UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/arch/sparc/kernel/ktlb.S

353 lines
7.5 KiB
ArmAsm
Raw Normal View History

[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
/* arch/sparc64/kernel/ktlb.S: Kernel mapping TLB miss handling.
*
[SPARC64]: Fix build with SPARSEMEM_VMEMMAP disabled. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-11 13:10:54 +08:00
* Copyright (C) 1995, 1997, 2005, 2008 David S. Miller <davem@davemloft.net>
[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
* Copyright (C) 1996 Eddie C. Dost (ecd@brainaid.de)
* Copyright (C) 1996 Miguel de Icaza (miguel@nuclecu.unam.mx)
* Copyright (C) 1996,98,99 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
*/
[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
#include <asm/head.h>
#include <asm/asi.h>
#include <asm/page.h>
#include <asm/pgtable.h>
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
#include <asm/tsb.h>
[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
.text
.align 32
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
kvmap_itlb:
/* g6: TAG TARGET */
mov TLB_TAG_ACCESS, %g4
ldxa [%g4] ASI_IMMU, %g4
[SPARC64]: Initial sun4v TLB miss handling infrastructure. Things are a little tricky because, unlike sun4u, we have to: 1) do a hypervisor trap to do the TLB load. 2) do the TSB lookup calculations by hand Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-07 15:44:37 +08:00
/* sun4v_itlb_miss branches here with the missing virtual
* address already loaded into %g4
*/
kvmap_itlb_4v:
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
/* Catch kernel NULL pointer calls. */
sethi %hi(PAGE_SIZE), %g5
cmp %g4, %g5
sparc64: Fix ITLB handler of null page 1)Use kvmap_itlb_longpath instead of kvmap_dtlb_longpath. 2)Handle page #0 only, don't handle page #1: bleu -> blu (KERNBASE is 0x400000, so #1 does not exist too. But everything is possible in the future. Fix to not to have problems later.) 3)Remove unused kvmap_itlb_nonlinear. Signed-off-by: Kirill Tkhai <tkhai@yandex.ru> CC: David Miller <davem@davemloft.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-02 23:23:18 +08:00
blu,pn %xcc, kvmap_itlb_longpath
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
nop
KERN_TSB_LOOKUP_TL1(%g4, %g6, %g5, %g1, %g2, %g3, kvmap_itlb_load)
kvmap_itlb_tsb_miss:
[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
sethi %hi(LOW_OBP_ADDRESS), %g5
cmp %g4, %g5
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
blu,pn %xcc, kvmap_itlb_vmalloc_addr
[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
mov 0x1, %g5
sllx %g5, 32, %g5
cmp %g4, %g5
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
blu,pn %xcc, kvmap_itlb_obp
[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
nop
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
kvmap_itlb_vmalloc_addr:
KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_itlb_longpath)
sparc: Access kernel TSB using physical addressing when possible. On sun4v this is basically required since we point the hypervisor and the TSB walking hardware at these tables using physical addressing too. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-08-05 15:53:57 +08:00
TSB_LOCK_TAG(%g1, %g2, %g7)
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
/* Load and check PTE. */
ldxa [%g5] ASI_PHYS_USE_EC, %g5
[SPARC64]: More TLB/TSB handling fixes. The SUN4V convention with non-shared TSBs is that the context bit of the TAG is clear. So we have to choose an "invalid" bit and initialize new TSBs appropriately. Otherwise a zero TAG looks "valid". Make sure, for the window fixup cases, that we use the right global registers and that we don't potentially trample on the live global registers in etrap/rtrap handling (%g2 and %g6) and that we put the missing virtual address properly in %g5. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-18 10:01:02 +08:00
mov 1, %g7
sllx %g7, TSB_TAG_INVALID_BIT, %g7
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
brgez,a,pn %g5, kvmap_itlb_longpath
sparc: Access kernel TSB using physical addressing when possible. On sun4v this is basically required since we point the hypervisor and the TSB walking hardware at these tables using physical addressing too. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-08-05 15:53:57 +08:00
TSB_STORE(%g1, %g7)
[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
sparc: Access kernel TSB using physical addressing when possible. On sun4v this is basically required since we point the hypervisor and the TSB walking hardware at these tables using physical addressing too. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-08-05 15:53:57 +08:00
TSB_WRITE(%g1, %g5, %g6)
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
/* fallthrough to TLB load */
kvmap_itlb_load:
[SPARC64]: Fix some SUN4V TLB miss bugs. Code patching did not sign extend negative branch offsets correctly. Kernel TLB miss path needs patching and %g4 register preservation in order to handle SUN4V correctly. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-12 04:21:20 +08:00
661: stxa %g5, [%g0] ASI_ITLB_DATA_IN
[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
retry
[SPARC64]: Fix some SUN4V TLB miss bugs. Code patching did not sign extend negative branch offsets correctly. Kernel TLB miss path needs patching and %g4 register preservation in order to handle SUN4V correctly. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-12 04:21:20 +08:00
.section .sun4v_2insn_patch, "ax"
.word 661b
nop
nop
.previous
/* For sun4v the ASI_ITLB_DATA_IN store and the retry
* instruction get nop'd out and we get here to branch
* to the sun4v tlb load code. The registers are setup
* as follows:
*
* %g4: vaddr
* %g5: PTE
* %g6: TAG
*
* The sun4v TLB load wants the PTE in %g3 so we fix that
* up here.
