lpar.c

linux内核源码

		DBG_LOW(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r);

	/* Now fill in the actual HPTE */
	/* Set CEC cookie to 0         */
	/* Zero page = 0               */
	/* I-cache Invalidate = 0      */
	/* I-cache synchronize = 0     */
	/* Exact = 0                   */
	flags = 0;

	/* Make pHyp happy */
	if (rflags & (_PAGE_GUARDED|_PAGE_NO_CACHE))
		hpte_r &= ~_PAGE_COHERENT;

	lpar_rc = plpar_pte_enter(flags, hpte_group, hpte_v, hpte_r, &slot);
	if (unlikely(lpar_rc == H_PTEG_FULL)) {
		if (!(vflags & HPTE_V_BOLTED))
			DBG_LOW(" full\n");
		return -1;
	}

	/*
	 * Since we try and ioremap PHBs we don't own, the pte insert
	 * will fail. However we must catch the failure in hash_page
	 * or we will loop forever, so return -2 in this case.
	 */
	if (unlikely(lpar_rc != H_SUCCESS)) {
		if (!(vflags & HPTE_V_BOLTED))
			DBG_LOW(" lpar err %d\n", lpar_rc);
		return -2;
	}
	if (!(vflags & HPTE_V_BOLTED))
		DBG_LOW(" -> slot: %d\n", slot & 7);

	/* Because of iSeries, we have to pass down the secondary
	 * bucket bit here as well
	 */
	return (slot & 7) | (!!(vflags & HPTE_V_SECONDARY) << 3);
}

static DEFINE_SPINLOCK(pSeries_lpar_tlbie_lock);

static long pSeries_lpar_hpte_remove(unsigned long hpte_group)
{
	unsigned long slot_offset;
	unsigned long lpar_rc;
	int i;
	unsigned long dummy1, dummy2;

	/* pick a random slot to start at */
	slot_offset = mftb() & 0x7;

	for (i = 0; i < HPTES_PER_GROUP; i++) {

		/* don't remove a bolted entry */
		lpar_rc = plpar_pte_remove(H_ANDCOND, hpte_group + slot_offset,
					   (0x1UL << 4), &dummy1, &dummy2);
		if (lpar_rc == H_SUCCESS)
			return i;
		BUG_ON(lpar_rc != H_NOT_FOUND);

		slot_offset++;
		slot_offset &= 0x7;
	}

	return -1;
}

static void pSeries_lpar_hptab_clear(void)
{
	unsigned long size_bytes = 1UL << ppc64_pft_size;
	unsigned long hpte_count = size_bytes >> 4;
	unsigned long dummy1, dummy2, dword0;
	long lpar_rc;
	int i;

	/* TODO: Use bulk call */
	for (i = 0; i < hpte_count; i++) {
		/* dont remove HPTEs with VRMA mappings */
		lpar_rc = plpar_pte_remove_raw(H_ANDCOND, i, HPTE_V_1TB_SEG,
						&dummy1, &dummy2);
		if (lpar_rc == H_NOT_FOUND) {
			lpar_rc = plpar_pte_read_raw(0, i, &dword0, &dummy1);
			if (!lpar_rc && ((dword0 & HPTE_V_VRMA_MASK)
				!= HPTE_V_VRMA_MASK))
				/* Can be hpte for 1TB Seg. So remove it */
				plpar_pte_remove_raw(0, i, 0, &dummy1, &dummy2);
		}
	}
}

/*
 * This computes the AVPN and B fields of the first dword of a HPTE,
 * for use when we want to match an existing PTE.  The bottom 7 bits
 * of the returned value are zero.
 */
static inline unsigned long hpte_encode_avpn(unsigned long va, int psize,
					     int ssize)
{
	unsigned long v;

	v = (va >> 23) & ~(mmu_psize_defs[psize].avpnm);
	v <<= HPTE_V_AVPN_SHIFT;
	v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT;
	return v;
}

/*
 * NOTE: for updatepp ops we are fortunate that the linux "newpp" bits and
 * the low 3 bits of flags happen to line up.  So no transform is needed.
 * We can probably optimize here and assume the high bits of newpp are
 * already zero.  For now I am paranoid.
 */
static long pSeries_lpar_hpte_updatepp(unsigned long slot,
				       unsigned long newpp,
				       unsigned long va,
				       int psize, int ssize, int local)
{
	unsigned long lpar_rc;
	unsigned long flags = (newpp & 7) | H_AVPN;
	unsigned long want_v;

	want_v = hpte_encode_avpn(va, psize, ssize);

	DBG_LOW("    update: avpnv=%016lx, hash=%016lx, f=%x, psize: %d ... ",
		want_v, slot, flags, psize);

	lpar_rc = plpar_pte_protect(flags, slot, want_v);

	if (lpar_rc == H_NOT_FOUND) {
		DBG_LOW("not found !\n");
		return -1;
	}

	DBG_LOW("ok\n");

	BUG_ON(lpar_rc != H_SUCCESS);

	return 0;
}

static unsigned long pSeries_lpar_hpte_getword0(unsigned long slot)
{
	unsigned long dword0;
	unsigned long lpar_rc;
	unsigned long dummy_word1;
	unsigned long flags;

