提交 bc33b1fc 编写于 作者: P Paul Mackerras

Merge remote-tracking branch 'remotes/powerpc/topic/ppc-kvm' into kvm-ppc-next

This merges in the ppc-kvm topic branch to get changes to
arch/powerpc code that are necessary for adding POWER9 KVM support.
Signed-off-by: NPaul Mackerras <paulus@ozlabs.org>
......@@ -70,7 +70,9 @@
#define HPTE_V_SSIZE_SHIFT 62
#define HPTE_V_AVPN_SHIFT 7
#define HPTE_V_COMMON_BITS ASM_CONST(0x000fffffffffffff)
#define HPTE_V_AVPN ASM_CONST(0x3fffffffffffff80)
#define HPTE_V_AVPN_3_0 ASM_CONST(0x000fffffffffff80)
#define HPTE_V_AVPN_VAL(x) (((x) & HPTE_V_AVPN) >> HPTE_V_AVPN_SHIFT)
#define HPTE_V_COMPARE(x,y) (!(((x) ^ (y)) & 0xffffffffffffff80UL))
#define HPTE_V_BOLTED ASM_CONST(0x0000000000000010)
......@@ -80,14 +82,16 @@
#define HPTE_V_VALID ASM_CONST(0x0000000000000001)
/*
* ISA 3.0 have a different HPTE format.
* ISA 3.0 has a different HPTE format.
*/
#define HPTE_R_3_0_SSIZE_SHIFT 58
#define HPTE_R_3_0_SSIZE_MASK (3ull << HPTE_R_3_0_SSIZE_SHIFT)
#define HPTE_R_PP0 ASM_CONST(0x8000000000000000)
#define HPTE_R_TS ASM_CONST(0x4000000000000000)
#define HPTE_R_KEY_HI ASM_CONST(0x3000000000000000)
#define HPTE_R_RPN_SHIFT 12
#define HPTE_R_RPN ASM_CONST(0x0ffffffffffff000)
#define HPTE_R_RPN_3_0 ASM_CONST(0x01fffffffffff000)
#define HPTE_R_PP ASM_CONST(0x0000000000000003)
#define HPTE_R_PPP ASM_CONST(0x8000000000000003)
#define HPTE_R_N ASM_CONST(0x0000000000000004)
......@@ -316,11 +320,42 @@ static inline unsigned long hpte_encode_avpn(unsigned long vpn, int psize,
*/
v = (vpn >> (23 - VPN_SHIFT)) & ~(mmu_psize_defs[psize].avpnm);
v <<= HPTE_V_AVPN_SHIFT;
if (!cpu_has_feature(CPU_FTR_ARCH_300))
v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT;
v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT;
return v;
}
/*
* ISA v3.0 defines a new HPTE format, which differs from the old
* format in having smaller AVPN and ARPN fields, and the B field
* in the second dword instead of the first.
*/
static inline unsigned long hpte_old_to_new_v(unsigned long v)
{
/* trim AVPN, drop B */
return v & HPTE_V_COMMON_BITS;
}
static inline unsigned long hpte_old_to_new_r(unsigned long v, unsigned long r)
{
/* move B field from 1st to 2nd dword, trim ARPN */
return (r & ~HPTE_R_3_0_SSIZE_MASK) |
(((v) >> HPTE_V_SSIZE_SHIFT) << HPTE_R_3_0_SSIZE_SHIFT);
}
static inline unsigned long hpte_new_to_old_v(unsigned long v, unsigned long r)
{
/* insert B field */
return (v & HPTE_V_COMMON_BITS) |
((r & HPTE_R_3_0_SSIZE_MASK) <<
(HPTE_V_SSIZE_SHIFT - HPTE_R_3_0_SSIZE_SHIFT));
}
static inline unsigned long hpte_new_to_old_r(unsigned long r)
{
/* clear out B field */
return r & ~HPTE_R_3_0_SSIZE_MASK;
}
/*
* This function sets the AVPN and L fields of the HPTE appropriately
* using the base page size and actual page size.
