ppc: misc fixes for Radix and Hash
cover ppc: misc fixes for Radix and Hash
Hi,
Here is a series of patches from Ben providing MMU fixes for sPAPR and PowerNV. They seem of interest and deserve a closer look by people with good knowledge of the PPC MMU.
Thanks,
C.
Benjamin Herrenschmidt (6):
target/ppc: Don't check UPRT in radix mode when in HV real mode ppc/spapr: Use proper HPTE accessors for H_READ ppc/hash64: Rework R and C bit updates
ppc/hash32: Rework R and C bit updates
memory_ldst: Add atomic ops for PTE updates
ppc: Fix radix RC updates
include/exec/memory_ldst.inc.h | 6 +++ include/hw/ppc/spapr.h | 2 + target/ppc/cpu.h | 5 +- target/ppc/mmu-hash64.h | 2 - hw/ppc/spapr.c | 41 ++++++++++++++-- hw/ppc/spapr_hcall.c | 24 +++++----- memory_ldst.inc.c | 80 +++++++++++++++++++++++++++++++ target/ppc/mmu-hash32.c | 45 ++++++++++++------ target/ppc/mmu-hash64.c | 76 ++++++++++++++++++------------ target/ppc/mmu-radix64.c | 86 ++++++++++++++++++++++++++++------ 10 files changed, 288 insertions(+), 79 deletions(-)
Signature · 1 line
2.20.1
PATCH 1/6 target/ppc: Don't check UPRT in radix mode when in HV real mode
From: Benjamin Herrenschmidt <[email protected]>
It appears that during kexec, we run for a while in hypervisor real mode with LPCR:HR set and LPCR:UPRT clear, which trips the assertion in ppc_radix64_handle_mmu_fault().
First this shouldn't be an assertion, it's a guest error.
Then we shouldn't be checking these things in hypervisor real mode (or in virtual hypervisor guest real mode which is similar) as the real HW won't use those LPCR bits in those cases anyway, so technically it's ok to have this discrepancy.
--- target/ppc/mmu-radix64.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-)
target/ppc/mmu-radix64.c +13 -3
@@ -228,10 +228,10 @@ int ppc_radix64_handle_mmu_fault(PowerPCCPU *cpu, vaddr eaddr, int rwx,ppc_v3_pate_t pate;assert ((rwx ==0 ) || (rwx ==1 ) || (rwx ==2 )); -assert (ppc64_use_proc_tbl (cpu)); -/* Real Mode Access */ -if (((rwx ==2 ) && (msr_ir ==0 )) || ((rwx !=2 ) && (msr_dr ==0 ))) { +/* HV or virtual hypervisor Real Mode Access */ +if ((msr_hv || cpu->vhyp) && + (((rwx ==2 ) && (msr_ir ==0 )) || ((rwx !=2 ) && (msr_dr ==0 )))) {/* In real mode top 4 effective addr bits (mostly) ignored */ raddr = eaddr &0x0FFFFFFFFFFFFFFFULL ;
@@ -241,6 +241,16 @@ int ppc_radix64_handle_mmu_fault(PowerPCCPU *cpu, vaddr eaddr, int rwx,return 0 ; } +/* +* Check UPRT (we avoid the check in real mode to deal with +* transitional states during kexec. +*/ +if (!ppc64_use_proc_tbl (cpu)) { +qemu_log_mask (LOG_GUEST_ERROR , +"LPCR:UPRT not set in radix mode ! LPCR=%016lx\n" , + env->spr[SPR_LPCR ]); + } +/* Virtual Mode Access - get the fully qualified address */ if (!ppc_radix64_get_fully_qualified_addr (env, eaddr, &lpid, &pid)) {ppc_radix64_raise_segi (cpu, rwx, eaddr);
Signature · 1 line
2.20.1
David Gibson
AppliedRe: [Qemu-devel] [PATCH 1/6] target/ppc: Don't check UPRT in radix mode when in HV real mode
Quoted 8 lines · Cédric Le Goater
From: Benjamin Herrenschmidt <[email protected]>
It appears that during kexec, we run for a while in hypervisor real mode with LPCR:HR set and LPCR:UPRT clear, which trips the assertion in
ppc_radix64_handle_mmu_fault().First this shouldn't be an assertion, it's a guest error.
Quoted 7 lines
Then we shouldn't be checking these things in hypervisor real mode (or in virtual hypervisor guest real mode which is similar) as the real HW won't use those LPCR bits in those cases anyway, so technically it's ok to have this discrepancy.
Signed-off-by Benjamin Herrenschmidt <[email protected]>Signed-off-by Cédric Le Goater <[email protected]>
Applied to ppc-for-4.1, thanks.
Quoted 9 lines
--- target/ppc/mmu-radix64.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-)target/ppc/mmu-radix64.c +0
-0
target/ppc/mmu-radix64.c int ppc_radix64_handle_mmu_fault(PowerPCCPU *cpu, vaddr eaddr, int rwx, · line 234
Quoted 10 lines
target/ppc/mmu-radix64.c +3
-3@@ -228,10 +228,10 @@ int ppc_radix64_handle_mmu_fault(PowerPCCPU *cpu, vaddr eaddr, int rwx,ppc_v3_pate_t pate;assert ((rwx ==0 ) || (rwx ==1 ) || (rwx ==2 )); -assert (ppc64_use_proc_tbl (cpu)); -/* Real Mode Access */ -if (((rwx ==2 ) && (msr_ir ==0 )) || ((rwx !=2 ) && (msr_dr ==0 ))) { +/* HV or virtual hypervisor Real Mode Access */ +if ((msr_hv || cpu->vhyp) && + (((rwx ==2 ) && (msr_ir ==0 )) || ((rwx !=2 ) && (msr_dr ==0 )))) {
Hrm.. this looks like a different bug fix. Were we preivously incorrectly handling guest real mode when running powernv?
