Newer
Older
/*
* pSeries_lpar.c
* Copyright (C) 2001 Todd Inglett, IBM Corporation
*
* pSeries LPAR support.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
/* Enables debugging of low-level hash table routines - careful! */
#undef DEBUG
#include <linux/kernel.h>
#include <linux/dma-mapping.h>
#include <linux/console.h>
#include <linux/export.h>
#include <asm/processor.h>
#include <asm/mmu.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/machdep.h>
#include <asm/mmu_context.h>
#include <asm/iommu.h>
#include <asm/tlbflush.h>
#include <asm/tlb.h>
#include <asm/prom.h>
#include <asm/cputable.h>
#include <asm/trace.h>
#include <asm/firmware.h>
#include "plpar_wrappers.h"
#include "pseries.h"
/* 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
EXPORT_SYMBOL(plpar_hcall9);
extern void pSeries_find_serial_port(void);
void vpa_init(int cpu)
{
int hwcpu = get_hard_smp_processor_id(cpu);
struct paca_struct *pp;
struct dtl_entry *dtl;
if (cpu_has_feature(CPU_FTR_ALTIVEC))
lppaca_of(cpu).vmxregs_in_use = 1;
if (cpu_has_feature(CPU_FTR_ARCH_207S))
lppaca_of(cpu).ebb_regs_in_use = 1;
addr = __pa(&lppaca_of(cpu));
pr_err("WARNING: VPA registration for cpu %d (hw %d) of area "
"%lx failed with %ld\n", cpu, hwcpu, addr, ret);
return;
}
/*
* PAPR says this feature is SLB-Buffer but firmware never
* reports that. All SPLPAR support SLB shadow buffer.
*/
addr = __pa(&slb_shadow[cpu]);
if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
ret = register_slb_shadow(hwcpu, addr);
if (ret)
pr_err("WARNING: SLB shadow buffer registration for "
"cpu %d (hw %d) of area %lx failed with %ld\n",
cpu, hwcpu, addr, ret);
/*
* Register dispatch trace log, if one has been allocated.
*/
pp = &paca[cpu];
dtl = pp->dispatch_log;
if (dtl) {
pp->dtl_ridx = 0;
pp->dtl_curr = dtl;
lppaca_of(cpu).dtl_idx = 0;
/* hypervisor reads buffer length from this field */
dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES;
ret = register_dtl(hwcpu, __pa(dtl));
if (ret)
pr_err("WARNING: DTL registration of cpu %d (hw %d) "
"failed with %ld\n", smp_processor_id(),
hwcpu, ret);
lppaca_of(cpu).dtl_enable_mask = 2;
}
static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
unsigned long vpn, unsigned long pa,
unsigned long rflags, unsigned long vflags,
int psize, int apsize, int ssize)
{
unsigned long lpar_rc;
unsigned long flags;
unsigned long slot;
unsigned long hpte_v, hpte_r;
if (!(vflags & HPTE_V_BOLTED))
pr_devel("hpte_insert(group=%lx, vpn=%016lx, "
"pa=%016lx, rflags=%lx, vflags=%lx, psize=%d)\n",
hpte_group, vpn, pa, rflags, vflags, psize);
hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
if (!(vflags & HPTE_V_BOLTED))
pr_devel(" 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;
if ((rflags & _PAGE_NO_CACHE) & !(rflags & _PAGE_WRITETHRU))
hpte_r &= ~_PAGE_COHERENT;
if (firmware_has_feature(FW_FEATURE_XCMO) && !(hpte_r & HPTE_R_N))
flags |= H_COALESCE_CAND;
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))
pr_devel(" full\n");
/*
* 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))
pr_devel(" lpar err %ld\n", lpar_rc);
}
if (!(vflags & HPTE_V_BOLTED))
pr_devel(" -> slot: %lu\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)
Michael Wolf
committed
/*
* The test for adjunct partition is performed before the
* ANDCOND test. H_RESOURCE may be returned, so we need to
* check for that as well.
