t0
+	ptl_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1532,7 +1518,7 @@ itlb_miss_20:
 
 	L2_ptep		ptp,pte,t0,va,itlb_fault
 
-	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
+	ptl_lock	spc,ptp,pte,t0,t1,itlb_fault
 	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot,t1
@@ -1541,7 +1527,7 @@ itlb_miss_20:
 
 	iitlbt          pte,prot
 
-	tlb_unlock1	spc,t0
+	ptl_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1552,7 +1538,7 @@ naitlb_miss_20:
 
 	L2_ptep		ptp,pte,t0,va,naitlb_check_alias_20
 
-	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_20
+	ptl_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_20
 	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot,t1
@@ -1561,7 +1547,7 @@ naitlb_miss_20:
 
 	iitlbt          pte,prot
 
-	tlb_unlock1	spc,t0
+	ptl_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1584,14 +1570,14 @@ dbit_trap_20w:
 
 	L3_ptep		ptp,pte,t0,va,dbit_fault
 
-	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
+	ptl_lock	spc,ptp,pte,t0,t1,dbit_fault
 	update_dirty	ptp,pte,t1
 
 	make_insert_tlb	spc,pte,prot,t1
 		
 	idtlbt          pte,prot
 
-	tlb_unlock0	spc,t0
+	ptl_unlock0	spc,t0
 	rfir
 	nop
 #else
@@ -1604,7 +1590,7 @@ dbit_trap_11:
 
 	L2_ptep		ptp,pte,t0,va,dbit_fault
 
-	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
+	ptl_lock	spc,ptp,pte,t0,t1,dbit_fault
 	update_dirty	ptp,pte,t1
 
 	make_insert_tlb_11	spc,pte,prot
@@ -1617,7 +1603,7 @@ dbit_trap_11:
 
 	mtsp            t1, %sr1     /* Restore sr1 */
 
-	tlb_unlock0	spc,t0
+	ptl_unlock0	spc,t0
 	rfir
 	nop
 
@@ -1628,7 +1614,7 @@ dbit_trap_20:
 
 	L2_ptep		ptp,pte,t0,va,dbit_fault
 
-	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
+	ptl_lock	spc,ptp,pte,t0,t1,dbit_fault
 	update_dirty	ptp,pte,t1
 
 	make_insert_tlb	spc,pte,prot,t1
@@ -1637,7 +1623,7 @@ dbit_trap_20:
 	
 	idtlbt		pte,prot
 
-	tlb_unlock0	spc,t0
+	ptl_unlock0	spc,t0
 	rfir
 	nop
 #endif

arch/parisc/kernel/hpmc.S

@@ -289,13 +289,3 @@ os_hpmc_6:
 	b .
 	nop
 	.align 16	/* make function length multiple of 16 bytes */
-.os_hpmc_end:
-
-
-	__INITRODATA
-.globl os_hpmc_size
-	.align 4
-	.type   os_hpmc_size, @object
-	.size   os_hpmc_size, 4
-os_hpmc_size:
-	.word .os_hpmc_end-.os_hpmc

arch/parisc/kernel/irq.c

@@ -373,7 +373,11 @@ static inline int eirr_to_irq(unsigned long eirr)
 /*
  * IRQ STACK - used for irq handler
  */
+#ifdef CONFIG_64BIT
+#define IRQ_STACK_SIZE      (4096 << 4) /* 64k irq stack size */
+#else
 #define IRQ_STACK_SIZE      (4096 << 3) /* 32k irq stack size */
+#endif
 
 union irq_stack_union {
 	unsigned long stack[IRQ_STACK_SIZE/sizeof(unsigned long)];

arch/parisc/kernel/process.c

@@ -260,6 +260,8 @@ get_wchan(struct task_struct *p)
 	do {
 		if (unwind_once(&info) < 0)
 			return 0;
+		if (p->state == TASK_RUNNING)
+                        return 0;
 		ip = info.ip;
 		if (!in_sched_functions(ip))
 			return ip;

arch/parisc/kernel/traps.c

@@ -798,14 +798,13 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 
 void __init initialize_ivt(const void *iva)
 {
-	extern u32 os_hpmc_size;
 	extern const u32 os_hpmc[];
 
 	int i;
 	u32 check = 0;
 	u32 *ivap;
 	u32 *hpmcp;
-	u32 length, instr;
+	u32 instr;
 
 	if (strcmp((const char *)iva, "cows can fly"))
 		panic("IVT invalid");
@@ -836,18 +835,14 @@ void __init initialize_ivt(const void *iva)
 