......@@ -341,12 +376,8 @@ static inline unsigned long hpte_encode_v(unsigned long vpn, int base_psize,
* aligned for the requested page size
*/
static inline unsigned long hpte_encode_r(unsigned long pa, int base_psize,
int actual_psize, int ssize)
int actual_psize)
{
if (cpu_has_feature(CPU_FTR_ARCH_300))
pa |= ((unsigned long) ssize) << HPTE_R_3_0_SSIZE_SHIFT;
/* A 4K page needs no special encoding */
if (actual_psize == MMU_PAGE_4K)
return pa & HPTE_R_RPN;
......
......@@ -208,6 +208,11 @@ extern u64 ppc64_rma_size;
/* Cleanup function used by kexec */
extern void mmu_cleanup_all(void);
extern void radix__mmu_cleanup_all(void);
/* Functions for creating and updating partition table on POWER9 */
extern void mmu_partition_table_init(void);
extern void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0,
unsigned long dw1);
#endif /* CONFIG_PPC64 */
struct mm_struct;
......
......@@ -220,9 +220,12 @@ int64_t opal_pci_set_power_state(uint64_t async_token, uint64_t id,
int64_t opal_pci_poll2(uint64_t id, uint64_t data);
int64_t opal_int_get_xirr(uint32_t *out_xirr, bool just_poll);
int64_t opal_rm_int_get_xirr(__be32 *out_xirr, bool just_poll);
int64_t opal_int_set_cppr(uint8_t cppr);
int64_t opal_int_eoi(uint32_t xirr);
int64_t opal_rm_int_eoi(uint32_t xirr);
int64_t opal_int_set_mfrr(uint32_t cpu, uint8_t mfrr);
int64_t opal_rm_int_set_mfrr(uint32_t cpu, uint8_t mfrr);
int64_t opal_pci_tce_kill(uint64_t phb_id, uint32_t kill_type,
uint32_t pe_num, uint32_t tce_size,
uint64_t dma_addr, uint32_t npages);
......
......@@ -153,6 +153,8 @@
#define PSSCR_EC 0x00100000 /* Exit Criterion */
#define PSSCR_ESL 0x00200000 /* Enable State Loss */
#define PSSCR_SD 0x00400000 /* Status Disable */
#define PSSCR_PLS 0xf000000000000000 /* Power-saving Level Status */
#define PSSCR_GUEST_VIS 0xf0000000000003ff /* Guest-visible PSSCR fields */
/* Floating Point Status and Control Register (FPSCR) Fields */
#define FPSCR_FX 0x80000000 /* FPU exception summary */
......@@ -236,6 +238,7 @@
#define SPRN_TEXASRU 0x83 /* '' '' '' Upper 32 */
#define TEXASR_FS __MASK(63-36) /* TEXASR Failure Summary */
#define SPRN_TFHAR 0x80 /* Transaction Failure Handler Addr */
#define SPRN_TIDR 144 /* Thread ID register */
#define SPRN_CTRLF 0x088
#define SPRN_CTRLT 0x098
#define CTRL_CT 0xc0000000 /* current thread */
......@@ -294,6 +297,7 @@
#define SPRN_HSRR1 0x13B /* Hypervisor Save/Restore 1 */
#define SPRN_LMRR 0x32D /* Load Monitor Region Register */
#define SPRN_LMSER 0x32E /* Load Monitor Section Enable Register */
#define SPRN_ASDR 0x330 /* Access segment descriptor register */
#define SPRN_IC 0x350 /* Virtual Instruction Count */
#define SPRN_VTB 0x351 /* Virtual Time Base */
#define SPRN_LDBAR 0x352 /* LD Base Address Register */
......@@ -305,6 +309,7 @@
/* HFSCR and FSCR bit numbers are the same */
#define FSCR_LM_LG 11 /* Enable Load Monitor Registers */
#define FSCR_MSGP_LG 10 /* Enable MSGP */
#define FSCR_TAR_LG 8 /* Enable Target Address Register */
#define FSCR_EBB_LG 7 /* Enable Event Based Branching */
#define FSCR_TM_LG 5 /* Enable Transactional Memory */
......@@ -320,6 +325,7 @@
#define FSCR_DSCR __MASK(FSCR_DSCR_LG)
#define SPRN_HFSCR 0xbe /* HV=1 Facility Status & Control Register */
#define HFSCR_LM __MASK(FSCR_LM_LG)
#define HFSCR_MSGP __MASK(FSCR_MSGP_LG)
#define HFSCR_TAR __MASK(FSCR_TAR_LG)
#define HFSCR_EBB __MASK(FSCR_EBB_LG)
#define HFSCR_TM __MASK(FSCR_TM_LG)
......@@ -355,8 +361,10 @@