*/
ba,pt %xcc, sun4v_itlb_load
mov %g5, %g3
[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
kvmap_itlb_longpath:
[SPARC64]: Sanitize %pstate writes for sun4v. If we're just switching between different alternate global sets, nop it out on sun4v. Also, get rid of all of the alternate global save/restore in the OBP CIF trampoline code. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-06 14:27:28 +08:00
661: rdpr %pstate, %g5
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
wrpr %g5, PSTATE_AG | PSTATE_MG, %pstate
[SPARC64]: Rename gl_{1,2}insn_patch --> sun4v_{1,2}insn_patch Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-07 16:00:16 +08:00
.section .sun4v_2insn_patch, "ax"
[SPARC64]: Sanitize %pstate writes for sun4v. If we're just switching between different alternate global sets, nop it out on sun4v. Also, get rid of all of the alternate global save/restore in the OBP CIF trampoline code. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-06 14:27:28 +08:00
.word 661b
[SPARC64]: Set %gl to 1 in kvmap_itlb_longpath on SUN4V. Just like kvmap_dtlb_longpath we have to force the global register level to one in order to mimick the PSTATE_MG --> PSTATE_AG trasition done on SUN4U. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-19 08:36:39 +08:00
SET_GL(1)
[SPARC64]: Sanitize %pstate writes for sun4v. If we're just switching between different alternate global sets, nop it out on sun4v. Also, get rid of all of the alternate global save/restore in the OBP CIF trampoline code. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-06 14:27:28 +08:00
nop
.previous
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
rdpr %tpc, %g5
ba,pt %xcc, sparc64_realfault_common
mov FAULT_CODE_ITLB, %g4
kvmap_itlb_obp:
OBP_TRANS_LOOKUP(%g4, %g5, %g2, %g3, kvmap_itlb_longpath)
sparc: Access kernel TSB using physical addressing when possible. On sun4v this is basically required since we point the hypervisor and the TSB walking hardware at these tables using physical addressing too. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-08-05 15:53:57 +08:00
TSB_LOCK_TAG(%g1, %g2, %g7)
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
sparc: Access kernel TSB using physical addressing when possible. On sun4v this is basically required since we point the hypervisor and the TSB walking hardware at these tables using physical addressing too. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-08-05 15:53:57 +08:00
TSB_WRITE(%g1, %g5, %g6)
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
ba,pt %xcc, kvmap_itlb_load
nop
kvmap_dtlb_obp:
OBP_TRANS_LOOKUP(%g4, %g5, %g2, %g3, kvmap_dtlb_longpath)
sparc: Access kernel TSB using physical addressing when possible. On sun4v this is basically required since we point the hypervisor and the TSB walking hardware at these tables using physical addressing too. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-08-05 15:53:57 +08:00
TSB_LOCK_TAG(%g1, %g2, %g7)
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
sparc: Access kernel TSB using physical addressing when possible. On sun4v this is basically required since we point the hypervisor and the TSB walking hardware at these tables using physical addressing too. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-08-05 15:53:57 +08:00
TSB_WRITE(%g1, %g5, %g6)
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
ba,pt %xcc, kvmap_dtlb_load
nop
[SPARC64]: Fix boot failures on SunBlade-150 The sequence to move over to the Linux trap tables from the firmware ones needs to be more air tight. It turns out that to be %100 safe we do need to be able to translate OBP mappings in our TLB miss handlers early. In order not to eat up a lot of kernel image memory with static page tables, just use the translations array in the OBP TLB miss handlers. That solves the bulk of the problem. Furthermore, to make sure the OBP TLB miss path will work even before the fixed MMU globals are loaded, explicitly load %g1 to TLB_SFSR at the beginning of the i-TLB and d-TLB miss handlers. To ease the OBP TLB miss walking of the prom_trans[] array, we sort it then delete all of the non-OBP entries in there (for example, there are entries for the kernel image itself which we're not interested in at all). We also save about 32K of kernel image size with this change. Not a bad side effect :-) There are still some reasons why trampoline.S can't use the setup_trap_table() yet. The most noteworthy are: 1) OBP boots secondary processors with non-bias'd stack for some reason. This is easily fixed by using a small bootup stack in the kernel image explicitly for this purpose. 2) Doing a firmware call via the normal C call prom_set_trap_table() goes through the whole OBP enter/exit sequence that saves and restores OBP and Linux kernel state in the MMUs. This path unfortunately does a "flush %g6" while loading up the OBP locked TLB entries for the firmware call. If we setup the %g6 in the trampoline.S code properly, that is in the PAGE_OFFSET linear mapping, but we're not on the kernel trap table yet so those addresses won't translate properly. One idea is to do a by-hand firmware call like we do in the early bootup code and elsewhere here in trampoline.S But this fails as well, as aparently the secondary processors are not booted with OBP's special locked TLB entries loaded. These are necessary for the firwmare to processes TLB misses correctly up until the point where we take over the trap table. This does need to be resolved at some point. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-10-13 03:22:46 +08:00
[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
.align 32
[SPARC64]: Create a seperate kernel TSB for 4MB/256MB mappings. It can map all of the linear kernel mappings with zero TSB hash conflicts for systems with 16GB or less ram. In such cases, on SUN4V, once we load up this TSB the first time with all the mappings, we never take a linear kernel mapping TLB miss ever again, the hypervisor handles them all. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-22 14:31:11 +08:00
kvmap_dtlb_tsb4m_load:
sparc: Access kernel TSB using physical addressing when possible. On sun4v this is basically required since we point the hypervisor and the TSB walking hardware at these tables using physical addressing too. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-08-05 15:53:57 +08:00
TSB_LOCK_TAG(%g1, %g2, %g7)
TSB_WRITE(%g1, %g5, %g6)
[SPARC64]: Create a seperate kernel TSB for 4MB/256MB mappings. It can map all of the linear kernel mappings with zero TSB hash conflicts for systems with 16GB or less ram. In such cases, on SUN4V, once we load up this TSB the first time with all the mappings, we never take a linear kernel mapping TLB miss ever again, the hypervisor handles them all. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-22 14:31:11 +08:00
ba,pt %xcc, kvmap_dtlb_load
nop
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
kvmap_dtlb:
/* %g6: TAG TARGET */
mov TLB_TAG_ACCESS, %g4
ldxa [%g4] ASI_DMMU, %g4
[SPARC64]: Initial sun4v TLB miss handling infrastructure. Things are a little tricky because, unlike sun4u, we have to: 1) do a hypervisor trap to do the TLB load. 2) do the TSB lookup calculations by hand Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-07 15:44:37 +08:00
/* sun4v_dtlb_miss branches here with the missing virtual
* address already loaded into %g4
*/
kvmap_dtlb_4v:
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
brgez,pn %g4, kvmap_dtlb_nonlinear
[SPARC64]: Add CONFIG_DEBUG_PAGEALLOC support. The trick is that we do the kernel linear mapping TLB miss starting with an instruction sequence like this: ba,pt %xcc, kvmap_load xor %g2, %g4, %g5 succeeded by an instruction sequence which performs a full page table walk starting at swapper_pg_dir. We first take over the trap table from the firmware. Then, using this constant PTE generation for the linear mapping area above, we build the kernel page tables for the linear mapping. After this is setup, we patch that branch above into a "nop", which will cause TLB misses to fall through to the full page table walk. With this, the page unmapping for CONFIG_DEBUG_PAGEALLOC is trivial. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-26 07:46:57 +08:00
nop
[SPARC64]: Get DEBUG_PAGEALLOC working again. We have to make sure to use base-pagesize TLB entries even during the early transition period where we need TLB miss handling but don't have the kernel page tables setup yet for the linear region. Also, it is necessary therefore to not use the 4MB TSB for these translations, and instead use the normal kernel TSB. This allows us to also get rid of the 4MB tsb for debug builds which shrinks the kernel a little bit. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-17 08:20:28 +08:00
#ifdef CONFIG_DEBUG_PAGEALLOC
/* Index through the base page size TSB even for linear
* mappings when using page allocation debugging.