 	/* Setup IVA and compute checksum for HPMC handler */
 	ivap[6] = (u32)__pa(os_hpmc);
-	length = os_hpmc_size;
-	ivap[7] = length;
 
 	hpmcp = (u32 *)os_hpmc;
 
-	for (i=0; i<length/4; i++)
-	    check += *hpmcp++;
-
 	for (i=0; i<8; i++)
 	    check += ivap[i];
 
 	ivap[5] = -check;
+	pr_debug("initialize_ivt: IVA[6] = 0x%08x\n", ivap[6]);
 }
 	
 

arch/parisc/mm/hugetlbpage.c

@@ -142,24 +142,17 @@ static void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t entry)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(pgd_spinlock((mm)->pgd), flags);
 	__set_huge_pte_at(mm, addr, ptep, entry);
-	spin_unlock_irqrestore(pgd_spinlock((mm)->pgd), flags);
 }
 
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep)
 {
-	unsigned long flags;
 	pte_t entry;
 
-	spin_lock_irqsave(pgd_spinlock((mm)->pgd), flags);
 	entry = *ptep;
 	__set_huge_pte_at(mm, addr, ptep, __pte(0));
-	spin_unlock_irqrestore(pgd_spinlock((mm)->pgd), flags);
 
 	return entry;
 }
@@ -168,29 +161,23 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 void huge_ptep_set_wrprotect(struct mm_struct *mm,
 				unsigned long addr, pte_t *ptep)
 {
-	unsigned long flags;
 	pte_t old_pte;
 
-	spin_lock_irqsave(pgd_spinlock((mm)->pgd), flags);
 	old_pte = *ptep;
 	__set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
-	spin_unlock_irqrestore(pgd_spinlock((mm)->pgd), flags);
 }
 
 int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 				unsigned long addr, pte_t *ptep,
 				pte_t pte, int dirty)
 {
-	unsigned long flags;
 	int changed;
 	struct mm_struct *mm = vma->vm_mm;
 
-	spin_lock_irqsave(pgd_spinlock((mm)->pgd), flags);
 	changed = !pte_same(*ptep, pte);
 	if (changed) {
 		__set_huge_pte_at(mm, addr, ptep, pte);
 	}
-	spin_unlock_irqrestore(pgd_spinlock((mm)->pgd), flags);
 	return changed;
 }
 

arch/parisc/mm/init.c

@@ -37,11 +37,6 @@ extern int  data_start;
 extern void parisc_kernel_start(void);	/* Kernel entry point in head.S */
 
 #if CONFIG_PGTABLE_LEVELS == 3
-/* NOTE: This layout exactly conforms to the hybrid L2/L3 page table layout
- * with the first pmd adjacent to the pgd and below it. gcc doesn't actually
- * guarantee that global objects will be laid out in memory in the same order
- * as the order of declaration, so put these in different sections and use
- * the linker script to order them. */
 pmd_t pmd0[PTRS_PER_PMD] __section(".data..vm0.pmd") __attribute__ ((aligned(PAGE_SIZE)));
 #endif
 
@@ -559,6 +554,11 @@ void __init mem_init(void)
 	BUILD_BUG_ON(PGD_ENTRY_SIZE != sizeof(pgd_t));
 	BUILD_BUG_ON(PAGE_SHIFT + BITS_PER_PTE + BITS_PER_PMD + BITS_PER_PGD
 			> BITS_PER_LONG);
+#if CONFIG_PGTABLE_LEVELS == 3
+	BUILD_BUG_ON(PT_INITIAL > PTRS_PER_PMD);
+#else
+	BUILD_BUG_ON(PT_INITIAL > PTRS_PER_PGD);
+#endif
 
 	high_memory = __va((max_pfn << PAGE_SHIFT));
 	set_max_mapnr(max_low_pfn);

