Commit a7428c3d authored by Paolo Bonzini's avatar Paolo Bonzini
Browse files

Merge tag 'kvm-s390-next-20140825' of... 

Merge tag 'kvm-s390-next-20140825' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

KVM: s390: Fixes and features for 3.18 part 1

1. The usual cleanups: get rid of duplicate code, use defines, factor
   out the sync_reg handling, additional docs for sync_regs, better
   error handling on interrupt injection
2. We use KVM_REQ_TLB_FLUSH instead of open coding tlb flushes
3. Additional registers for kvm_run sync regs. This is usually not
   needed in the fast path due to eventfd/irqfd, but kvm stat claims
   that we reduced the overhead of console output by ~50% on my system
4. A rework of the gmap infrastructure. This is the 2nd step towards
   host large page support (after getting rid of the storage key
   dependency). We introduces two radix trees to store the guest-to-host
   and host-to-guest translations. This gets us rid of most of
   the page-table walks in the gmap code. Only one in __gmap_link is left,
   this one is required to link the shadow page table to the process page
   table. Finally this contains the plumbing to support gmap page tables
   with less than 5 levels.
parents 54ad89b0 f079e952

Documentation/virtual/kvm/api.txt

+4 −0
Original line number Diff line number Diff line
@@ -2861,6 +2861,10 @@ kvm_valid_regs for specific bits. These bits are architecture specific 
and usually define the validity of a groups of registers. (e.g. one bit

 for general purpose registers)



Please note that the kernel is allowed to use the kvm_run structure as the

primary storage for certain register types. Therefore, the kernel may use the

values in kvm_run even if the corresponding bit in kvm_dirty_regs is not set.



};

arch/s390/include/asm/pgalloc.h

+4 −4
Original line number Diff line number Diff line
@@ -18,9 +18,9 @@ 
unsigned long *crst_table_alloc(struct mm_struct *);

void crst_table_free(struct mm_struct *, unsigned long *);



unsigned long *page_table_alloc(struct mm_struct *, unsigned long);

unsigned long *page_table_alloc(struct mm_struct *);

void page_table_free(struct mm_struct *, unsigned long *);

void page_table_free_rcu(struct mmu_gather *, unsigned long *);

void page_table_free_rcu(struct mmu_gather *, unsigned long *, unsigned long);



void page_table_reset_pgste(struct mm_struct *, unsigned long, unsigned long,

			    bool init_skey);
@@ -145,8 +145,8 @@ static inline void pmd_populate(struct mm_struct *mm, 
/*

 * page table entry allocation/free routines.

 */

#define pte_alloc_one_kernel(mm, vmaddr) ((pte_t *) page_table_alloc(mm, vmaddr))

#define pte_alloc_one(mm, vmaddr) ((pte_t *) page_table_alloc(mm, vmaddr))

#define pte_alloc_one_kernel(mm, vmaddr) ((pte_t *) page_table_alloc(mm))

#define pte_alloc_one(mm, vmaddr) ((pte_t *) page_table_alloc(mm))



#define pte_free_kernel(mm, pte) page_table_free(mm, (unsigned long *) pte)

#define pte_free(mm, pte) page_table_free(mm, (unsigned long *) pte)

arch/s390/include/asm/pgtable.h

+29 −43
Original line number Diff line number Diff line
@@ -30,6 +30,7 @@ 
#include <linux/sched.h>

#include <linux/mm_types.h>

#include <linux/page-flags.h>

#include <linux/radix-tree.h>

#include <asm/bug.h>

#include <asm/page.h>
@@ -789,82 +790,67 @@ static inline pgste_t pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry) 


/**

 * struct gmap_struct - guest address space

 * @crst_list: list of all crst tables used in the guest address space

 * @mm: pointer to the parent mm_struct

 * @guest_to_host: radix tree with guest to host address translation

 * @host_to_guest: radix tree with pointer to segment table entries

 * @guest_table_lock: spinlock to protect all entries in the guest page table

 * @table: pointer to the page directory

 * @asce: address space control element for gmap page table

 * @crst_list: list of all crst tables used in the guest address space

 * @pfault_enabled: defines if pfaults are applicable for the guest

 */

struct gmap {

	struct list_head list;

	struct list_head crst_list;

	struct mm_struct *mm;

	struct radix_tree_root guest_to_host;

	struct radix_tree_root host_to_guest;

	spinlock_t guest_table_lock;

	unsigned long *table;

	unsigned long asce;

	unsigned long asce_end;

	void *private;

	struct list_head crst_list;

	bool pfault_enabled;