*/
BUG_ON(lpar_rc != H_NOT_FOUND && lpar_rc != H_RESOURCE);
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;
struct {
unsigned long pteh;
unsigned long ptel;
} ptes[4];
unsigned long i, j;
/* Read in batches of 4,
* invalidate only valid entries not in the VRMA
* hpte_count will be a multiple of 4
*/
for (i = 0; i < hpte_count; i += 4) {
lpar_rc = plpar_pte_read_4_raw(0, i, (void *)ptes);
if (lpar_rc != H_SUCCESS)
continue;
for (j = 0; j < 4; j++){
if ((ptes[j].pteh & HPTE_V_VRMA_MASK) ==
HPTE_V_VRMA_MASK)
continue;
if (ptes[j].pteh & HPTE_V_VALID)
plpar_pte_remove_raw(0, i + j, 0,
&(ptes[j].pteh), &(ptes[j].ptel));
}
/*
* 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,
Aneesh Kumar K.V
committed
int psize, int apsize,
int ssize, int local)
{
unsigned long lpar_rc;
unsigned long flags = (newpp & 7) | H_AVPN;
want_v = hpte_encode_avpn(vpn, psize, ssize);
pr_devel(" update: avpnv=%016lx, hash=%016lx, f=%lx, psize: %d ...",
want_v, slot, flags, psize);
lpar_rc = plpar_pte_protect(flags, slot, want_v);
if (lpar_rc == H_NOT_FOUND) {
pr_devel("not found !\n");
pr_devel("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);
static long pSeries_lpar_hpte_find(unsigned long vpn, int psize, int ssize)
hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize);
want_v = hpte_encode_avpn(vpn, 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 vpn;
unsigned long lpar_rc, slot, vsid, flags;
vpn = hpt_vpn(ea, vsid, ssize);
slot = pSeries_lpar_hpte_find(vpn, 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 vpn,
Aneesh Kumar K.V
committed
int psize, int apsize,
int ssize, int local)
unsigned long lpar_rc;
unsigned long dummy1, dummy2;
pr_devel(" inval : slot=%lx, vpn=%016lx, psize: %d, local: %d\n",
slot, vpn, psize, local);
want_v = hpte_encode_avpn(vpn, psize, ssize);
lpar_rc = plpar_pte_remove(H_AVPN, slot, want_v, &dummy1, &dummy2);
if (lpar_rc == H_NOT_FOUND)
BUG_ON(lpar_rc != H_SUCCESS);
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
/*
* Limit iterations holding pSeries_lpar_tlbie_lock to 3. We also need
* to make sure that we avoid bouncing the hypervisor tlbie lock.
*/
#define PPC64_HUGE_HPTE_BATCH 12
static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
unsigned long *vpn, int count,
int psize, int ssize)
{
unsigned long param[8];
int i = 0, pix = 0, rc;
unsigned long flags = 0;
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
if (lock_tlbie)
spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);
for (i = 0; i < count; i++) {
if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
pSeries_lpar_hpte_invalidate(slot[i], vpn[i], psize, 0,
ssize, 0);
} else {
param[pix] = HBR_REQUEST | HBR_AVPN | slot[i];
param[pix+1] = hpte_encode_avpn(vpn[i], 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;
}
}
}
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);
}
static void pSeries_lpar_hugepage_invalidate(struct mm_struct *mm,
unsigned char *hpte_slot_array,
unsigned long addr, int psize)
{
int ssize = 0, i, index = 0;
unsigned long s_addr = addr;
unsigned int max_hpte_count, valid;
unsigned long vpn_array[PPC64_HUGE_HPTE_BATCH];
unsigned long slot_array[PPC64_HUGE_HPTE_BATCH];
unsigned long shift, hidx, vpn = 0, vsid, hash, slot;
shift = mmu_psize_defs[psize].shift;
max_hpte_count = 1U << (PMD_SHIFT - shift);
for (i = 0; i < max_hpte_count; i++) {
valid = hpte_valid(hpte_slot_array, i);
if (!valid)
continue;
hidx = hpte_hash_index(hpte_slot_array, i);
/* get the vpn */
addr = s_addr + (i * (1ul << shift));
if (!is_kernel_addr(addr)) {
ssize = user_segment_size(addr);
vsid = get_vsid(mm->context.id, addr, ssize);
WARN_ON(vsid == 0);
} else {
vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
ssize = mmu_kernel_ssize;
}