*/
KERN_TSB_LOOKUP_TL1(%g4, %g6, %g5, %g1, %g2, %g3, kvmap_dtlb_load)
#else
[SPARC64]: Create a seperate kernel TSB for 4MB/256MB mappings. It can map all of the linear kernel mappings with zero TSB hash conflicts for systems with 16GB or less ram. In such cases, on SUN4V, once we load up this TSB the first time with all the mappings, we never take a linear kernel mapping TLB miss ever again, the hypervisor handles them all. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-22 14:31:11 +08:00
/* Correct TAG_TARGET is already in %g6, check 4mb TSB. */
KERN_TSB4M_LOOKUP_TL1(%g6, %g5, %g1, %g2, %g3, kvmap_dtlb_load)
[SPARC64]: Get DEBUG_PAGEALLOC working again. We have to make sure to use base-pagesize TLB entries even during the early transition period where we need TLB miss handling but don't have the kernel page tables setup yet for the linear region. Also, it is necessary therefore to not use the 4MB TSB for these translations, and instead use the normal kernel TSB. This allows us to also get rid of the 4MB tsb for debug builds which shrinks the kernel a little bit. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-17 08:20:28 +08:00
#endif
[SPARC64]: Create a seperate kernel TSB for 4MB/256MB mappings. It can map all of the linear kernel mappings with zero TSB hash conflicts for systems with 16GB or less ram. In such cases, on SUN4V, once we load up this TSB the first time with all the mappings, we never take a linear kernel mapping TLB miss ever again, the hypervisor handles them all. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-22 14:31:11 +08:00
/* TSB entry address left in %g1, lookup linear PTE.
* Must preserve %g1 and %g6 (TAG).
*/
kvmap_dtlb_tsb4m_miss:
sparc64: Validate linear D-TLB misses. When page alloc debugging is not enabled, we essentially accept any virtual address for linear kernel TLB misses. But with kgdb, kernel address probing, and other facilities we can try to access arbitrary crap. So, make sure the address we miss on will translate to physical memory that actually exists. In order to make this work we have to embed the valid address bitmap into the kernel image. And in order to make that less expensive we make an adjustment, in that the max physical memory address is decreased to "1 << 41", even on the chips that support a 42-bit physical address space. We can do this because bit 41 indicates "I/O space" and thus covers non-memory ranges. The result of this is that: 1) kpte_linear_bitmap shrinks from 2K to 1K in size 2) we need 64K more for the valid address bitmap We can't let the valid address bitmap be dynamically allocated once we start using it to validate TLB misses, otherwise we have crazy issues to deal with wrt. recursive TLB misses and such. If we're in a TLB miss it could be the deepest trap level that's legal inside of the cpu. So if we TLB miss referencing the bitmap, the cpu will be out of trap levels and enter RED state. To guard against out-of-range accesses to the bitmap, we have to check to make sure no bits in the physical address above bit 40 are set. We could export and use last_valid_pfn for this check, but that's just an unnecessary extra memory reference. On the plus side of all this, since we load all of these translations into the special 4MB mapping TSB, and we check the TSB first for TLB misses, there should be absolutely no real cost for these new checks in the TLB miss path. Reported-by: heyongli@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-26 07:47:46 +08:00
/* Clear the PAGE_OFFSET top virtual bits, shift
* down to get PFN, and make sure PFN is in range.