Quoted 20 lines
target/ppc/mmu-radix64.c +10
-0/* In real mode top 4 effective addr bits (mostly) ignored */ raddr = eaddr &0x0FFFFFFFFFFFFFFFULL ;@@ -241,6 +241,16 @@ int ppc_radix64_handle_mmu_fault(PowerPCCPU *cpu, vaddr eaddr, int rwx,return 0 ; } +/* +* Check UPRT (we avoid the check in real mode to deal with +* transitional states during kexec. +*/ +if (!ppc64_use_proc_tbl (cpu)) { +qemu_log_mask (LOG_GUEST_ERROR , +"LPCR:UPRT not set in radix mode ! LPCR=%016lx\n" , + env->spr[SPR_LPCR ]); + } +/* Virtual Mode Access - get the fully qualified address */ if (!ppc_radix64_get_fully_qualified_addr (env, eaddr, &lpid, &pid)) {ppc_radix64_raise_segi (cpu, rwx, eaddr);
Signature · 4 lines
David Gibson | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_ | _way_ _around_! http://www.ozlabs.org/~dgibson
PATCH 2/6 ppc/spapr: Use proper HPTE accessors for H_READ
In reply to Cédric Le GoaterFrom: Benjamin Herrenschmidt <[email protected]>
--- hw/ppc/spapr_hcall.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-)
hw/ppc/spapr_hcall.c +5 -6
@@ -304,8 +304,8 @@ static target_ulong h_read(PowerPCCPU *cpu, SpaprMachineState *spapr, {target_ulong flags = args[0 ];target_ulong ptex = args[1 ]; -uint8_t *hpte;int i, ridx, n_entries =1 ; +const ppc_hash_pte64_t *hptes;if (!valid_ptex (cpu, ptex)) {return H_PARAMETER ;
@@ -317,13 +317,12 @@ static target_ulong h_read(PowerPCCPU *cpu, SpaprMachineState *spapr, n_entries =4 ; } - hpte = spapr->htab + (ptex *HASH_PTE_SIZE_64 ); - + hptes =ppc_hash64_map_hptes (cpu, ptex, n_entries);for (i =0 , ridx =0 ; i < n_entries; i++) { - args[ridx++] =ldq_p (hpte); - args[ridx++] =ldq_p (hpte + (HASH_PTE_SIZE_64 /2 )); - hpte +=HASH_PTE_SIZE_64 ; + args[ridx++] =ppc_hash64_hpte0 (cpu, hptes, i); + args[ridx++] =ppc_hash64_hpte1 (cpu, hptes, i); } +ppc_hash64_unmap_hptes (cpu, hptes, ptex, n_entries);return H_SUCCESS ; }
Signature · 1 line
2.20.1
David Gibson
AppliedRe: [Qemu-devel] [PATCH 2/6] ppc/spapr: Use proper HPTE accessors for H_READ
Quoted 4 lines · Cédric Le Goater
From: Benjamin Herrenschmidt <[email protected]>
Signed-off-by Benjamin Herrenschmidt <[email protected]>Signed-off-by Cédric Le Goater <[email protected]>
Applied, thanks.
Quoted 36 lines
--- hw/ppc/spapr_hcall.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-)hw/ppc/spapr_hcall.c +5
-6@@ -304,8 +304,8 @@ static target_ulong h_read(PowerPCCPU *cpu, SpaprMachineState *spapr, {target_ulong flags = args[0 ];target_ulong ptex = args[1 ]; -uint8_t *hpte;int i, ridx, n_entries =1 ; +const ppc_hash_pte64_t *hptes;if (!valid_ptex (cpu, ptex)) {return H_PARAMETER ;@@ -317,13 +317,12 @@ static target_ulong h_read(PowerPCCPU *cpu, SpaprMachineState *spapr, n_entries =4 ; } - hpte = spapr->htab + (ptex *HASH_PTE_SIZE_64 ); - + hptes =ppc_hash64_map_hptes (cpu, ptex, n_entries);for (i =0 , ridx =0 ; i < n_entries; i++) { - args[ridx++] =ldq_p (hpte); - args[ridx++] =ldq_p (hpte + (HASH_PTE_SIZE_64 /2 )); - hpte +=HASH_PTE_SIZE_64 ; + args[ridx++] =ppc_hash64_hpte0 (cpu, hptes, i); + args[ridx++] =ppc_hash64_hpte1 (cpu, hptes, i); } +ppc_hash64_unmap_hptes (cpu, hptes, ptex, n_entries);return H_SUCCESS ; }
Signature · 4 lines
David Gibson | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_ | _way_ _around_! http://www.ozlabs.org/~dgibson
PATCH 3/6 ppc/hash64: Rework R and C bit updates
In reply to Cédric Le GoaterFrom: Benjamin Herrenschmidt <[email protected]>
With MT-TCG, we are now running translation in a racy way, thus we need to mimic hardware when it comes to updating the R and C bits, by doing byte stores.
The current "store_hpte" abstraction is ill suited for this, we replace it with two separate callbacks for setting R and C.
--- include/hw/ppc/spapr.h | 2 ++ target/ppc/cpu.h | 4 +-- target/ppc/mmu-hash64.h | 2 -- hw/ppc/spapr.c | 41 +++++++++++++++++++--- hw/ppc/spapr_hcall.c | 13 +++---- target/ppc/mmu-hash64.c | 76 ++++++++++++++++++++++++----------------- 6 files changed, 93 insertions(+), 45 deletions(-)
include/hw/ppc/spapr.h +2 -0
@@ -784,6 +784,8 @@ void spapr_reallocate_hpt(SpaprMachineState *spapr, int shift, Error **errp);void spapr_clear_pending_events (SpaprMachineState *spapr);int spapr_max_server_number (SpaprMachineState *spapr); +void spapr_store_hpte (PowerPCCPU *cpu,hwaddr ptex, +uint64_t pte0,uint64_t pte1);/* DRC callbacks. */ void spapr_core_release (DeviceState *dev);
target/ppc/cpu.h +2 -2
@@ -1268,8 +1268,8 @@ struct PPCVirtualHypervisorClass {void (*unmap_hptes)(PPCVirtualHypervisor *vhyp,const ppc_hash_pte64_t *hptes,hwaddr ptex,int n); -void (*store_hpte)(PPCVirtualHypervisor *vhyp,hwaddr ptex, -uint64_t pte0,uint64_t pte1); +void (*hpte_set_c)(PPCVirtualHypervisor *vhyp,hwaddr ptex,uint64_t pte1); +void (*hpte_set_r)(PPCVirtualHypervisor *vhyp,hwaddr ptex,uint64_t pte1);void (*get_pate)(PPCVirtualHypervisor *vhyp,ppc_v3_pate_t *entry);target_ulong (*encode_hpt_for_kvm_pr)(PPCVirtualHypervisor *vhyp); };