vpn = hpt_vpn(addr, vsid, ssize);
hash = hpt_hash(vpn, shift, ssize);
if (hidx & _PTEIDX_SECONDARY)
hash = ~hash;
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
slot += hidx & _PTEIDX_GROUP_IX;
slot_array[index] = slot;
vpn_array[index] = vpn;
if (index == PPC64_HUGE_HPTE_BATCH - 1) {
/*
* Now do a bluk invalidate
*/
__pSeries_lpar_hugepage_invalidate(slot_array,
vpn_array,
PPC64_HUGE_HPTE_BATCH,
psize, ssize);
index = 0;
} else
index++;
}
if (index)
__pSeries_lpar_hugepage_invalidate(slot_array, vpn_array,
index, psize, ssize);
}
static void pSeries_lpar_hpte_removebolted(unsigned long ea,
int psize, int ssize)
{
unsigned long vpn;
unsigned long slot, vsid;
vsid = get_kernel_vsid(ea, ssize);
vpn = hpt_vpn(ea, vsid, ssize);
slot = pSeries_lpar_hpte_find(vpn, psize, ssize);
BUG_ON(slot == -1);
Aneesh Kumar K.V
committed
/*
* lpar doesn't use the passed actual page size
*/
pSeries_lpar_hpte_invalidate(slot, vpn, psize, 0, ssize, 0);
}
/*
* 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 = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
unsigned long param[9];
unsigned long hash, index, shift, hidx, slot;
real_pte_t pte;
if (lock_tlbie)
spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);
psize = batch->psize;
pix = 0;
for (i = 0; i < number; i++) {
pte = batch->pte[i];
pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
hash = hpt_hash(vpn, 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)) {
Aneesh Kumar K.V
committed
/*
* lpar doesn't use the passed actual page size
*/
pSeries_lpar_hpte_invalidate(slot, vpn, psize,
Aneesh Kumar K.V
committed
0, ssize, local);
} else {
param[pix] = HBR_REQUEST | HBR_AVPN | slot;
param[pix+1] = hpte_encode_avpn(vpn, psize,
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);
}
static int __init disable_bulk_remove(char *str)
{
if (strcmp(str, "off") == 0 &&
firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
printk(KERN_INFO "Disabling BULK_REMOVE firmware feature");
powerpc_firmware_features &= ~FW_FEATURE_BULK_REMOVE;
}
return 1;
}
__setup("bulk_remove=", disable_bulk_remove);
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.hpte_removebolted = pSeries_lpar_hpte_removebolted;
ppc_md.flush_hash_range = pSeries_lpar_flush_hash_range;
ppc_md.hpte_clear_all = pSeries_lpar_hptab_clear;
ppc_md.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
#ifdef CONFIG_PPC_SMLPAR
#define CMO_FREE_HINT_DEFAULT 1
static int cmo_free_hint_flag = CMO_FREE_HINT_DEFAULT;
static int __init cmo_free_hint(char *str)
{
char *parm;
parm = strstrip(str);
if (strcasecmp(parm, "no") == 0 || strcasecmp(parm, "off") == 0) {
printk(KERN_INFO "cmo_free_hint: CMO free page hinting is not active.\n");
cmo_free_hint_flag = 0;
return 1;
}
cmo_free_hint_flag = 1;
printk(KERN_INFO "cmo_free_hint: CMO free page hinting is active.\n");
if (strcasecmp(parm, "yes") == 0 || strcasecmp(parm, "on") == 0)
return 1;
return 0;
}
__setup("cmo_free_hint=", cmo_free_hint);
static void pSeries_set_page_state(struct page *page, int order,
unsigned long state)
{
int i, j;
unsigned long cmo_page_sz, addr;
cmo_page_sz = cmo_get_page_size();
addr = __pa((unsigned long)page_address(page));
for (i = 0; i < (1 << order); i++, addr += PAGE_SIZE) {
for (j = 0; j < PAGE_SIZE; j += cmo_page_sz)
plpar_hcall_norets(H_PAGE_INIT, state, addr + j, 0);
}
}
void arch_free_page(struct page *page, int order)
{
if (!cmo_free_hint_flag || !firmware_has_feature(FW_FEATURE_CMO))
return;
pSeries_set_page_state(page, order, H_PAGE_SET_UNUSED);
}
EXPORT_SYMBOL(arch_free_page);
#endif
#ifdef CONFIG_TRACEPOINTS
/*
* We optimise our hcall path by placing hcall_tracepoint_refcount
* directly in the TOC so we can check if the hcall tracepoints are
* enabled via a single load.