};



/**

 * struct gmap_rmap - reverse mapping for segment table entries

 * @gmap: pointer to the gmap_struct

 * @entry: pointer to a segment table entry

 * @vmaddr: virtual address in the guest address space

 */

struct gmap_rmap {

	struct list_head list;

	struct gmap *gmap;

	unsigned long *entry;

	unsigned long vmaddr;

};



/**

 * struct gmap_pgtable - gmap information attached to a page table

 * @vmaddr: address of the 1MB segment in the process virtual memory

 * @mapper: list of segment table entries mapping a page table

 */

struct gmap_pgtable {

	unsigned long vmaddr;

	struct list_head mapper;

};



/**

 * struct gmap_notifier - notify function block for page invalidation

 * @notifier_call: address of callback function

 */

struct gmap_notifier {

	struct list_head list;

	void (*notifier_call)(struct gmap *gmap, unsigned long address);

	void (*notifier_call)(struct gmap *gmap, unsigned long gaddr);

};



struct gmap *gmap_alloc(struct mm_struct *mm);

struct gmap *gmap_alloc(struct mm_struct *mm, unsigned long limit);

void gmap_free(struct gmap *gmap);

void gmap_enable(struct gmap *gmap);

void gmap_disable(struct gmap *gmap);

int gmap_map_segment(struct gmap *gmap, unsigned long from,

		     unsigned long to, unsigned long len);

int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len);

unsigned long __gmap_translate(unsigned long address, struct gmap *);

unsigned long gmap_translate(unsigned long address, struct gmap *);

unsigned long __gmap_fault(unsigned long address, struct gmap *);

unsigned long gmap_fault(unsigned long address, struct gmap *);

void gmap_discard(unsigned long from, unsigned long to, struct gmap *);

void __gmap_zap(unsigned long address, struct gmap *);

unsigned long __gmap_translate(struct gmap *, unsigned long gaddr);

unsigned long gmap_translate(struct gmap *, unsigned long gaddr);

int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr);

int gmap_fault(struct gmap *, unsigned long gaddr, unsigned int fault_flags);

void gmap_discard(struct gmap *, unsigned long from, unsigned long to);

void __gmap_zap(struct gmap *, unsigned long gaddr);

bool gmap_test_and_clear_dirty(unsigned long address, struct gmap *);





void gmap_register_ipte_notifier(struct gmap_notifier *);

void gmap_unregister_ipte_notifier(struct gmap_notifier *);

int gmap_ipte_notify(struct gmap *, unsigned long start, unsigned long len);

void gmap_do_ipte_notify(struct mm_struct *, pte_t *);

void gmap_do_ipte_notify(struct mm_struct *, unsigned long addr, pte_t *);



static inline pgste_t pgste_ipte_notify(struct mm_struct *mm,

					unsigned long addr,

					pte_t *ptep, pgste_t pgste)

{

#ifdef CONFIG_PGSTE

	if (pgste_val(pgste) & PGSTE_IN_BIT) {

		pgste_val(pgste) &= ~PGSTE_IN_BIT;

		gmap_do_ipte_notify(mm, ptep);

		gmap_do_ipte_notify(mm, addr, ptep);

	}

#endif

	return pgste;
@@ -1110,7 +1096,7 @@ static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm, 
	pgste_val(pgste) &= ~PGSTE_UC_BIT;

	pte = *ptep;

	if (dirty && (pte_val(pte) & _PAGE_PRESENT)) {

		pgste = pgste_ipte_notify(mm, ptep, pgste);

		pgste = pgste_ipte_notify(mm, addr, ptep, pgste);