fs/binfmt_elf.c

@@ -186,6 +186,7 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec,
 	unsigned char k_rand_bytes[16];
 	int items;
 	elf_addr_t *elf_info;
+	elf_addr_t flags = 0;
 	int ei_index;
 	const struct cred *cred = current_cred();
 	struct vm_area_struct *vma;
@@ -260,7 +261,9 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec,
 	NEW_AUX_ENT(AT_PHENT, sizeof(struct elf_phdr));
 	NEW_AUX_ENT(AT_PHNUM, exec->e_phnum);
 	NEW_AUX_ENT(AT_BASE, interp_load_addr);
-	NEW_AUX_ENT(AT_FLAGS, 0);
+	if (bprm->interp_flags & BINPRM_FLAGS_PRESERVE_ARGV0)
+		flags |= AT_FLAGS_PRESERVE_ARGV0;
+	NEW_AUX_ENT(AT_FLAGS, flags);
 	NEW_AUX_ENT(AT_ENTRY, e_entry);
 	NEW_AUX_ENT(AT_UID, from_kuid_munged(cred->user_ns, cred->uid));
 	NEW_AUX_ENT(AT_EUID, from_kuid_munged(cred->user_ns, cred->euid));

fs/binfmt_elf_fdpic.c

@@ -506,6 +506,7 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
 	char __user *u_platform, *u_base_platform, *p;
 	int loop;
 	int nr;	/* reset for each csp adjustment */
+	unsigned long flags = 0;
 
 #ifdef CONFIG_MMU
 	/* In some cases (e.g. Hyper-Threading), we want to avoid L1 evictions
@@ -648,7 +649,9 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
 	NEW_AUX_ENT(AT_PHENT,	sizeof(struct elf_phdr));
 	NEW_AUX_ENT(AT_PHNUM,	exec_params->hdr.e_phnum);
 	NEW_AUX_ENT(AT_BASE,	interp_params->elfhdr_addr);
-	NEW_AUX_ENT(AT_FLAGS,	0);
+	if (bprm->interp_flags & BINPRM_FLAGS_PRESERVE_ARGV0)
+		flags |= AT_FLAGS_PRESERVE_ARGV0;
+	NEW_AUX_ENT(AT_FLAGS,	flags);
 	NEW_AUX_ENT(AT_ENTRY,	exec_params->entry_addr);
 	NEW_AUX_ENT(AT_UID,	(elf_addr_t) from_kuid_munged(cred->user_ns, cred->uid));
 	NEW_AUX_ENT(AT_EUID,	(elf_addr_t) from_kuid_munged(cred->user_ns, cred->euid));

fs/binfmt_misc.c

@@ -153,7 +153,9 @@ static int load_misc_binary(struct linux_binprm *bprm)
 	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
 		goto ret;
 
-	if (!(fmt->flags & MISC_FMT_PRESERVE_ARGV0)) {
+	if (fmt->flags & MISC_FMT_PRESERVE_ARGV0) {
+		bprm->interp_flags |= BINPRM_FLAGS_PRESERVE_ARGV0;
+	} else {
 		retval = remove_arg_zero(bprm);
 		if (retval)
 			goto ret;

include/linux/binfmts.h

@@ -73,6 +73,10 @@ struct linux_binprm {
 #define BINPRM_FLAGS_PATH_INACCESSIBLE_BIT 2
 #define BINPRM_FLAGS_PATH_INACCESSIBLE (1 << BINPRM_FLAGS_PATH_INACCESSIBLE_BIT)
 
+/* preserve argv0 for the interpreter  */
+#define BINPRM_FLAGS_PRESERVE_ARGV0_BIT 3
+#define BINPRM_FLAGS_PRESERVE_ARGV0 (1 << BINPRM_FLAGS_PRESERVE_ARGV0_BIT)
+
 /* Function parameter for binfmt->coredump */
 struct coredump_params {
 	const kernel_siginfo_t *siginfo;

include/uapi/linux/binfmts.h

@@ -18,4 +18,8 @@ struct pt_regs;
 /* sizeof(linux_binprm->buf) */
 #define BINPRM_BUF_SIZE 256
 
+/* preserve argv0 for the interpreter  */
+#define AT_FLAGS_PRESERVE_ARGV0_BIT 0
+#define AT_FLAGS_PRESERVE_ARGV0 (1 << AT_FLAGS_PRESERVE_ARGV0_BIT)
+
 #endif /* _UAPI_LINUX_BINFMTS_H */