*/
sparc64: Make PAGE_OFFSET variable. Choose PAGE_OFFSET dynamically based upon cpu type. Original UltraSPARC-I (spitfire) chips only supported a 44-bit virtual address space. Newer chips (T4 and later) support 52-bit virtual addresses and up to 47-bits of physical memory space. Therefore we have to adjust PAGE_SIZE dynamically based upon the capabilities of the chip. Note that this change alone does not allow us to support > 43-bit physical memory, to do that we need to re-arrange our page table support. The current encodings of the pmd_t and pgd_t pointers restricts us to "32 + 11" == 43 bits. This change can waste quite a bit of memory for the various tables. In particular, a future change should work to size and allocate kern_linear_bitmap[] and sparc64_valid_addr_bitmap[] dynamically. This isn't easy as we really cannot take a TLB miss when accessing kern_linear_bitmap[]. We'd have to lock it into the TLB or similar. Signed-off-by: David S. Miller <davem@davemloft.net> Acked-by: Bob Picco <bob.picco@oracle.com>
2013-09-21 12:50:41 +08:00
661: sllx %g4, 0, %g5
.section .page_offset_shift_patch, "ax"
.word 661b
.previous
[SPARC64]: Make use of Niagara 256MB PTEs for kernel mappings. We use a bitmap, one bit for every 256MB of memory. If the bit is set we can use a 256MB PTE for linear mappings, else we have to use a 4MB PTE. SUN4V support is there, and we can very easily add support for Panther cpu 256MB PTEs in the future. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-22 12:51:13 +08:00
sparc64: Validate linear D-TLB misses. When page alloc debugging is not enabled, we essentially accept any virtual address for linear kernel TLB misses. But with kgdb, kernel address probing, and other facilities we can try to access arbitrary crap. So, make sure the address we miss on will translate to physical memory that actually exists. In order to make this work we have to embed the valid address bitmap into the kernel image. And in order to make that less expensive we make an adjustment, in that the max physical memory address is decreased to "1 << 41", even on the chips that support a 42-bit physical address space. We can do this because bit 41 indicates "I/O space" and thus covers non-memory ranges. The result of this is that: 1) kpte_linear_bitmap shrinks from 2K to 1K in size 2) we need 64K more for the valid address bitmap We can't let the valid address bitmap be dynamically allocated once we start using it to validate TLB misses, otherwise we have crazy issues to deal with wrt. recursive TLB misses and such. If we're in a TLB miss it could be the deepest trap level that's legal inside of the cpu. So if we TLB miss referencing the bitmap, the cpu will be out of trap levels and enter RED state. To guard against out-of-range accesses to the bitmap, we have to check to make sure no bits in the physical address above bit 40 are set. We could export and use last_valid_pfn for this check, but that's just an unnecessary extra memory reference. On the plus side of all this, since we load all of these translations into the special 4MB mapping TSB, and we check the TSB first for TLB misses, there should be absolutely no real cost for these new checks in the TLB miss path. Reported-by: heyongli@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-26 07:47:46 +08:00
/* Check to see if we know about valid memory at the 4MB
* chunk this physical address will reside within.
[SPARC64]: Make use of Niagara 256MB PTEs for kernel mappings. We use a bitmap, one bit for every 256MB of memory. If the bit is set we can use a 256MB PTE for linear mappings, else we have to use a 4MB PTE. SUN4V support is there, and we can very easily add support for Panther cpu 256MB PTEs in the future. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-22 12:51:13 +08:00
*/
sparc64: Make PAGE_OFFSET variable. Choose PAGE_OFFSET dynamically based upon cpu type. Original UltraSPARC-I (spitfire) chips only supported a 44-bit virtual address space. Newer chips (T4 and later) support 52-bit virtual addresses and up to 47-bits of physical memory space. Therefore we have to adjust PAGE_SIZE dynamically based upon the capabilities of the chip. Note that this change alone does not allow us to support > 43-bit physical memory, to do that we need to re-arrange our page table support. The current encodings of the pmd_t and pgd_t pointers restricts us to "32 + 11" == 43 bits. This change can waste quite a bit of memory for the various tables. In particular, a future change should work to size and allocate kern_linear_bitmap[] and sparc64_valid_addr_bitmap[] dynamically. This isn't easy as we really cannot take a TLB miss when accessing kern_linear_bitmap[]. We'd have to lock it into the TLB or similar. Signed-off-by: David S. Miller <davem@davemloft.net> Acked-by: Bob Picco <bob.picco@oracle.com>
2013-09-21 12:50:41 +08:00
661: srlx %g5, MAX_PHYS_ADDRESS_BITS, %g2
.section .page_offset_shift_patch, "ax"
.word 661b
.previous
sparc64: Validate linear D-TLB misses. When page alloc debugging is not enabled, we essentially accept any virtual address for linear kernel TLB misses. But with kgdb, kernel address probing, and other facilities we can try to access arbitrary crap. So, make sure the address we miss on will translate to physical memory that actually exists. In order to make this work we have to embed the valid address bitmap into the kernel image. And in order to make that less expensive we make an adjustment, in that the max physical memory address is decreased to "1 << 41", even on the chips that support a 42-bit physical address space. We can do this because bit 41 indicates "I/O space" and thus covers non-memory ranges. The result of this is that: 1) kpte_linear_bitmap shrinks from 2K to 1K in size 2) we need 64K more for the valid address bitmap We can't let the valid address bitmap be dynamically allocated once we start using it to validate TLB misses, otherwise we have crazy issues to deal with wrt. recursive TLB misses and such. If we're in a TLB miss it could be the deepest trap level that's legal inside of the cpu. So if we TLB miss referencing the bitmap, the cpu will be out of trap levels and enter RED state. To guard against out-of-range accesses to the bitmap, we have to check to make sure no bits in the physical address above bit 40 are set. We could export and use last_valid_pfn for this check, but that's just an unnecessary extra memory reference. On the plus side of all this, since we load all of these translations into the special 4MB mapping TSB, and we check the TSB first for TLB misses, there should be absolutely no real cost for these new checks in the TLB miss path. Reported-by: heyongli@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-26 07:47:46 +08:00
brnz,pn %g2, kvmap_dtlb_longpath
nop
/* This unconditional branch and delay-slot nop gets patched
* by the sethi sequence once the bitmap is properly setup.