target/ppc/mmu-hash64.h +0 -2
@@ -10,8 +10,6 @@ int ppc_store_slb(PowerPCCPU *cpu, target_ulong slot,hwaddr ppc_hash64_get_phys_page_debug (PowerPCCPU *cpu,target_ulong addr);int ppc_hash64_handle_mmu_fault (PowerPCCPU *cpu,vaddr address,int rw,int mmu_idx); -void ppc_hash64_store_hpte (PowerPCCPU *cpu,hwaddr ptex, -uint64_t pte0,uint64_t pte1);void ppc_hash64_tlb_flush_hpte (PowerPCCPU *cpu,target_ulong pte_index,target_ulong pte0,target_ulong pte1);
hw/ppc/spapr.c +37 -4
60 lines not on this page · raw message
hw/ppc/spapr_hcall.c +7 -6
@@ -118,7 +118,7 @@ static target_ulong h_enter(PowerPCCPU *cpu, SpaprMachineState *spapr,ppc_hash64_unmap_hptes (cpu, hptes, ptex,1 ); } -ppc_hash64_store_hpte (cpu, ptex + slot, pteh |HPTE64_V_HPTE_DIRTY , ptel); +spapr_store_hpte (cpu, ptex + slot, pteh |HPTE64_V_HPTE_DIRTY , ptel); args[0 ] = ptex + slot;return H_SUCCESS ;
@@ -131,7 +131,8 @@ typedef enum {REMOVE_HW =3 , } RemoveResult; -static RemoveResult remove_hpte (PowerPCCPU *cpu,target_ulong ptex, +static RemoveResult remove_hpte (PowerPCCPU *cpu + ,target_ulong ptex,target_ulong avpn,target_ulong flags,target_ulong *vp,target_ulong *rp)
@@ -155,7 +156,7 @@ static RemoveResult remove_hpte(PowerPCCPU *cpu, target_ulong ptex, } *vp = v; *rp = r; -ppc_hash64_store_hpte (cpu, ptex,HPTE64_V_HPTE_DIRTY ,0 ); +spapr_store_hpte (cpu, ptex,HPTE64_V_HPTE_DIRTY ,0 );ppc_hash64_tlb_flush_hpte (cpu, ptex, v, r);return REMOVE_SUCCESS ; }
@@ -289,13 +290,13 @@ static target_ulong h_protect(PowerPCCPU *cpu, SpaprMachineState *spapr, r |= (flags <<55 ) &HPTE64_R_PP0 ; r |= (flags <<48 ) &HPTE64_R_KEY_HI ; r |= flags & (HPTE64_R_PP |HPTE64_R_N |HPTE64_R_KEY_LO ); -ppc_hash64_store_hpte (cpu, ptex, - (v & ~HPTE64_V_VALID ) |HPTE64_V_HPTE_DIRTY ,0 ); +spapr_store_hpte (cpu, ptex, + (v & ~HPTE64_V_VALID ) |HPTE64_V_HPTE_DIRTY ,0 );ppc_hash64_tlb_flush_hpte (cpu, ptex, v, r);/* Flush the tlb */ check_tlb_flush (env, true);/* Don't need a memory barrier, due to qemu's global lock */ -ppc_hash64_store_hpte (cpu, ptex, v |HPTE64_V_HPTE_DIRTY , r); +spapr_store_hpte (cpu, ptex, v |HPTE64_V_HPTE_DIRTY , r);return H_SUCCESS ; }
target/ppc/mmu-hash64.c +45 -31
101 lines not on this page · raw message
Signature · 1 line
2.20.1
David Gibson
AppliedRe: [Qemu-devel] [PATCH 3/6] ppc/hash64: Rework R and C bit updates
Quoted 11 lines · Cédric Le Goater
From: Benjamin Herrenschmidt <[email protected]>
With MT-TCG, we are now running translation in a racy way, thus we need to mimic hardware when it comes to updating the R and C bits, by doing byte stores.
The current "
store_hpte" abstraction is ill suited for this, we replace it with two separate callbacks for setting R and C.Signed-off-by Benjamin Herrenschmidt <[email protected]>Signed-off-by Cédric Le Goater <[email protected]>
Applied, thanks.
Quoted 275 lines
--- include/hw/ppc/spapr.h | 2 ++ target/ppc/cpu.h | 4 +-- target/ppc/mmu-hash64.h | 2 -- hw/ppc/spapr.c | 41 +++++++++++++++++++--- hw/ppc/spapr_hcall.c | 13 +++---- target/ppc/mmu-hash64.c | 76 ++++++++++++++++++++++++----------------- 6 files changed, 93 insertions(+), 45 deletions(-)include/hw/ppc/spapr.h +2
-0@@ -784,6 +784,8 @@ void spapr_reallocate_hpt(SpaprMachineState *spapr, int shift, Error **errp);void spapr_clear_pending_events (SpaprMachineState *spapr);int spapr_max_server_number (SpaprMachineState *spapr); +void spapr_store_hpte (PowerPCCPU *cpu,hwaddr ptex, +uint64_t pte0,uint64_t pte1);/* DRC callbacks. */ void spapr_core_release (DeviceState *dev);target/ppc/cpu.h +2
-2@@ -1268,8 +1268,8 @@ struct PPCVirtualHypervisorClass {void (*unmap_hptes)(PPCVirtualHypervisor *vhyp,const ppc_hash_pte64_t *hptes,hwaddr ptex,int n); -void (*store_hpte)(PPCVirtualHypervisor *vhyp,hwaddr ptex, -uint64_t pte0,uint64_t pte1); +void (*hpte_set_c)(PPCVirtualHypervisor *vhyp,hwaddr ptex,uint64_t pte1); +void (*hpte_set_r)(PPCVirtualHypervisor *vhyp,hwaddr ptex,uint64_t pte1);void (*get_pate)(PPCVirtualHypervisor *vhyp,ppc_v3_pate_t *entry);target_ulong (*encode_hpt_for_kvm_pr)(PPCVirtualHypervisor *vhyp); };target/ppc/mmu-hash64.h +0
-2@@ -10,8 +10,6 @@ int ppc_store_slb(PowerPCCPU *cpu, target_ulong slot,hwaddr ppc_hash64_get_phys_page_debug (PowerPCCPU *cpu,target_ulong addr);int ppc_hash64_handle_mmu_fault (PowerPCCPU *cpu,vaddr address,int rw,int mmu_idx); -void ppc_hash64_store_hpte (PowerPCCPU *cpu,hwaddr ptex, -uint64_t pte0,uint64_t pte1);void ppc_hash64_tlb_flush_hpte (PowerPCCPU *cpu,target_ulong pte_index,target_ulong pte0,target_ulong pte1);hw/ppc/spapr.c +37
