AcoSail/kernel_optimize_test
8
0
Fork 0
forked from luck/tmp_suning_uos_patched
Code Pull Requests Activity
5680d48be8
kernel_optimize_test/arch/sparc64/kernel/ttable.S

266 lines
11 KiB
ArmAsm
Raw Normal View History

[SPARC64]: Implement sun4v TSB miss handlers. When we register a TSB with the hypervisor, so that it or hardware can handle TLB misses and do the TSB walk for us, the hypervisor traps down to these trap when it incurs a TSB miss. Processing is simple, we load the missing virtual address and context, and do a full page table walk. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-10 08:12:22 +08:00
/* ttable.S: Sparc V9 Trap Table(s) with SpitFire/Cheetah/SUN4V extensions.
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
*
[SPARC64]: Implement sun4v TSB miss handlers. When we register a TSB with the hypervisor, so that it or hardware can handle TLB misses and do the TSB walk for us, the hypervisor traps down to these trap when it incurs a TSB miss. Processing is simple, we load the missing virtual address and context, and do a full page table walk. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-10 08:12:22 +08:00
* Copyright (C) 1996, 2001, 2006 David S. Miller (davem@davemloft.net)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
*/
.globl sparc64_ttable_tl0, sparc64_ttable_tl1
.globl tl0_icpe, tl1_icpe
.globl tl0_dcpe, tl1_dcpe
.globl tl0_fecc, tl1_fecc
.globl tl0_cee, tl1_cee
.globl tl0_iae, tl1_iae
.globl tl0_dae, tl1_dae
sparc64_ttable_tl0:
tl0_resv000: BOOT_KERNEL BTRAP(0x1) BTRAP(0x2) BTRAP(0x3)
tl0_resv004: BTRAP(0x4) BTRAP(0x5) BTRAP(0x6) BTRAP(0x7)
tl0_iax: membar #Sync
[SPARC64]: Revamp Spitfire error trap handling. Current uncorrectable error handling was poor enough that the processor could just loop taking the same trap over and over again. Fix things up so that we at least get a log message and perhaps even some register state. In the process, much consolidation became possible, particularly with the correctable error handler. Prefix assembler and C function names with "spitfire" to indicate that these are for Ultra-I/II/IIi/IIe only. More work is needed to make these routines robust and featureful to the level of the Ultra-III error handlers. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-30 03:45:11 +08:00
TRAP_NOSAVE_7INSNS(__spitfire_insn_access_exception)
[SPARC64]: Put SUN4V ITSB miss into correct trap table entry. It's 0x9 not 0xb. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-18 02:28:24 +08:00
tl0_itsb_4v: SUN4V_ITSB_MISS
[SPARC64]: Revamp Spitfire error trap handling. Current uncorrectable error handling was poor enough that the processor could just loop taking the same trap over and over again. Fix things up so that we at least get a log message and perhaps even some register state. In the process, much consolidation became possible, particularly with the correctable error handler. Prefix assembler and C function names with "spitfire" to indicate that these are for Ultra-I/II/IIi/IIe only. More work is needed to make these routines robust and featureful to the level of the Ultra-III error handlers. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-30 03:45:11 +08:00
tl0_iae: membar #Sync
TRAP_NOSAVE_7INSNS(__spitfire_access_error)
[SPARC64]: Put SUN4V ITSB miss into correct trap table entry. It's 0x9 not 0xb. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-18 02:28:24 +08:00
tl0_resv00b: BTRAP(0xb) BTRAP(0xc) BTRAP(0xd) BTRAP(0xe) BTRAP(0xf)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tl0_ill: membar #Sync
TRAP_7INSNS(do_illegal_instruction)
tl0_privop: TRAP(do_privop)
tl0_resv012: BTRAP(0x12) BTRAP(0x13) BTRAP(0x14) BTRAP(0x15) BTRAP(0x16) BTRAP(0x17)
tl0_resv018: BTRAP(0x18) BTRAP(0x19) BTRAP(0x1a) BTRAP(0x1b) BTRAP(0x1c) BTRAP(0x1d)
tl0_resv01e: BTRAP(0x1e) BTRAP(0x1f)
tl0_fpdis: TRAP_NOSAVE(do_fpdis)
tl0_fpieee: TRAP_SAVEFPU(do_fpieee)
tl0_fpother: TRAP_NOSAVE(do_fpother_check_fitos)
tl0_tof: TRAP(do_tof)
tl0_cwin: CLEAN_WINDOW
tl0_div0: TRAP(do_div0)
tl0_resv029: BTRAP(0x29) BTRAP(0x2a) BTRAP(0x2b) BTRAP(0x2c) BTRAP(0x2d) BTRAP(0x2e)
tl0_resv02f: BTRAP(0x2f)
[SPARC64]: Revamp Spitfire error trap handling. Current uncorrectable error handling was poor enough that the processor could just loop taking the same trap over and over again. Fix things up so that we at least get a log message and perhaps even some register state. In the process, much consolidation became possible, particularly with the correctable error handler. Prefix assembler and C function names with "spitfire" to indicate that these are for Ultra-I/II/IIi/IIe only. More work is needed to make these routines robust and featureful to the level of the Ultra-III error handlers. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-30 03:45:11 +08:00
tl0_dax: TRAP_NOSAVE(__spitfire_data_access_exception)