*/
.globl valid_addr_bitmap_insn
valid_addr_bitmap_insn:
ba,pt %xcc, 2f
nop
.subsection 2
.globl valid_addr_bitmap_patch
valid_addr_bitmap_patch:
sethi %hi(sparc64_valid_addr_bitmap), %g7
or %g7, %lo(sparc64_valid_addr_bitmap), %g7
.previous
sparc64: Make PAGE_OFFSET variable. Choose PAGE_OFFSET dynamically based upon cpu type. Original UltraSPARC-I (spitfire) chips only supported a 44-bit virtual address space. Newer chips (T4 and later) support 52-bit virtual addresses and up to 47-bits of physical memory space. Therefore we have to adjust PAGE_SIZE dynamically based upon the capabilities of the chip. Note that this change alone does not allow us to support > 43-bit physical memory, to do that we need to re-arrange our page table support. The current encodings of the pmd_t and pgd_t pointers restricts us to "32 + 11" == 43 bits. This change can waste quite a bit of memory for the various tables. In particular, a future change should work to size and allocate kern_linear_bitmap[] and sparc64_valid_addr_bitmap[] dynamically. This isn't easy as we really cannot take a TLB miss when accessing kern_linear_bitmap[]. We'd have to lock it into the TLB or similar. Signed-off-by: David S. Miller <davem@davemloft.net> Acked-by: Bob Picco <bob.picco@oracle.com>
2013-09-21 12:50:41 +08:00
661: srlx %g5, ILOG2_4MB, %g2
.section .page_offset_shift_patch, "ax"
.word 661b
.previous
sparc64: Validate linear D-TLB misses. When page alloc debugging is not enabled, we essentially accept any virtual address for linear kernel TLB misses. But with kgdb, kernel address probing, and other facilities we can try to access arbitrary crap. So, make sure the address we miss on will translate to physical memory that actually exists. In order to make this work we have to embed the valid address bitmap into the kernel image. And in order to make that less expensive we make an adjustment, in that the max physical memory address is decreased to "1 << 41", even on the chips that support a 42-bit physical address space. We can do this because bit 41 indicates "I/O space" and thus covers non-memory ranges. The result of this is that: 1) kpte_linear_bitmap shrinks from 2K to 1K in size 2) we need 64K more for the valid address bitmap We can't let the valid address bitmap be dynamically allocated once we start using it to validate TLB misses, otherwise we have crazy issues to deal with wrt. recursive TLB misses and such. If we're in a TLB miss it could be the deepest trap level that's legal inside of the cpu. So if we TLB miss referencing the bitmap, the cpu will be out of trap levels and enter RED state. To guard against out-of-range accesses to the bitmap, we have to check to make sure no bits in the physical address above bit 40 are set. We could export and use last_valid_pfn for this check, but that's just an unnecessary extra memory reference. On the plus side of all this, since we load all of these translations into the special 4MB mapping TSB, and we check the TSB first for TLB misses, there should be absolutely no real cost for these new checks in the TLB miss path. Reported-by: heyongli@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-26 07:47:46 +08:00
srlx %g2, 6, %g5
and %g2, 63, %g2
sllx %g5, 3, %g5
ldx [%g7 + %g5], %g5
mov 1, %g7
sllx %g7, %g2, %g7
andcc %g5, %g7, %g0
be,pn %xcc, kvmap_dtlb_longpath
2: sethi %hi(kpte_linear_bitmap), %g2
/* Get the 256MB physical address index. */
sparc64: Make PAGE_OFFSET variable. Choose PAGE_OFFSET dynamically based upon cpu type. Original UltraSPARC-I (spitfire) chips only supported a 44-bit virtual address space. Newer chips (T4 and later) support 52-bit virtual addresses and up to 47-bits of physical memory space. Therefore we have to adjust PAGE_SIZE dynamically based upon the capabilities of the chip. Note that this change alone does not allow us to support > 43-bit physical memory, to do that we need to re-arrange our page table support. The current encodings of the pmd_t and pgd_t pointers restricts us to "32 + 11" == 43 bits. This change can waste quite a bit of memory for the various tables. In particular, a future change should work to size and allocate kern_linear_bitmap[] and sparc64_valid_addr_bitmap[] dynamically. This isn't easy as we really cannot take a TLB miss when accessing kern_linear_bitmap[]. We'd have to lock it into the TLB or similar. Signed-off-by: David S. Miller <davem@davemloft.net> Acked-by: Bob Picco <bob.picco@oracle.com>
2013-09-21 12:50:41 +08:00
661: sllx %g4, 0, %g5
.section .page_offset_shift_patch, "ax"
.word 661b
.previous
sparc64: Support 2GB and 16GB page sizes for kernel linear mappings. SPARC-T4 supports 2GB pages. So convert kpte_linear_bitmap into an array of 2-bit values which index into kern_linear_pte_xor. Now kern_linear_pte_xor is used for 4 page size aligned regions, 4MB, 256MB, 2GB, and 16GB respectively. Enabling 2GB pages is currently hardcoded using a check against sun4v_chip_type. In the future this will be done more cleanly by interrogating the machine description which is the correct way to determine this kind of thing. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-07 09:13:58 +08:00
or %g2, %lo(kpte_linear_bitmap), %g2
sparc64: Make PAGE_OFFSET variable. Choose PAGE_OFFSET dynamically based upon cpu type. Original UltraSPARC-I (spitfire) chips only supported a 44-bit virtual address space. Newer chips (T4 and later) support 52-bit virtual addresses and up to 47-bits of physical memory space. Therefore we have to adjust PAGE_SIZE dynamically based upon the capabilities of the chip. Note that this change alone does not allow us to support > 43-bit physical memory, to do that we need to re-arrange our page table support. The current encodings of the pmd_t and pgd_t pointers restricts us to "32 + 11" == 43 bits. This change can waste quite a bit of memory for the various tables. In particular, a future change should work to size and allocate kern_linear_bitmap[] and sparc64_valid_addr_bitmap[] dynamically. This isn't easy as we really cannot take a TLB miss when accessing kern_linear_bitmap[]. We'd have to lock it into the TLB or similar. Signed-off-by: David S. Miller <davem@davemloft.net> Acked-by: Bob Picco <bob.picco@oracle.com>
2013-09-21 12:50:41 +08:00
661: srlx %g5, ILOG2_256MB, %g5
.section .page_offset_shift_patch, "ax"
.word 661b
.previous
sparc64: Support 2GB and 16GB page sizes for kernel linear mappings. SPARC-T4 supports 2GB pages. So convert kpte_linear_bitmap into an array of 2-bit values which index into kern_linear_pte_xor. Now kern_linear_pte_xor is used for 4 page size aligned regions, 4MB, 256MB, 2GB, and 16GB respectively. Enabling 2GB pages is currently hardcoded using a check against sun4v_chip_type. In the future this will be done more cleanly by interrogating the machine description which is the correct way to determine this kind of thing. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-07 09:13:58 +08:00