-4@@ -1520,10 +1520,10 @@ static void spapr_unmap_hptes(PPCVirtualHypervisor *vhyp,/* Nothing to do for qemu managed HPT */ } -static void spapr_store_hpte (PPCVirtualHypervisor *vhyp,hwaddr ptex, -uint64_t pte0,uint64_t pte1) +void spapr_store_hpte (PowerPCCPU *cpu,hwaddr ptex, +uint64_t pte0,uint64_t pte1) { -SpaprMachineState *spapr =SPAPR_MACHINE (vhyp); +SpaprMachineState *spapr =SPAPR_MACHINE (cpu->vhyp);hwaddr offset = ptex *HASH_PTE_SIZE_64 ;if (!spapr->htab) {@@ -1551,6 +1551,38 @@ static void spapr_store_hpte(PPCVirtualHypervisor *vhyp, hwaddr ptex, } } +static void spapr_hpte_set_c (PPCVirtualHypervisor *vhyp,hwaddr ptex, +uint64_t pte1) +{ +hwaddr offset = ptex *HASH_PTE_SIZE_64 +15 ; +SpaprMachineState *spapr =SPAPR_MACHINE (vhyp); + +if (!spapr->htab) { +/* There should always be a hash table when this is called */ +error_report ("spapr_hpte_set_c called with no hash table !" ); +return ; + } + +/* The HW performs a non-atomic byte update */ +stb_p (spapr->htab + offset, (pte1 &0xff ) |0x80 ); +} + +static void spapr_hpte_set_r (PPCVirtualHypervisor *vhyp,hwaddr ptex, +uint64_t pte1) +{ +hwaddr offset = ptex *HASH_PTE_SIZE_64 +14 ; +SpaprMachineState *spapr =SPAPR_MACHINE (vhyp); + +if (!spapr->htab) { +/* There should always be a hash table when this is called */ +error_report ("spapr_hpte_set_r called with no hash table !" ); +return ; + } + +/* The HW performs a non-atomic byte update */ +stb_p (spapr->htab + offset, ((pte1 >>8 ) &0xff ) |0x01 ); +} +int spapr_hpt_shift_for_ramsize (uint64_t ramsize) {int shift;@@ -4291,7 +4323,8 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data) vhc->hpt_mask = spapr_hpt_mask; vhc->map_hptes = spapr_map_hptes; vhc->unmap_hptes = spapr_unmap_hptes; - vhc->store_hpte = spapr_store_hpte; + vhc->hpte_set_c = spapr_hpte_set_c; + vhc->hpte_set_r = spapr_hpte_set_r; vhc->get_pate = spapr_get_pate; vhc->encode_hpt_for_kvm_pr = spapr_encode_hpt_for_kvm_pr; xic->ics_get = spapr_ics_get;hw/ppc/spapr_hcall.c +7
-6@@ -118,7 +118,7 @@ static target_ulong h_enter(PowerPCCPU *cpu, SpaprMachineState *spapr,ppc_hash64_unmap_hptes (cpu, hptes, ptex,1 ); } -ppc_hash64_store_hpte (cpu, ptex + slot, pteh |HPTE64_V_HPTE_DIRTY , ptel); +spapr_store_hpte (cpu, ptex + slot, pteh |HPTE64_V_HPTE_DIRTY , ptel); args[0 ] = ptex + slot;return H_SUCCESS ;@@ -131,7 +131,8 @@ typedef enum {REMOVE_HW =3 , } RemoveResult; -static RemoveResult remove_hpte (PowerPCCPU *cpu,target_ulong ptex, +static RemoveResult remove_hpte (PowerPCCPU *cpu + ,target_ulong ptex,target_ulong avpn,target_ulong flags,target_ulong *vp,target_ulong *rp)@@ -155,7 +156,7 @@ static RemoveResult remove_hpte(PowerPCCPU *cpu, target_ulong ptex, } *vp = v; *rp = r; -ppc_hash64_store_hpte (cpu, ptex,HPTE64_V_HPTE_DIRTY ,0 ); +spapr_store_hpte (cpu, ptex,HPTE64_V_HPTE_DIRTY ,0 );ppc_hash64_tlb_flush_hpte (cpu, ptex, v, r);return REMOVE_SUCCESS ; }@@ -289,13 +290,13 @@ static target_ulong h_protect(PowerPCCPU *cpu, SpaprMachineState *spapr, r |= (flags <<55 ) &HPTE64_R_PP0 ; r |= (flags <<48 ) &HPTE64_R_KEY_HI ; r |= flags & (HPTE64_R_PP |HPTE64_R_N |HPTE64_R_KEY_LO ); -ppc_hash64_store_hpte (cpu, ptex, - (v & ~HPTE64_V_VALID ) |HPTE64_V_HPTE_DIRTY ,0 ); +spapr_store_hpte (cpu, ptex, + (v & ~HPTE64_V_VALID ) |HPTE64_V_HPTE_DIRTY ,0 );ppc_hash64_tlb_flush_hpte (cpu, ptex, v, r);/* Flush the tlb */ check_tlb_flush (env, true);/* Don't need a memory barrier, due to qemu's global lock */ -ppc_hash64_store_hpte (cpu, ptex, v |HPTE64_V_HPTE_DIRTY , r); +spapr_store_hpte (cpu, ptex, v |HPTE64_V_HPTE_DIRTY , r);return H_SUCCESS ; }target/ppc/mmu-hash64.c +45
-31@@ -724,6 +724,39 @@ static void ppc_hash64_set_dsi(CPUState *cs, uint64_t dar, uint64_t dsisr) } +static void ppc_hash64_set_r (PowerPCCPU *cpu,hwaddr ptex,uint64_t pte1) +{ +hwaddr base, offset = ptex *HASH_PTE_SIZE_64 +16 ; + +if (cpu->vhyp) { +PPCVirtualHypervisorClass *vhc = +PPC_VIRTUAL_HYPERVISOR_GET_CLASS (cpu->vhyp); + vhc->hpte_set_r (cpu->vhyp, ptex, pte1); +return ; + } + base =ppc_hash64_hpt_base (cpu); + + +/* The HW performs a non-atomic byte update */ +stb_phys (CPU (cpu)->as, base + offset, ((pte1 >>8 ) &0xff ) |0x01 ); +} + +static void ppc_hash64_set_c (PowerPCCPU *cpu,hwaddr ptex,uint64_t pte1) +{ +hwaddr base, offset = ptex *HASH_PTE_SIZE_64 +15 ; + +if (cpu->vhyp) { +PPCVirtualHypervisorClass *vhc = +PPC_VIRTUAL_HYPERVISOR_GET_CLASS (cpu->vhyp); + vhc->hpte_set_c (cpu->vhyp, ptex, pte1); +return ; + } + base =ppc_hash64_hpt_base (cpu); + +/* The HW performs a non-atomic byte update */ +stb_phys (CPU (cpu)->as, base + offset, (pte1 &0xff ) |0x80 ); +} +int ppc_hash64_handle_mmu_fault (PowerPCCPU *cpu,vaddr eaddr,int rwx,int mmu_idx) {@@ -734,7 +767,6 @@ int ppc_hash64_handle_mmu_fault(PowerPCCPU *cpu, vaddr eaddr,hwaddr ptex;ppc_hash_pte64_t pte;int exec_prot, pp_prot, amr_prot, prot; -uint64_t new_pte1;const int need_prot[] = {PAGE_READ ,PAGE_WRITE ,PAGE_EXEC };hwaddr raddr;@@ -882,19 +914,19 @@ skip_slb_search:/* 6. Update PTE referenced and changed bits if necessary */ - new_pte1 = pte.pte1 |HPTE64_R_R ;/* set referenced bit */ -if (rwx ==1 ) { - new_pte1 |=HPTE64_R_C ;/* set changed (dirty) bit */ - }else { -/* -* Treat the page as read-only for now, so that a later write -* will pass through this function again to set the C bit -*/ - prot &= ~PAGE_WRITE ; +if (!