#define LPCR_PECE0 ASM_CONST(0x0000000000004000) /* ext. exceptions can cause exit */
#define LPCR_PECE1 ASM_CONST(0x0000000000002000) /* decrementer can cause exit */
#define LPCR_PECE2 ASM_CONST(0x0000000000001000) /* machine check etc can cause exit */
#define LPCR_PECE_HVEE ASM_CONST(0x0000400000000000) /* P9 Wakeup on HV interrupts */
#define LPCR_MER ASM_CONST(0x0000000000000800) /* Mediated External Exception */
#define LPCR_MER_SH 11
#define LPCR_GTSE ASM_CONST(0x0000000000000400) /* Guest Translation Shootdown Enable */
#define LPCR_TC ASM_CONST(0x0000000000000200) /* Translation control */
#define LPCR_LPES 0x0000000c
#define LPCR_LPES0 ASM_CONST(0x0000000000000008) /* LPAR Env selector 0 */
......@@ -377,6 +385,12 @@
#define PCR_VEC_DIS (1ul << (63-0)) /* Vec. disable (bit NA since POWER8) */
#define PCR_VSX_DIS (1ul << (63-1)) /* VSX disable (bit NA since POWER8) */
#define PCR_TM_DIS (1ul << (63-2)) /* Trans. memory disable (POWER8) */
/*
* These bits are used in the function kvmppc_set_arch_compat() to specify and
* determine both the compatibility level which we want to emulate and the
* compatibility level which the host is capable of emulating.
*/
#define PCR_ARCH_207 0x8 /* Architecture 2.07 */
#define PCR_ARCH_206 0x4 /* Architecture 2.06 */
#define PCR_ARCH_205 0x2 /* Architecture 2.05 */
#define SPRN_HEIR 0x153 /* Hypervisor Emulated Instruction Register */
......@@ -1218,6 +1232,7 @@
#define PVR_ARCH_206 0x0f000003
#define PVR_ARCH_206p 0x0f100003
#define PVR_ARCH_207 0x0f000004
#define PVR_ARCH_300 0x0f000005
/* Macros for setting and retrieving special purpose registers */
#ifndef __ASSEMBLY__
......
......@@ -174,7 +174,7 @@ __init_FSCR:
__init_HFSCR:
mfspr r3,SPRN_HFSCR
ori r3,r3,HFSCR_TAR|HFSCR_TM|HFSCR_BHRB|HFSCR_PM|\
HFSCR_DSCR|HFSCR_VECVSX|HFSCR_FP|HFSCR_EBB
HFSCR_DSCR|HFSCR_VECVSX|HFSCR_FP|HFSCR_EBB|HFSCR_MSGP
mtspr SPRN_HFSCR,r3
blr
......
......@@ -221,13 +221,18 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
return -1;
hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
hpte_r = hpte_encode_r(pa, psize, apsize, ssize) | rflags;
hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
if (!(vflags & HPTE_V_BOLTED)) {
DBG_LOW(" i=%x hpte_v=%016lx, hpte_r=%016lx\n",
i, hpte_v, hpte_r);
}
if (cpu_has_feature(CPU_FTR_ARCH_300)) {
hpte_r = hpte_old_to_new_r(hpte_v, hpte_r);
hpte_v = hpte_old_to_new_v(hpte_v);
}
hptep->r = cpu_to_be64(hpte_r);
/* Guarantee the second dword is visible before the valid bit */
eieio();
......@@ -295,6 +300,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
vpn, want_v & HPTE_V_AVPN, slot, newpp);
hpte_v = be64_to_cpu(hptep->v);
if (cpu_has_feature(CPU_FTR_ARCH_300))
hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r));
/*
* We need to invalidate the TLB always because hpte_remove doesn't do
* a tlb invalidate. If a hash bucket gets full, we "evict" a more/less
......@@ -309,6 +316,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
native_lock_hpte(hptep);
/* recheck with locks held */
hpte_v = be64_to_cpu(hptep->v);
if (cpu_has_feature(CPU_FTR_ARCH_300))
hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r));
if (unlikely(!HPTE_V_COMPARE(hpte_v, want_v) ||
!(hpte_v & HPTE_V_VALID))) {
ret = -1;
......@@ -350,6 +359,8 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize)
for (i = 0; i < HPTES_PER_GROUP; i++) {
hptep = htab_address + slot;
hpte_v = be64_to_cpu(hptep->v);
if (cpu_has_feature(CPU_FTR_ARCH_300))
hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r));