	/* Read 1 pte at a time                        */
	/* Do not need RPN to logical page translation */
	/* No cross CEC PFT access                     */
	flags = 0;

	lpar_rc = plpar_pte_read(flags, slot, &dword0, &dummy_word1);

	BUG_ON(lpar_rc != H_SUCCESS);

	return dword0;
}

static long pSeries_lpar_hpte_find(unsigned long va, int psize, int ssize)
{
	unsigned long hash;
	unsigned long i;
	long slot;
	unsigned long want_v, hpte_v;

	hash = hpt_hash(va, mmu_psize_defs[psize].shift, ssize);
	want_v = hpte_encode_avpn(va, psize, ssize);

	/* Bolted entries are always in the primary group */
	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
	for (i = 0; i < HPTES_PER_GROUP; i++) {
		hpte_v = pSeries_lpar_hpte_getword0(slot);

		if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID))
			/* HPTE matches */
			return slot;
		++slot;
	}

	return -1;
} 

static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp,
					     unsigned long ea,
					     int psize, int ssize)
{
	unsigned long lpar_rc, slot, vsid, va, flags;

	vsid = get_kernel_vsid(ea, ssize);
	va = hpt_va(ea, vsid, ssize);

	slot = pSeries_lpar_hpte_find(va, psize, ssize);
	BUG_ON(slot == -1);

	flags = newpp & 7;
	lpar_rc = plpar_pte_protect(flags, slot, 0);

	BUG_ON(lpar_rc != H_SUCCESS);
}

static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long va,
					 int psize, int ssize, int local)
{
	unsigned long want_v;
	unsigned long lpar_rc;
	unsigned long dummy1, dummy2;

	DBG_LOW("    inval : slot=%lx, va=%016lx, psize: %d, local: %d",
		slot, va, psize, local);

	want_v = hpte_encode_avpn(va, psize, ssize);
	lpar_rc = plpar_pte_remove(H_AVPN, slot, want_v, &dummy1, &dummy2);
	if (lpar_rc == H_NOT_FOUND)
		return;

	BUG_ON(lpar_rc != H_SUCCESS);
}

/* Flag bits for H_BULK_REMOVE */
#define HBR_REQUEST	0x4000000000000000UL
#define HBR_RESPONSE	0x8000000000000000UL
#define HBR_END		0xc000000000000000UL
#define HBR_AVPN	0x0200000000000000UL
#define HBR_ANDCOND	0x0100000000000000UL

/*
 * Take a spinlock around flushes to avoid bouncing the hypervisor tlbie
 * lock.
 */
static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
{
	unsigned long i, pix, rc;
	unsigned long flags = 0;
	struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
	int lock_tlbie = !cpu_has_feature(CPU_FTR_LOCKLESS_TLBIE);
	unsigned long param[9];
	unsigned long va;
	unsigned long hash, index, shift, hidx, slot;
	real_pte_t pte;
	int psize, ssize;

	if (lock_tlbie)
		spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);

	psize = batch->psize;
	ssize = batch->ssize;
	pix = 0;
	for (i = 0; i < number; i++) {
		va = batch->vaddr[i];
		pte = batch->pte[i];
		pte_iterate_hashed_subpages(pte, psize, va, index, shift) {
			hash = hpt_hash(va, shift, ssize);
			hidx = __rpte_to_hidx(pte, index);
			if (hidx & _PTEIDX_SECONDARY)
				hash = ~hash;
			slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
			slot += hidx & _PTEIDX_GROUP_IX;
			if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
				pSeries_lpar_hpte_invalidate(slot, va, psize,
							     ssize, local);
			} else {
				param[pix] = HBR_REQUEST | HBR_AVPN | slot;
				param[pix+1] = hpte_encode_avpn(va, psize,
								ssize);
				pix += 2;
				if (pix == 8) {
					rc = plpar_hcall9(H_BULK_REMOVE, param,
						param[0], param[1], param[2],
						param[3], param[4], param[5],
						param[6], param[7]);
					BUG_ON(rc != H_SUCCESS);
					pix = 0;
				}
			}
		} pte_iterate_hashed_end();
	}
	if (pix) {
		param[pix] = HBR_END;
		rc = plpar_hcall9(H_BULK_REMOVE, param, param[0], param[1],
				  param[2], param[3], param[4], param[5],
				  param[6], param[7]);
		BUG_ON(rc != H_SUCCESS);
	}

	if (lock_tlbie)
		spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags);
}

void __init hpte_init_lpar(void)
{
	ppc_md.hpte_invalidate	= pSeries_lpar_hpte_invalidate;
	ppc_md.hpte_updatepp	= pSeries_lpar_hpte_updatepp;
	ppc_md.hpte_updateboltedpp = pSeries_lpar_hpte_updateboltedpp;
	ppc_md.hpte_insert	= pSeries_lpar_hpte_insert;
	ppc_md.hpte_remove	= pSeries_lpar_hpte_remove;
	ppc_md.flush_hash_range	= pSeries_lpar_flush_hash_range;
	ppc_md.hpte_clear_all   = pSeries_lpar_hptab_clear;
}