(pte.pte1 &HPTE64_R_R )) { +ppc_hash64_set_r (cpu, ptex, pte.pte1); } - -if (new_pte1 != pte.pte1) { -ppc_hash64_store_hpte (cpu, ptex, pte.pte0, new_pte1); +if (!(pte.pte1 &HPTE64_R_C )) { +if (rwx ==1 ) { +ppc_hash64_set_c (cpu, ptex, pte.pte1); + }else { +/* +* Treat the page as read-only for now, so that a later write +* will pass through this function again to set the C bit +*/ + prot &= ~PAGE_WRITE ; + } }/* 7. Determine the real address from the PTE */ @@ -953,24 +985,6 @@ hwaddr ppc_hash64_get_phys_page_debug(PowerPCCPU *cpu, target_ulong addr) &TARGET_PAGE_MASK ; } -void ppc_hash64_store_hpte (PowerPCCPU *cpu,hwaddr ptex, -uint64_t pte0,uint64_t pte1) -{ -hwaddr base; -hwaddr offset = ptex *HASH_PTE_SIZE_64 ; - -if (cpu->vhyp) { -PPCVirtualHypervisorClass *vhc = -PPC_VIRTUAL_HYPERVISOR_GET_CLASS (cpu->vhyp); - vhc->store_hpte (cpu->vhyp, ptex, pte0, pte1); -return ; - } - base =ppc_hash64_hpt_base (cpu); - -stq_phys (CPU (cpu)->as, base + offset, pte0); -stq_phys (CPU (cpu)->as, base + offset +HASH_PTE_SIZE_64 /2 , pte1); -} -void ppc_hash64_tlb_flush_hpte (PowerPCCPU *cpu,target_ulong ptex,target_ulong pte0,target_ulong pte1) {
Signature · 4 lines
David Gibson | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_ | _way_ _around_! http://www.ozlabs.org/~dgibson
PATCH 4/6 ppc/hash32: Rework R and C bit updates
In reply to Cédric Le GoaterFrom: Benjamin Herrenschmidt <[email protected]>
With MT-TCG, we are now running translation in a racy way, thus we need to mimic hardware when it comes to updating the R and C bits, by doing byte stores.
--- target/ppc/mmu-hash32.c | 45 ++++++++++++++++++++++++++++------------- 1 file changed, 31 insertions(+), 14 deletions(-)
target/ppc/mmu-hash32.c +31 -14
@@ -345,6 +345,24 @@ static hwaddr ppc_hash32_pteg_search(PowerPCCPU *cpu, hwaddr pteg_off,return -1 ; } +static void ppc_hash32_set_r (PowerPCCPU *cpu,hwaddr pte_offset,uint32_t pte1) +{ +target_ulong base =ppc_hash32_hpt_base (cpu); +hwaddr offset = pte_offset +6 ; + +/* The HW performs a non-atomic byte update */ +stb_phys (CPU (cpu)->as, base + offset, ((pte1 >>8 ) &0xff ) |0x01 ); +} + +static void ppc_hash32_set_c (PowerPCCPU *cpu,hwaddr pte_offset,uint64_t pte1) +{ +target_ulong base =ppc_hash32_hpt_base (cpu); +hwaddr offset = pte_offset +7 ; + +/* The HW performs a non-atomic byte update */ +stb_phys (CPU (cpu)->as, base + offset, (pte1 &0xff ) |0x80 ); +} +static hwaddr ppc_hash32_htab_lookup (PowerPCCPU *cpu,target_ulong sr,target_ulong eaddr,ppc_hash_pte32_t *pte)
@@ -403,7 +421,6 @@ int ppc_hash32_handle_mmu_fault(PowerPCCPU *cpu, vaddr eaddr, int rwx,hwaddr pte_offset;ppc_hash_pte32_t pte;int prot; -uint32_t new_pte1;const int need_prot[] = {PAGE_READ ,PAGE_WRITE ,PAGE_EXEC };hwaddr raddr;
@@ -519,20 +536,20 @@ int ppc_hash32_handle_mmu_fault(PowerPCCPU *cpu, vaddr eaddr, int rwx,/* 8. Update PTE referenced and changed bits if necessary */ - new_pte1 = pte.pte1 |HPTE32_R_R ;/* set referenced bit */ -if (rwx ==1 ) { - new_pte1 |=HPTE32_R_C ;/* set changed (dirty) bit */ - }else { -/* -* Treat the page as read-only for now, so that a later write -* will pass through this function again to set the C bit -*/ - prot &= ~PAGE_WRITE ; - } - -if (new_pte1 != pte.pte1) { -ppc_hash32_store_hpte1 (cpu, pte_offset, new_pte1); +if (!(pte.pte1 &HPTE32_R_R )) { +ppc_hash32_set_r (cpu, pte_offset, pte.pte1); } +if (!(pte.pte1 &HPTE32_R_C )) { +if (rwx ==1 ) { +ppc_hash32_set_c (cpu, pte_offset, pte.pte1); + }else { +/* +* Treat the page as read-only for now, so that a later write +* will pass through this function again to set the C bit +*/ + prot &= ~PAGE_WRITE ; + } + }/* 9. Determine the real address from the PTE */
Signature · 1 line
2.20.1
David Gibson
AppliedRe: [Qemu-devel] [PATCH 4/6] ppc/hash32: Rework R and C bit updates
Quoted 8 lines · Cédric Le Goater
From: Benjamin Herrenschmidt <[email protected]>
With MT-TCG, we are now running translation in a racy way, thus we need to mimic hardware when it comes to updating the R and C bits, by doing byte stores.
Signed-off-by Benjamin Herrenschmidt <[email protected]>Signed-off-by Cédric Le Goater <[email protected]>
Applied, thanks.