if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID))
/* HPTE matches */
......@@ -409,6 +420,8 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
want_v = hpte_encode_avpn(vpn, bpsize, ssize);
native_lock_hpte(hptep);
hpte_v = be64_to_cpu(hptep->v);
if (cpu_has_feature(CPU_FTR_ARCH_300))
hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r));
/*
* We need to invalidate the TLB always because hpte_remove doesn't do
......@@ -467,6 +480,8 @@ static void native_hugepage_invalidate(unsigned long vsid,
want_v = hpte_encode_avpn(vpn, psize, ssize);
native_lock_hpte(hptep);
hpte_v = be64_to_cpu(hptep->v);
if (cpu_has_feature(CPU_FTR_ARCH_300))
hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r));
/* Even if we miss, we need to invalidate the TLB */
if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
......@@ -504,6 +519,10 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
/* Look at the 8 bit LP value */
unsigned int lp = (hpte_r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
if (cpu_has_feature(CPU_FTR_ARCH_300)) {
hpte_v = hpte_new_to_old_v(hpte_v, hpte_r);
hpte_r = hpte_new_to_old_r(hpte_r);
}
if (!(hpte_v & HPTE_V_LARGE)) {
size = MMU_PAGE_4K;
a_size = MMU_PAGE_4K;
......@@ -512,11 +531,7 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
a_size = hpte_page_sizes[lp] >> 4;
}
/* This works for all page sizes, and for 256M and 1T segments */
if (cpu_has_feature(CPU_FTR_ARCH_300))
*ssize = hpte_r >> HPTE_R_3_0_SSIZE_SHIFT;
else
*ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
*ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
shift = mmu_psize_defs[size].shift;
avpn = (HPTE_V_AVPN_VAL(hpte_v) & ~mmu_psize_defs[size].avpnm);
......@@ -639,6 +654,9 @@ static void native_flush_hash_range(unsigned long number, int local)
want_v = hpte_encode_avpn(vpn, psize, ssize);
native_lock_hpte(hptep);
hpte_v = be64_to_cpu(hptep->v);
if (cpu_has_feature(CPU_FTR_ARCH_300))
hpte_v = hpte_new_to_old_v(hpte_v,
be64_to_cpu(hptep->r));
if (!HPTE_V_COMPARE(hpte_v, want_v) ||
!(hpte_v & HPTE_V_VALID))
native_unlock_hpte(hptep);
......
......@@ -792,37 +792,17 @@ static void update_hid_for_hash(void)
static void __init hash_init_partition_table(phys_addr_t hash_table,
unsigned long htab_size)
{
unsigned long ps_field;
unsigned long patb_size = 1UL << PATB_SIZE_SHIFT;
mmu_partition_table_init();
/*
* slb llp encoding for the page size used in VPM real mode.
* We can ignore that for lpid 0
* PS field (VRMA page size) is not used for LPID 0, hence set to 0.
* For now, UPRT is 0 and we have no segment table.
*/
ps_field = 0;
htab_size = __ilog2(htab_size) - 18;
BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 24), "Partition table size too large.");
partition_tb = __va(memblock_alloc_base(patb_size, patb_size,
MEMBLOCK_ALLOC_ANYWHERE));
/* Initialize the Partition Table with no entries */
memset((void *)partition_tb, 0, patb_size);
partition_tb->patb0 = cpu_to_be64(ps_field | hash_table | htab_size);
/*
* FIXME!! This should be done via update_partition table
* For now UPRT is 0 for us.
*/
partition_tb->patb1 = 0;
mmu_partition_table_set_entry(0, hash_table | htab_size, 0);
pr_info("Partition table %p\n", partition_tb);
if (cpu_has_feature(CPU_FTR_POWER9_DD1))
update_hid_for_hash();
/*
* update partition table control register,
* 64 K size.
*/
mtspr(SPRN_PTCR, __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
}
static void __init htab_initialize(void)
......