*/
/* NB: reg/unreg are called while guarded with the tracepoints_mutex */
extern long hcall_tracepoint_refcount;
/*
* Since the tracing code might execute hcalls we need to guard against
* recursion. One example of this are spinlocks calling H_YIELD on
* shared processor partitions.
*/
static DEFINE_PER_CPU(unsigned int, hcall_trace_depth);
void hcall_tracepoint_regfunc(void)
{
hcall_tracepoint_refcount++;
}
void hcall_tracepoint_unregfunc(void)
{
hcall_tracepoint_refcount--;
}
void __trace_hcall_entry(unsigned long opcode, unsigned long *args)
unsigned long flags;
unsigned int *depth;
/*
* We cannot call tracepoints inside RCU idle regions which
* means we must not trace H_CEDE.
*/
if (opcode == H_CEDE)
return;
local_irq_save(flags);
depth = &__get_cpu_var(hcall_trace_depth);
if (*depth)
goto out;
(*depth)++;
preempt_disable();
trace_hcall_entry(opcode, args);
(*depth)--;
out:
local_irq_restore(flags);
void __trace_hcall_exit(long opcode, unsigned long retval,
unsigned long *retbuf)
unsigned long flags;
unsigned int *depth;
if (opcode == H_CEDE)
return;
local_irq_save(flags);
depth = &__get_cpu_var(hcall_trace_depth);
if (*depth)
goto out;
(*depth)++;
trace_hcall_exit(opcode, retval, retbuf);
preempt_enable();
(*depth)--;
out:
local_irq_restore(flags);
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
/**
* h_get_mpp
* H_GET_MPP hcall returns info in 7 parms
*/
int h_get_mpp(struct hvcall_mpp_data *mpp_data)
{
int rc;
unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
rc = plpar_hcall9(H_GET_MPP, retbuf);
mpp_data->entitled_mem = retbuf[0];
mpp_data->mapped_mem = retbuf[1];
mpp_data->group_num = (retbuf[2] >> 2 * 8) & 0xffff;
mpp_data->pool_num = retbuf[2] & 0xffff;
mpp_data->mem_weight = (retbuf[3] >> 7 * 8) & 0xff;
mpp_data->unallocated_mem_weight = (retbuf[3] >> 6 * 8) & 0xff;
mpp_data->unallocated_entitlement = retbuf[3] & 0xffffffffffff;
mpp_data->pool_size = retbuf[4];
mpp_data->loan_request = retbuf[5];
mpp_data->backing_mem = retbuf[6];
return rc;
}
EXPORT_SYMBOL(h_get_mpp);
int h_get_mpp_x(struct hvcall_mpp_x_data *mpp_x_data)
{
int rc;
unsigned long retbuf[PLPAR_HCALL9_BUFSIZE] = { 0 };
rc = plpar_hcall9(H_GET_MPP_X, retbuf);
mpp_x_data->coalesced_bytes = retbuf[0];
mpp_x_data->pool_coalesced_bytes = retbuf[1];
mpp_x_data->pool_purr_cycles = retbuf[2];
mpp_x_data->pool_spurr_cycles = retbuf[3];
return rc;
}