Quoted 75 lines
--- target/ppc/mmu-hash32.c | 45 ++++++++++++++++++++++++++++------------- 1 file changed, 31 insertions(+), 14 deletions(-)target/ppc/mmu-hash32.c +31
-14@@ -345,6 +345,24 @@ static hwaddr ppc_hash32_pteg_search(PowerPCCPU *cpu, hwaddr pteg_off,return -1 ; } +static void ppc_hash32_set_r (PowerPCCPU *cpu,hwaddr pte_offset,uint32_t pte1) +{ +target_ulong base =ppc_hash32_hpt_base (cpu); +hwaddr offset = pte_offset +6 ; + +/* The HW performs a non-atomic byte update */ +stb_phys (CPU (cpu)->as, base + offset, ((pte1 >>8 ) &0xff ) |0x01 ); +} + +static void ppc_hash32_set_c (PowerPCCPU *cpu,hwaddr pte_offset,uint64_t pte1) +{ +target_ulong base =ppc_hash32_hpt_base (cpu); +hwaddr offset = pte_offset +7 ; + +/* The HW performs a non-atomic byte update */ +stb_phys (CPU (cpu)->as, base + offset, (pte1 &0xff ) |0x80 ); +} +static hwaddr ppc_hash32_htab_lookup (PowerPCCPU *cpu,target_ulong sr,target_ulong eaddr,ppc_hash_pte32_t *pte)@@ -403,7 +421,6 @@ int ppc_hash32_handle_mmu_fault(PowerPCCPU *cpu, vaddr eaddr, int rwx,hwaddr pte_offset;ppc_hash_pte32_t pte;int prot; -uint32_t new_pte1;const int need_prot[] = {PAGE_READ ,PAGE_WRITE ,PAGE_EXEC };hwaddr raddr;@@ -519,20 +536,20 @@ int ppc_hash32_handle_mmu_fault(PowerPCCPU *cpu, vaddr eaddr, int rwx,/* 8. Update PTE referenced and changed bits if necessary */ - new_pte1 = pte.pte1 |HPTE32_R_R ;/* set referenced bit */ -if (rwx ==1 ) { - new_pte1 |=HPTE32_R_C ;/* set changed (dirty) bit */ - }else { -/* -* Treat the page as read-only for now, so that a later write -* will pass through this function again to set the C bit -*/ - prot &= ~PAGE_WRITE ; - } - -if (new_pte1 != pte.pte1) { -ppc_hash32_store_hpte1 (cpu, pte_offset, new_pte1); +if (!(pte.pte1 &HPTE32_R_R )) { +ppc_hash32_set_r (cpu, pte_offset, pte.pte1); } +if (!(pte.pte1 &HPTE32_R_C )) { +if (rwx ==1 ) { +ppc_hash32_set_c (cpu, pte_offset, pte.pte1); + }else { +/* +* Treat the page as read-only for now, so that a later write +* will pass through this function again to set the C bit +*/ + prot &= ~PAGE_WRITE ; + } + }/* 9. Determine the real address from the PTE */
Signature · 4 lines
David Gibson | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_ | _way_ _around_! http://www.ozlabs.org/~dgibson
PATCH 5/6 memory_ldst: Add atomic ops for PTE updates
In reply to Cédric Le GoaterFrom: Benjamin Herrenschmidt <[email protected]>
On some architectures, PTE updates for dirty and changed bits need to be performed atomically. This adds a couple of address_space_cmpxchg* helpers for that purpose.
--- include/exec/memory_ldst.inc.h | 6 +++ memory_ldst.inc.c | 80 ++++++++++++++++++++++++++++++++++ 2 files changed, 86 insertions(+)
include/exec/memory_ldst.inc.h +6 -0
@@ -28,6 +28,12 @@ extern uint64_t glue(address_space_ldq, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result);extern void glue (address_space_stl_notdirty ,SUFFIX )(ARG1_DECL ,hwaddr addr,uint32_t val,MemTxAttrs attrs,MemTxResult *result); +extern uint32_t glue (address_space_cmpxchgl_notdirty ,SUFFIX )(ARG1_DECL , +hwaddr addr,uint32_t old,uint32_t new,MemTxAttrs attrs, +MemTxResult *result); +extern uint32_t glue (address_space_cmpxchgq_notdirty ,SUFFIX )(ARG1_DECL , +hwaddr addr,uint64_t old,uint64_t new,MemTxAttrs attrs, +MemTxResult *result);extern void glue (address_space_stw ,SUFFIX )(ARG1_DECL ,hwaddr addr,uint32_t val,MemTxAttrs attrs,MemTxResult *result); extern void glue(address_space_stl, SUFFIX)(ARG1_DECL,
memory_ldst.inc.c +80 -0
86 lines not on this page · raw message
Signature · 1 line
2.20.1
Re: [Qemu-devel] [PATCH 5/6] memory_ldst: Add atomic ops for PTE updates
Quoted 8 lines · Cédric Le Goater
From: Benjamin Herrenschmidt <[email protected]>
On some architectures, PTE updates for dirty and changed bits need to be performed atomically. This adds a couple of address_space_cmpxchg* helpers for that purpose.
Signed-off-by Benjamin Herrenschmidt <[email protected]>Signed-off-by Cédric Le Goater <[email protected]>
But I think this needs to go past Paolo for review as memory subsystem maintainer.
Quoted 113 lines
--- include/exec/memory_ldst.inc.h | 6 +++ memory_ldst.inc.c | 80 ++++++++++++++++++++++++++++++++++ 2 files changed, 86 insertions(+)include/exec/memory_ldst.inc.h +6
-0@@ -28,6 +28,12 @@ extern uint64_t glue(address_space_ldq, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result);extern void glue (address_space_stl_notdirty ,SUFFIX )(ARG1_DECL ,hwaddr addr,uint32_t val,MemTxAttrs attrs,MemTxResult *result); +extern uint32_t glue (address_space_cmpxchgl_notdirty ,SUFFIX )(ARG1_DECL , +hwaddr addr,uint32_t old,uint32_t new,MemTxAttrs attrs, +MemTxResult *result); +extern uint32_t glue (address_space_cmpxchgq_notdirty ,SUFFIX )(ARG1_DECL , +hwaddr addr,uint64_t old,uint64_t new,MemTxAttrs attrs, +MemTxResult *result);extern void glue (address_space_stw ,SUFFIX )(ARG1_DECL ,hwaddr addr,uint32_t val,MemTxAttrs attrs,MemTxResult *result); extern void glue(address_space_stl, SUFFIX)(ARG1_DECL,memory_ldst.inc.c +80