......@@ -177,23 +177,15 @@ static void __init radix_init_pgtable(void)
static void __init radix_init_partition_table(void)
{
unsigned long rts_field;
unsigned long rts_field, dw0;
mmu_partition_table_init();
rts_field = radix__get_tree_size();
dw0 = rts_field | __pa(init_mm.pgd) | RADIX_PGD_INDEX_SIZE | PATB_HR;
mmu_partition_table_set_entry(0, dw0, 0);
BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 24), "Partition table size too large.");
partition_tb = early_alloc_pgtable(1UL << PATB_SIZE_SHIFT);
partition_tb->patb0 = cpu_to_be64(rts_field | __pa(init_mm.pgd) |
RADIX_PGD_INDEX_SIZE | PATB_HR);
pr_info("Initializing Radix MMU\n");
pr_info("Partition table %p\n", partition_tb);
memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
/*
* update partition table control register,
* 64 K size.
*/
mtspr(SPRN_PTCR, __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
}
void __init radix_init_native(void)
......@@ -378,6 +370,8 @@ void __init radix__early_init_mmu(void)
radix_init_partition_table();
}
memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
radix_init_pgtable();
}
......
......@@ -431,3 +431,37 @@ void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
}
}
#endif
#ifdef CONFIG_PPC_BOOK3S_64
void __init mmu_partition_table_init(void)
{
unsigned long patb_size = 1UL << PATB_SIZE_SHIFT;
BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 36), "Partition table size too large.");
partition_tb = __va(memblock_alloc_base(patb_size, patb_size,
MEMBLOCK_ALLOC_ANYWHERE));
/* Initialize the Partition Table with no entries */
memset((void *)partition_tb, 0, patb_size);
/*
* update partition table control register,
* 64 K size.
*/
mtspr(SPRN_PTCR, __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
}
void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0,
unsigned long dw1)
{
partition_tb[lpid].patb0 = cpu_to_be64(dw0);
partition_tb[lpid].patb1 = cpu_to_be64(dw1);
/* Global flush of TLBs and partition table caches for this lpid */
asm volatile("ptesync" : : : "memory");
asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : :
"r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
asm volatile("eieio; tlbsync; ptesync" : : : "memory");
}
EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry);
#endif /* CONFIG_PPC_BOOK3S_64 */
......@@ -304,8 +304,11 @@ OPAL_CALL(opal_pci_get_presence_state, OPAL_PCI_GET_PRESENCE_STATE);
OPAL_CALL(opal_pci_get_power_state, OPAL_PCI_GET_POWER_STATE);
OPAL_CALL(opal_pci_set_power_state, OPAL_PCI_SET_POWER_STATE);
OPAL_CALL(opal_int_get_xirr, OPAL_INT_GET_XIRR);
OPAL_CALL_REAL(opal_rm_int_get_xirr, OPAL_INT_GET_XIRR);
OPAL_CALL(opal_int_set_cppr, OPAL_INT_SET_CPPR);
OPAL_CALL(opal_int_eoi, OPAL_INT_EOI);
OPAL_CALL_REAL(opal_rm_int_eoi, OPAL_INT_EOI);
OPAL_CALL(opal_int_set_mfrr, OPAL_INT_SET_MFRR);
OPAL_CALL_REAL(opal_rm_int_set_mfrr, OPAL_INT_SET_MFRR);
OPAL_CALL(opal_pci_tce_kill, OPAL_PCI_TCE_KILL);
OPAL_CALL_REAL(opal_rm_pci_tce_kill, OPAL_PCI_TCE_KILL);
......@@ -896,3 +896,5 @@ EXPORT_SYMBOL_GPL(opal_leds_get_ind);
EXPORT_SYMBOL_GPL(opal_leds_set_ind);
/* Export this symbol for PowerNV Operator Panel class driver */
EXPORT_SYMBOL_GPL(opal_write_oppanel_async);
/* Export this for KVM */
EXPORT_SYMBOL_GPL(opal_int_set_mfrr);
......@@ -63,7 +63,7 @@ static long ps3_hpte_insert(unsigned long hpte_group, unsigned long vpn,
vflags &= ~HPTE_V_SECONDARY;
hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
hpte_r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize, apsize, ssize) | rflags;
hpte_r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize, apsize) | rflags;
spin_lock_irqsave(&ps3_htab_lock, flags);
......
......@@ -145,7 +145,7 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
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, ssize) | rflags;
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);
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册