and %g5, (32 - 1), %g7
[SPARC64]: Make use of Niagara 256MB PTEs for kernel mappings. We use a bitmap, one bit for every 256MB of memory. If the bit is set we can use a 256MB PTE for linear mappings, else we have to use a 4MB PTE. SUN4V support is there, and we can very easily add support for Panther cpu 256MB PTEs in the future. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-22 12:51:13 +08:00
sparc64: Support 2GB and 16GB page sizes for kernel linear mappings. SPARC-T4 supports 2GB pages. So convert kpte_linear_bitmap into an array of 2-bit values which index into kern_linear_pte_xor. Now kern_linear_pte_xor is used for 4 page size aligned regions, 4MB, 256MB, 2GB, and 16GB respectively. Enabling 2GB pages is currently hardcoded using a check against sun4v_chip_type. In the future this will be done more cleanly by interrogating the machine description which is the correct way to determine this kind of thing. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-07 09:13:58 +08:00
/* Divide by 32 to get the offset into the bitmask. */
srlx %g5, 5, %g5
add %g7, %g7, %g7
[SPARC64]: Fix indexing into kpte_linear_bitmap. Need to shift back up by 3 bits to get 8-byte entry index. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-27 15:09:37 +08:00
sllx %g5, 3, %g5
[SPARC64]: Make use of Niagara 256MB PTEs for kernel mappings. We use a bitmap, one bit for every 256MB of memory. If the bit is set we can use a 256MB PTE for linear mappings, else we have to use a 4MB PTE. SUN4V support is there, and we can very easily add support for Panther cpu 256MB PTEs in the future. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-22 12:51:13 +08:00
sparc64: Support 2GB and 16GB page sizes for kernel linear mappings. SPARC-T4 supports 2GB pages. So convert kpte_linear_bitmap into an array of 2-bit values which index into kern_linear_pte_xor. Now kern_linear_pte_xor is used for 4 page size aligned regions, 4MB, 256MB, 2GB, and 16GB respectively. Enabling 2GB pages is currently hardcoded using a check against sun4v_chip_type. In the future this will be done more cleanly by interrogating the machine description which is the correct way to determine this kind of thing. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-07 09:13:58 +08:00
/* kern_linear_pte_xor[(mask >> shift) & 3)] */
[SPARC64]: Make use of Niagara 256MB PTEs for kernel mappings. We use a bitmap, one bit for every 256MB of memory. If the bit is set we can use a 256MB PTE for linear mappings, else we have to use a 4MB PTE. SUN4V support is there, and we can very easily add support for Panther cpu 256MB PTEs in the future. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-22 12:51:13 +08:00
ldx [%g2 + %g5], %g2
sparc64: Support 2GB and 16GB page sizes for kernel linear mappings. SPARC-T4 supports 2GB pages. So convert kpte_linear_bitmap into an array of 2-bit values which index into kern_linear_pte_xor. Now kern_linear_pte_xor is used for 4 page size aligned regions, 4MB, 256MB, 2GB, and 16GB respectively. Enabling 2GB pages is currently hardcoded using a check against sun4v_chip_type. In the future this will be done more cleanly by interrogating the machine description which is the correct way to determine this kind of thing. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-07 09:13:58 +08:00
srlx %g2, %g7, %g7
[SPARC64]: Make use of Niagara 256MB PTEs for kernel mappings. We use a bitmap, one bit for every 256MB of memory. If the bit is set we can use a 256MB PTE for linear mappings, else we have to use a 4MB PTE. SUN4V support is there, and we can very easily add support for Panther cpu 256MB PTEs in the future. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-22 12:51:13 +08:00
sethi %hi(kern_linear_pte_xor), %g5
sparc64: Support 2GB and 16GB page sizes for kernel linear mappings. SPARC-T4 supports 2GB pages. So convert kpte_linear_bitmap into an array of 2-bit values which index into kern_linear_pte_xor. Now kern_linear_pte_xor is used for 4 page size aligned regions, 4MB, 256MB, 2GB, and 16GB respectively. Enabling 2GB pages is currently hardcoded using a check against sun4v_chip_type. In the future this will be done more cleanly by interrogating the machine description which is the correct way to determine this kind of thing. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-07 09:13:58 +08:00
and %g7, 3, %g7
[SPARC64]: Make use of Niagara 256MB PTEs for kernel mappings. We use a bitmap, one bit for every 256MB of memory. If the bit is set we can use a 256MB PTE for linear mappings, else we have to use a 4MB PTE. SUN4V support is there, and we can very easily add support for Panther cpu 256MB PTEs in the future. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-22 12:51:13 +08:00
or %g5, %lo(kern_linear_pte_xor), %g5
sparc64: Support 2GB and 16GB page sizes for kernel linear mappings. SPARC-T4 supports 2GB pages. So convert kpte_linear_bitmap into an array of 2-bit values which index into kern_linear_pte_xor. Now kern_linear_pte_xor is used for 4 page size aligned regions, 4MB, 256MB, 2GB, and 16GB respectively. Enabling 2GB pages is currently hardcoded using a check against sun4v_chip_type. In the future this will be done more cleanly by interrogating the machine description which is the correct way to determine this kind of thing. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-07 09:13:58 +08:00
sllx %g7, 3, %g7
ldx [%g5 + %g7], %g2
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
[SPARC64]: Add CONFIG_DEBUG_PAGEALLOC support. The trick is that we do the kernel linear mapping TLB miss starting with an instruction sequence like this: ba,pt %xcc, kvmap_load xor %g2, %g4, %g5 succeeded by an instruction sequence which performs a full page table walk starting at swapper_pg_dir. We first take over the trap table from the firmware. Then, using this constant PTE generation for the linear mapping area above, we build the kernel page tables for the linear mapping. After this is setup, we patch that branch above into a "nop", which will cause TLB misses to fall through to the full page table walk. With this, the page unmapping for CONFIG_DEBUG_PAGEALLOC is trivial. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-26 07:46:57 +08:00
.globl kvmap_linear_patch
kvmap_linear_patch:
[SPARC64]: Create a seperate kernel TSB for 4MB/256MB mappings. It can map all of the linear kernel mappings with zero TSB hash conflicts for systems with 16GB or less ram. In such cases, on SUN4V, once we load up this TSB the first time with all the mappings, we never take a linear kernel mapping TLB miss ever again, the hypervisor handles them all. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-22 14:31:11 +08:00
ba,pt %xcc, kvmap_dtlb_tsb4m_load
[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
xor %g2, %g4, %g5
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
kvmap_dtlb_vmalloc_addr:
KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath)
sparc: Access kernel TSB using physical addressing when possible. On sun4v this is basically required since we point the hypervisor and the TSB walking hardware at these tables using physical addressing too. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-08-05 15:53:57 +08:00
TSB_LOCK_TAG(%g1, %g2, %g7)
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
/* Load and check PTE. */
ldxa [%g5] ASI_PHYS_USE_EC, %g5
[SPARC64]: More TLB/TSB handling fixes. The SUN4V convention with non-shared TSBs is that the context bit of the TAG is clear. So we have to choose an "invalid" bit and initialize new TSBs appropriately. Otherwise a zero TAG looks "valid". Make sure, for the window fixup cases, that we use the right global registers and that we don't potentially trample on the live global registers in etrap/rtrap handling (%g2 and %g6) and that we put the missing virtual address properly in %g5. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-18 10:01:02 +08:00
mov 1, %g7
sllx %g7, TSB_TAG_INVALID_BIT, %g7
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
brgez,a,pn %g5, kvmap_dtlb_longpath
sparc: Access kernel TSB using physical addressing when possible. On sun4v this is basically required since we point the hypervisor and the TSB walking hardware at these tables using physical addressing too. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-08-05 15:53:57 +08:00
TSB_STORE(%g1, %g7)
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
sparc: Access kernel TSB using physical addressing when possible. On sun4v this is basically required since we point the hypervisor and the TSB walking hardware at these tables using physical addressing too. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-08-05 15:53:57 +08:00
TSB_WRITE(%g1, %g5, %g6)
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
/* fallthrough to TLB load */
kvmap_dtlb_load:
[SPARC64]: Fix some SUN4V TLB miss bugs. Code patching did not sign extend negative branch offsets correctly. Kernel TLB miss path needs patching and %g4 register preservation in order to handle SUN4V correctly. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-12 04:21:20 +08:00
661: stxa %g5, [%g0] ASI_DTLB_DATA_IN ! Reload TLB
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
retry
[SPARC64]: Fix some SUN4V TLB miss bugs. Code patching did not sign extend negative branch offsets correctly. Kernel TLB miss path needs patching and %g4 register preservation in order to handle SUN4V correctly. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-12 04:21:20 +08:00
.section .sun4v_2insn_patch, "ax"
.word 661b
nop
nop
.previous
/* For sun4v the ASI_DTLB_DATA_IN store and the retry
* instruction get nop'd out and we get here to branch
* to the sun4v tlb load code. The registers are setup
* as follows:
*
* %g4: vaddr
* %g5: PTE
* %g6: TAG
*
* The sun4v TLB load wants the PTE in %g3 so we fix that
* up here.
*/
ba,pt %xcc, sun4v_dtlb_load
mov %g5, %g3
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
[SPARC64]: Fix build with SPARSEMEM_VMEMMAP disabled. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-11 13:10:54 +08:00
#ifdef CONFIG_SPARSEMEM_VMEMMAP
SPARC64: SPARSEMEM_VMEMMAP support [apw@shadowen.org: style fixups] [apw@shadowen.org: vmemmap sparc64: convert to new config options] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Christoph Lameter <clameter@sgi.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:24:16 +08:00
kvmap_vmemmap:
sub %g4, %g5, %g5
srlx %g5, 22, %g5
sethi %hi(vmemmap_table), %g1
sllx %g5, 3, %g5
or %g1, %lo(vmemmap_table), %g1
ba,pt %xcc, kvmap_dtlb_load
ldx [%g1 + %g5], %g5
[SPARC64]: Fix build with SPARSEMEM_VMEMMAP disabled. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-11 13:10:54 +08:00
#endif
SPARC64: SPARSEMEM_VMEMMAP support [apw@shadowen.org: style fixups] [apw@shadowen.org: vmemmap sparc64: convert to new config options] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Christoph Lameter <clameter@sgi.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:24:16 +08:00
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
kvmap_dtlb_nonlinear:
/* Catch kernel NULL pointer derefs. */
sethi %hi(PAGE_SIZE), %g5
cmp %g4, %g5
bleu,pn %xcc, kvmap_dtlb_longpath
[SPARC64]: Add CONFIG_DEBUG_PAGEALLOC support. The trick is that we do the kernel linear mapping TLB miss starting with an instruction sequence like this: ba,pt %xcc, kvmap_load xor %g2, %g4, %g5 succeeded by an instruction sequence which performs a full page table walk starting at swapper_pg_dir. We first take over the trap table from the firmware. Then, using this constant PTE generation for the linear mapping area above, we build the kernel page tables for the linear mapping. After this is setup, we patch that branch above into a "nop", which will cause TLB misses to fall through to the full page table walk. With this, the page unmapping for CONFIG_DEBUG_PAGEALLOC is trivial. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-26 07:46:57 +08:00
nop
[SPARC64]: Fix build with SPARSEMEM_VMEMMAP disabled. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-11 13:10:54 +08:00
#ifdef CONFIG_SPARSEMEM_VMEMMAP
SPARC64: SPARSEMEM_VMEMMAP support [apw@shadowen.org: style fixups] [apw@shadowen.org: vmemmap sparc64: convert to new config options] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Christoph Lameter <clameter@sgi.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:24:16 +08:00
/* Do not use the TSB for vmemmap. */
sparc64: Increase vmalloc size to fix percpu regressions. Since we now use the embedding percpu allocator we have to make the vmalloc area at least as large as the stretch can be between nodes. Besides some minor asm adjustments, this turned out to be pretty trivial. Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-29 05:39:58 +08:00
mov (VMEMMAP_BASE >> 40), %g5
sllx %g5, 40, %g5
SPARC64: SPARSEMEM_VMEMMAP support [apw@shadowen.org: style fixups] [apw@shadowen.org: vmemmap sparc64: convert to new config options] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Christoph Lameter <clameter@sgi.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:24:16 +08:00
cmp %g4,%g5
bgeu,pn %xcc, kvmap_vmemmap