-0@@ -320,6 +320,86 @@ void glue(address_space_stl_notdirty, SUFFIX)(ARG1_DECL,RCU_READ_UNLOCK (); } +/* This is meant to be used for atomic PTE updates under MT-TCG */ +uint32_t glue (address_space_cmpxchgl_notdirty ,SUFFIX )(ARG1_DECL , +hwaddr addr,uint32_t old,uint32_t new,MemTxAttrs attrs, +MemTxResult *result) +{ +uint8_t *ptr; +MemoryRegion *mr; +hwaddr l =4 ; +hwaddr addr1; +MemTxResult r; +uint8_t dirty_log_mask; + +/* Must test result */ +assert (result); + +RCU_READ_LOCK (); + mr =TRANSLATE (addr, &addr1, &l, true, attrs); +if (l <4 || !memory_access_is_direct (mr, true)) { + r =MEMTX_ERROR ; + }else { +uint32_t orig = old; + + ptr =qemu_map_ram_ptr (mr->ram_block, addr1); + old =atomic_cmpxchg (ptr, orig, new); + +if (old == orig) { + dirty_log_mask =memory_region_get_dirty_log_mask (mr); + dirty_log_mask &= ~(1 <<DIRTY_MEMORY_CODE ); +cpu_physical_memory_set_dirty_range (memory_region_get_ram_addr (mr) + + addr,4 , dirty_log_mask); + } + r =MEMTX_OK ; + } + *result = r; +RCU_READ_UNLOCK (); + +return old; +} + +#ifdef CONFIG_ATOMIC64 +/* This is meant to be used for atomic PTE updates under MT-TCG */ +uint32_t glue (address_space_cmpxchgq_notdirty ,SUFFIX )(ARG1_DECL , +hwaddr addr,uint64_t old,uint64_t new,MemTxAttrs attrs, +MemTxResult *result) +{ +uint8_t *ptr; +MemoryRegion *mr; +hwaddr l =8 ; +hwaddr addr1; +MemTxResult r; +uint8_t dirty_log_mask; + +/* Must test result */ +assert (result); + +RCU_READ_LOCK (); + mr =TRANSLATE (addr, &addr1, &l, true, attrs); +if (l <8 || !memory_access_is_direct (mr, true)) { + r =MEMTX_ERROR ; + }else { +uint32_t orig = old; + + ptr =qemu_map_ram_ptr (mr->ram_block, addr1); + old =atomic_cmpxchg (ptr, orig, new); + +if (old == orig) { + dirty_log_mask =memory_region_get_dirty_log_mask (mr); + dirty_log_mask &= ~(1 <<DIRTY_MEMORY_CODE ); +cpu_physical_memory_set_dirty_range (memory_region_get_ram_addr (mr) + + addr,8 , dirty_log_mask); + } + r =MEMTX_OK ; + } + *result = r; +RCU_READ_UNLOCK (); + +return old; +} +#endif /* CONFIG_ATOMIC64 */ +/* warning: addr must be aligned */ static inline void glue(address_space_stl_internal, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val, MemTxAttrs attrs,
Signature · 4 lines
David Gibson | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_ | _way_ _around_! http://www.ozlabs.org/~dgibson
Re: [Qemu-devel] [PATCH 5/6] memory_ldst: Add atomic ops for PTE updates
Quoted 8 lines · David Gibson
Quoted 7 lines · Cédric Le Goater
From: Benjamin Herrenschmidt <[email protected]>
On some architectures, PTE updates for dirty and changed bits need to be performed atomically. This adds a couple of address_space_cmpxchg*
helpers for that purpose.
Quoted 7 lines
Quoted 2 lines
Signed-off-by Benjamin Herrenschmidt <[email protected]>Signed-off-by Cédric Le Goater <[email protected]>Reviewed-by David Gibson <[email protected]>But I think this needs to go past Paolo for review as memory subsystem maintainer.
This needs to go to rth and Peter. They were talking about a change in the abstraction to do these more cleanly... that said, it might be worthwhile merging the fixes first.
Cheers,
Ben.
Quoted 129 lines
Quoted 127 lines
--- include/exec/memory_ldst.inc.h | 6 +++ memory_ldst.inc.c | 80 ++++++++++++++++++++++++++++++++++ 2 files changed, 86 insertions(+)include/exec/memory_ldst.inc.h +4
-0@@ -28,6 +28,12 @@ extern uint64_t glue(address_space_ldq, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result);extern void glue (address_space_stl_notdirty ,SUFFIX )(ARG1_DECL ,hwaddr addr,uint32_t val,MemTxAttrs attrs,MemTxResult *result); +extern uint32_t glue (address_space_cmpxchgl_notdirty ,SUFFIX )(ARG1_DECL , +hwaddr addr,uint32_t old,uint32_t new,MemTxAttrs attrs, +MemTxResult *result); +extern uint32_t glue(address_space_cmpxchgq_notdirty,SUFFIX)(ARG1_DECL,
include/exec/memory_ldst.inc.h +2
-0+ hwaddr addr, uint64_t old, uint64_t new, MemTxAttrs attrs, + MemTxResult *result);extern void glue (address_space_stw ,SUFFIX )(ARG1_DECL , hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult*result);
extern voidglue(address_space_stl, SUFFIX)(ARG1_DECL,memory_ldst.inc.c +29
-0@@ -320,6 +320,86 @@ void glue(address_space_stl_notdirty, SUFFIX)(ARG1_DECL,RCU_READ_UNLOCK (); } +/* This is meant to be used for atomic PTE updates under MT-TCG */ +uint32_t glue (address_space_cmpxchgl_notdirty ,SUFFIX )(ARG1_DECL , +hwaddr addr,uint32_t old,uint32_t new,MemTxAttrs attrs, +MemTxResult *result) +{ +uint8_t *ptr; +MemoryRegion *mr; +hwaddr l =4 ; +hwaddr addr1; +MemTxResult r; +uint8_t dirty_log_mask; + +/* Must test result */ +assert (result); + +RCU_READ_LOCK (); + mr =TRANSLATE (addr, &addr1, &l, true, attrs); +if (l <4 || !memory_access_is_direct (mr, true)) { + r =MEMTX_ERROR ; + }else { +uint32_t orig = old; + + ptr =qemu_map_ram_ptr (mr->ram_block, addr1); + old =atomic_cmpxchg (ptr, orig, new); + +if (old == orig) { + dirty_log_mask =memory_region_get_dirty_log_mask (mr); + dirty_log_mask &= ~(1 <<DIRTY_MEMORY_CODE ); + cpu_physical_memory_set_dirty_range(memory_region_get_
ram_addr(mr)+
+ addr, 4,dirty_log_mask);memory_ldst.inc.c +39
-0+ } + r =MEMTX_OK ; + } + *result = r; +RCU_READ_UNLOCK (); + +return old; +} + +#ifdef CONFIG_ATOMIC64 +/* This is meant to be used for atomic PTE updates under MT-TCG */ +uint32_t glue (address_space_cmpxchgq_notdirty ,SUFFIX )(ARG1_DECL , +hwaddr addr,uint64_t old,uint64_t new,MemTxAttrs attrs, +MemTxResult *result) +{ +uint8_t *ptr; +MemoryRegion *mr; +hwaddr l =8 ; +hwaddr addr1; +MemTxResult r; +uint8_t dirty_log_mask; + +/* Must test result */ +assert (result); + +RCU_READ_LOCK (); + mr =TRANSLATE (addr, &addr1, &l, true, attrs); +if (l <8 || !memory_access_is_direct (mr, true)) { + r =MEMTX_ERROR ; + }else { +uint32_t orig = old; + + ptr =qemu_map_ram_ptr (mr->ram_block, addr1); + old =atomic_cmpxchg (ptr, orig, new); + +if (old == orig) { + dirty_log_mask =memory_region_get_dirty_log_mask (mr); + dirty_log_mask &= ~(1 <<DIRTY_MEMORY_CODE ); + cpu_physical_memory_set_dirty_range(memory_region_get_
ram_addr(mr)+
+ addr, 8,dirty_log_mask);memory_ldst.inc.c +10
-0+ } + r =MEMTX_OK ; + } + *result = r; +RCU_READ_UNLOCK (); + +return old; +} +#endif /* CONFIG_ATOMIC64 */ +/* warning: addr must be aligned */ static inline void glue(address_space_stl_internal,SUFFIX)(ARG1_DECL,
hwaddr addr,uint32_tval, MemTxAttrs attrs,
Re: [Qemu-devel] [PATCH 5/6] memory_ldst: Add atomic ops for PTE updates
In reply to David GibsonQuoted 7 lines · David Gibson
Quoted 6 lines · Cédric Le Goater
From: Benjamin Herrenschmidt <[email protected]>
On some architectures, PTE updates for dirty and changed bits need to be performed atomically. This adds a couple of address_space_cmpxchg* helpers for that purpose.