		__ptep_ipte(addr, ptep);

		if (MACHINE_HAS_ESOP || !(pte_val(pte) & _PAGE_WRITE))

			pte_val(pte) |= _PAGE_PROTECT;
@@ -1132,7 +1118,7 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, 


	if (mm_has_pgste(vma->vm_mm)) {

		pgste = pgste_get_lock(ptep);

		pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste);

		pgste = pgste_ipte_notify(vma->vm_mm, addr, ptep, pgste);

	}



	pte = *ptep;
@@ -1178,7 +1164,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, 


	if (mm_has_pgste(mm)) {

		pgste = pgste_get_lock(ptep);

		pgste = pgste_ipte_notify(mm, ptep, pgste);

		pgste = pgste_ipte_notify(mm, address, ptep, pgste);

	}



	pte = *ptep;
@@ -1202,7 +1188,7 @@ static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, 


	if (mm_has_pgste(mm)) {

		pgste = pgste_get_lock(ptep);

		pgste_ipte_notify(mm, ptep, pgste);

		pgste_ipte_notify(mm, address, ptep, pgste);

	}



	pte = *ptep;
@@ -1239,7 +1225,7 @@ static inline pte_t ptep_clear_flush(struct vm_area_struct *vma, 


	if (mm_has_pgste(vma->vm_mm)) {

		pgste = pgste_get_lock(ptep);

		pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste);

		pgste = pgste_ipte_notify(vma->vm_mm, address, ptep, pgste);

	}



	pte = *ptep;
@@ -1273,7 +1259,7 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, 


	if (!full && mm_has_pgste(mm)) {

		pgste = pgste_get_lock(ptep);

		pgste = pgste_ipte_notify(mm, ptep, pgste);

		pgste = pgste_ipte_notify(mm, address, ptep, pgste);

	}



	pte = *ptep;
@@ -1298,7 +1284,7 @@ static inline pte_t ptep_set_wrprotect(struct mm_struct *mm, 
	if (pte_write(pte)) {

		if (mm_has_pgste(mm)) {

			pgste = pgste_get_lock(ptep);

			pgste = pgste_ipte_notify(mm, ptep, pgste);

			pgste = pgste_ipte_notify(mm, address, ptep, pgste);

		}



		ptep_flush_lazy(mm, address, ptep);
@@ -1324,7 +1310,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, 
		return 0;

	if (mm_has_pgste(vma->vm_mm)) {

		pgste = pgste_get_lock(ptep);

		pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste);

		pgste = pgste_ipte_notify(vma->vm_mm, address, ptep, pgste);

	}



	ptep_flush_direct(vma->vm_mm, address, ptep);

arch/s390/include/asm/tlb.h

+1 −1
Original line number Diff line number Diff line
@@ -105,7 +105,7 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) 
static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,

				unsigned long address)

{

	page_table_free_rcu(tlb, (unsigned long *) pte);

	page_table_free_rcu(tlb, (unsigned long *) pte, address);

}



/*

arch/s390/include/uapi/asm/kvm.h

+10 −0
Original line number Diff line number Diff line
@@ -111,12 +111,22 @@ struct kvm_guest_debug_arch { 
#define KVM_SYNC_GPRS   (1UL << 1)

#define KVM_SYNC_ACRS   (1UL << 2)

#define KVM_SYNC_CRS    (1UL << 3)

#define KVM_SYNC_ARCH0  (1UL << 4)

#define KVM_SYNC_PFAULT (1UL << 5)

/* definition of registers in kvm_run */

struct kvm_sync_regs {

	__u64 prefix;	/* prefix register */

	__u64 gprs[16];	/* general purpose registers */

	__u32 acrs[16];	/* access registers */

	__u64 crs[16];	/* control registers */

	__u64 todpr;	/* tod programmable register [ARCH0] */

	__u64 cputm;	/* cpu timer [ARCH0] */

	__u64 ckc;	/* clock comparator [ARCH0] */

	__u64 pp;	/* program parameter [ARCH0] */

	__u64 gbea;	/* guest breaking-event address [ARCH0] */

	__u64 pft;	/* pfault token [PFAULT] */

	__u64 pfs;	/* pfault select [PFAULT] */

	__u64 pfc;	/* pfault compare [PFAULT] */

};



#define KVM_REG_S390_TODPR	(KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1)

CRA Git | Maintained and supported by SUSTech CRA and CCSE