nop
[SPARC64]: Fix build with SPARSEMEM_VMEMMAP disabled. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-11 13:10:54 +08:00
#endif
SPARC64: SPARSEMEM_VMEMMAP support [apw@shadowen.org: style fixups] [apw@shadowen.org: vmemmap sparc64: convert to new config options] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Christoph Lameter <clameter@sgi.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:24:16 +08:00
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
KERN_TSB_LOOKUP_TL1(%g4, %g6, %g5, %g1, %g2, %g3, kvmap_dtlb_load)
kvmap_dtlb_tsbmiss:
[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
sethi %hi(MODULES_VADDR), %g5
cmp %g4, %g5
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
blu,pn %xcc, kvmap_dtlb_longpath
sparc64: Increase vmalloc size to fix percpu regressions. Since we now use the embedding percpu allocator we have to make the vmalloc area at least as large as the stretch can be between nodes. Besides some minor asm adjustments, this turned out to be pretty trivial. Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-29 05:39:58 +08:00
mov (VMALLOC_END >> 40), %g5
sllx %g5, 40, %g5
[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
cmp %g4, %g5
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
bgeu,pn %xcc, kvmap_dtlb_longpath
[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
nop
kvmap_check_obp:
sethi %hi(LOW_OBP_ADDRESS), %g5
cmp %g4, %g5
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
blu,pn %xcc, kvmap_dtlb_vmalloc_addr
[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
mov 0x1, %g5
sllx %g5, 32, %g5
cmp %g4, %g5
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
blu,pn %xcc, kvmap_dtlb_obp
[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
nop
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
ba,pt %xcc, kvmap_dtlb_vmalloc_addr
[SPARC64]: Move kernel TLB miss handling into a seperate file. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-22 09:50:51 +08:00
nop
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
kvmap_dtlb_longpath:
[SPARC64]: Sanitize %pstate writes for sun4v. If we're just switching between different alternate global sets, nop it out on sun4v. Also, get rid of all of the alternate global save/restore in the OBP CIF trampoline code. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-06 14:27:28 +08:00
661: rdpr %pstate, %g5
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
wrpr %g5, PSTATE_AG | PSTATE_MG, %pstate
[SPARC64]: Rename gl_{1,2}insn_patch --> sun4v_{1,2}insn_patch Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-07 16:00:16 +08:00
.section .sun4v_2insn_patch, "ax"
[SPARC64]: Sanitize %pstate writes for sun4v. If we're just switching between different alternate global sets, nop it out on sun4v. Also, get rid of all of the alternate global save/restore in the OBP CIF trampoline code. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-06 14:27:28 +08:00
.word 661b
[SPARC64]: More TLB/TSB handling fixes. The SUN4V convention with non-shared TSBs is that the context bit of the TAG is clear. So we have to choose an "invalid" bit and initialize new TSBs appropriately. Otherwise a zero TAG looks "valid". Make sure, for the window fixup cases, that we use the right global registers and that we don't potentially trample on the live global registers in etrap/rtrap handling (%g2 and %g6) and that we put the missing virtual address properly in %g5. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-18 10:01:02 +08:00
SET_GL(1)
ldxa [%g0] ASI_SCRATCHPAD, %g5
[SPARC64]: Sanitize %pstate writes for sun4v. If we're just switching between different alternate global sets, nop it out on sun4v. Also, get rid of all of the alternate global save/restore in the OBP CIF trampoline code. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-06 14:27:28 +08:00
.previous
[SPARC64]: Fix some SUN4V TLB miss bugs. Code patching did not sign extend negative branch offsets correctly. Kernel TLB miss path needs patching and %g4 register preservation in order to handle SUN4V correctly. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-12 04:21:20 +08:00
rdpr %tl, %g3
cmp %g3, 1
661: mov TLB_TAG_ACCESS, %g4
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
ldxa [%g4] ASI_DMMU, %g5
[SPARC64]: Fix some SUN4V TLB miss bugs. Code patching did not sign extend negative branch offsets correctly. Kernel TLB miss path needs patching and %g4 register preservation in order to handle SUN4V correctly. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-12 04:21:20 +08:00
.section .sun4v_2insn_patch, "ax"
.word 661b
[SPARC64]: More TLB/TSB handling fixes. The SUN4V convention with non-shared TSBs is that the context bit of the TAG is clear. So we have to choose an "invalid" bit and initialize new TSBs appropriately. Otherwise a zero TAG looks "valid". Make sure, for the window fixup cases, that we use the right global registers and that we don't potentially trample on the live global registers in etrap/rtrap handling (%g2 and %g6) and that we put the missing virtual address properly in %g5. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-18 10:01:02 +08:00
ldx [%g5 + HV_FAULT_D_ADDR_OFFSET], %g5
[SPARC64]: Fix some SUN4V TLB miss bugs. Code patching did not sign extend negative branch offsets correctly. Kernel TLB miss path needs patching and %g4 register preservation in order to handle SUN4V correctly. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-12 04:21:20 +08:00
nop
.previous
[SPARC64]: Move away from virtual page tables, part 1. We now use the TSB hardware assist features of the UltraSPARC MMUs. SMP is currently knowingly broken, we need to find another place to store the per-cpu base pointers. We hid them away in the TSB base register, and that obviously will not work any more :-) Another known broken case is non-8KB base page size. Also noticed that flush_tlb_all() is not referenced anywhere, only the internal __flush_tlb_all() (local cpu only) is used by the sparc64 port, so we can get rid of flush_tlb_all(). The kernel gets it's own 8KB TSB (swapper_tsb) and each address space gets it's own private 8K TSB. Later we can add code to dynamically increase the size of per-process TSB as the RSS grows. An 8KB TSB is good enough for up to about a 4MB RSS, after which the TSB starts to incur many capacity and conflict misses. We even accumulate OBP translations into the kernel TSB. Another area for refinement is large page size support. We could use a secondary address space TSB to handle those. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-01 10:29:18 +08:00
be,pt %xcc, sparc64_realfault_common
mov FAULT_CODE_DTLB, %g4
ba,pt %xcc, winfix_trampoline
nop