Quoted 6 lines
Quoted 2 lines
Signed-off-by Benjamin Herrenschmidt <[email protected]>Signed-off-by Cédric Le Goater <[email protected]>Reviewed-by David Gibson <[email protected]>But I think this needs to go past Paolo for review as memory subsystem maintainer.
I will resend the last two patches in a new patchset and include a fix for Intel that Ben provided.
Thanks,
C.
Quoted 115 lines
Quoted 114 lines
--- include/exec/memory_ldst.inc.h | 6 +++ memory_ldst.inc.c | 80 ++++++++++++++++++++++++++++++++++ 2 files changed, 86 insertions(+)include/exec/memory_ldst.inc.h +6
-0@@ -28,6 +28,12 @@ extern uint64_t glue(address_space_ldq, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result);extern void glue (address_space_stl_notdirty ,SUFFIX )(ARG1_DECL ,hwaddr addr,uint32_t val,MemTxAttrs attrs,MemTxResult *result); +extern uint32_t glue (address_space_cmpxchgl_notdirty ,SUFFIX )(ARG1_DECL , +hwaddr addr,uint32_t old,uint32_t new,MemTxAttrs attrs, +MemTxResult *result); +extern uint32_t glue (address_space_cmpxchgq_notdirty ,SUFFIX )(ARG1_DECL , +hwaddr addr,uint64_t old,uint64_t new,MemTxAttrs attrs, +MemTxResult *result);extern void glue (address_space_stw ,SUFFIX )(ARG1_DECL ,hwaddr addr,uint32_t val,MemTxAttrs attrs,MemTxResult *result); extern void glue(address_space_stl, SUFFIX)(ARG1_DECL,memory_ldst.inc.c +80
-0@@ -320,6 +320,86 @@ void glue(address_space_stl_notdirty, SUFFIX)(ARG1_DECL,RCU_READ_UNLOCK (); } +/* This is meant to be used for atomic PTE updates under MT-TCG */ +uint32_t glue (address_space_cmpxchgl_notdirty ,SUFFIX )(ARG1_DECL , +hwaddr addr,uint32_t old,uint32_t new,MemTxAttrs attrs, +MemTxResult *result) +{ +uint8_t *ptr; +MemoryRegion *mr; +hwaddr l =4 ; +hwaddr addr1; +MemTxResult r; +uint8_t dirty_log_mask; + +/* Must test result */ +assert (result); + +RCU_READ_LOCK (); + mr =TRANSLATE (addr, &addr1, &l, true, attrs); +if (l <4 || !memory_access_is_direct (mr, true)) { + r =MEMTX_ERROR ; + }else { +uint32_t orig = old; + + ptr =qemu_map_ram_ptr (mr->ram_block, addr1); + old =atomic_cmpxchg (ptr, orig, new); + +if (old == orig) { + dirty_log_mask =memory_region_get_dirty_log_mask (mr); + dirty_log_mask &= ~(1 <<DIRTY_MEMORY_CODE ); +cpu_physical_memory_set_dirty_range (memory_region_get_ram_addr (mr) + + addr,4 , dirty_log_mask); + } + r =MEMTX_OK ; + } + *result = r; +RCU_READ_UNLOCK (); + +return old; +} + +#ifdef CONFIG_ATOMIC64 +/* This is meant to be used for atomic PTE updates under MT-TCG */ +uint32_t glue (address_space_cmpxchgq_notdirty ,SUFFIX )(ARG1_DECL , +hwaddr addr,uint64_t old,uint64_t new,MemTxAttrs attrs, +MemTxResult *result) +{ +uint8_t *ptr; +MemoryRegion *mr; +hwaddr l =8 ; +hwaddr addr1; +MemTxResult r; +uint8_t dirty_log_mask; + +/* Must test result */ +assert (result); + +RCU_READ_LOCK (); + mr =TRANSLATE (addr, &addr1, &l, true, attrs); +if (l <8 || !memory_access_is_direct (mr, true)) { + r =MEMTX_ERROR ; + }else { +uint32_t orig = old; + + ptr =qemu_map_ram_ptr (mr->ram_block, addr1); + old =atomic_cmpxchg (ptr, orig, new); + +if (old == orig) { + dirty_log_mask =memory_region_get_dirty_log_mask (mr); + dirty_log_mask &= ~(1 <<DIRTY_MEMORY_CODE ); +cpu_physical_memory_set_dirty_range (memory_region_get_ram_addr (mr) + + addr,8 , dirty_log_mask); + } + r =MEMTX_OK ; + } + *result = r; +RCU_READ_UNLOCK (); + +return old; +} +#endif /* CONFIG_ATOMIC64 */ +/* warning: addr must be aligned */ static inline void glue(address_space_stl_internal, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val, MemTxAttrs attrs,
PATCH 6/6 ppc: Fix radix RC updates
In reply to Cédric Le GoaterFrom: Benjamin Herrenschmidt <[email protected]>
They should be atomic for MTTCG. Note: a real POWER9 core doesn't actually implement atomic PTE updates, it always fault for SW to handle it. Only the nest MMU (used by some accelerator devices and GPUs) implements those HW updates.
However, the architecture does allow the core to do it, and doing so in TCG is faster than letting the guest do it.
--- target/ppc/cpu.h | 1 + target/ppc/mmu-radix64.c | 70 +++++++++++++++++++++++++++++++++------- 2 files changed, 60 insertions(+), 11 deletions(-)
target/ppc/cpu.h +1 -0
@@ -503,6 +503,7 @@ typedef struct ppc_v3_pate_t {#define DSISR_AMR 0x00200000/* Unsupported Radix Tree Configuration */ #define DSISR_R_BADCONFIG 0x00080000 +#define DSISR_ATOMIC_RC 0x00040000/* SRR1 error code fields */
target/ppc/mmu-radix64.c +59 -11
107 lines not on this page · raw message
Signature · 1 line
2.20.1