[SPARC64]: Implement sun4v TSB miss handlers. When we register a TSB with the hypervisor, so that it or hardware can handle TLB misses and do the TSB walk for us, the hypervisor traps down to these trap when it incurs a TSB miss. Processing is simple, we load the missing virtual address and context, and do a full page table walk. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-10 08:12:22 +08:00
tl0_dtsb_4v: SUN4V_DTSB_MISS
[SPARC64]: Revamp Spitfire error trap handling. Current uncorrectable error handling was poor enough that the processor could just loop taking the same trap over and over again. Fix things up so that we at least get a log message and perhaps even some register state. In the process, much consolidation became possible, particularly with the correctable error handler. Prefix assembler and C function names with "spitfire" to indicate that these are for Ultra-I/II/IIi/IIe only. More work is needed to make these routines robust and featureful to the level of the Ultra-III error handlers. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-30 03:45:11 +08:00
tl0_dae: membar #Sync
TRAP_NOSAVE_7INSNS(__spitfire_access_error)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tl0_resv033: BTRAP(0x33)
tl0_mna: TRAP_NOSAVE(do_mna)
tl0_lddfmna: TRAP_NOSAVE(do_lddfmna)
tl0_stdfmna: TRAP_NOSAVE(do_stdfmna)
tl0_privact: TRAP_NOSAVE(__do_privact)
tl0_resv038: BTRAP(0x38) BTRAP(0x39) BTRAP(0x3a) BTRAP(0x3b) BTRAP(0x3c) BTRAP(0x3d)
tl0_resv03e: BTRAP(0x3e) BTRAP(0x3f) BTRAP(0x40)
#ifdef CONFIG_SMP
tl0_irq1: TRAP_IRQ(smp_call_function_client, 1)
tl0_irq2: TRAP_IRQ(smp_receive_signal_client, 2)
tl0_irq3: TRAP_IRQ(smp_penguin_jailcell, 3)
[SPARC64]: Fix new context version SMP handling. Don't piggy back the SMP receive signal code to do the context version change handling. Instead allocate another fixed PIL number for this asynchronous cross-call. We can't use smp_call_function() because this thing is invoked with interrupts disabled and a few spinlocks held. Also, fix smp_call_function_mask() to count "cpus" correctly. There is no guarentee that the local cpu is in the mask yet that is exactly what this code was assuming. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-07 14:50:44 +08:00
tl0_irq4: TRAP_IRQ(smp_new_mmu_context_version_client, 4)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
#else
tl0_irq1: BTRAP(0x41)
tl0_irq2: BTRAP(0x42)
tl0_irq3: BTRAP(0x43)
[SPARC64]: Fix new context version SMP handling. Don't piggy back the SMP receive signal code to do the context version change handling. Instead allocate another fixed PIL number for this asynchronous cross-call. We can't use smp_call_function() because this thing is invoked with interrupts disabled and a few spinlocks held. Also, fix smp_call_function_mask() to count "cpus" correctly. There is no guarentee that the local cpu is in the mask yet that is exactly what this code was assuming. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-07 14:50:44 +08:00
tl0_irq4: BTRAP(0x44)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
#endif
[SPARC64]: Send all device interrupts via one PIL. This is the first in a series of cleanups that will hopefully allow a seamless attempt at using the generic IRQ handling infrastructure in the Linux kernel. Define PIL_DEVICE_IRQ and vector all device interrupts through there. Get rid of the ugly pil0_dummy_{bucket,desc}, instead vector the timer interrupt directly to a specific handler since the timer interrupt is the only event that will be signaled on PIL 14. The irq_worklist is now in the per-cpu trap_block[]. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-20 16:20:00 +08:00
tl0_irq5: TRAP_IRQ(handler_irq, 5)
tl0_irq6: BTRAP(0x46) BTRAP(0x47) BTRAP(0x48) BTRAP(0x49)
tl0_irq10: BTRAP(0x4a) BTRAP(0x4b) BTRAP(0x4c) BTRAP(0x4d)
[SPARC64]: Unify timer interrupt handler. Things were scattered all over the place, split between SMP and non-SMP. Unify it all so that dyntick support is easier to add. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-02-22 22:24:10 +08:00
tl0_irq14: TRAP_IRQ(timer_interrupt, 14)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tl0_irq15: TRAP_IRQ(handler_irq, 15)
tl0_resv050: BTRAP(0x50) BTRAP(0x51) BTRAP(0x52) BTRAP(0x53) BTRAP(0x54) BTRAP(0x55)
tl0_resv056: BTRAP(0x56) BTRAP(0x57) BTRAP(0x58) BTRAP(0x59) BTRAP(0x5a) BTRAP(0x5b)
tl0_resv05c: BTRAP(0x5c) BTRAP(0x5d) BTRAP(0x5e) BTRAP(0x5f)
tl0_ivec: TRAP_IVEC
tl0_paw: TRAP(do_paw)
tl0_vaw: TRAP(do_vaw)
[SPARC64]: Revamp Spitfire error trap handling. Current uncorrectable error handling was poor enough that the processor could just loop taking the same trap over and over again. Fix things up so that we at least get a log message and perhaps even some register state. In the process, much consolidation became possible, particularly with the correctable error handler. Prefix assembler and C function names with "spitfire" to indicate that these are for Ultra-I/II/IIi/IIe only. More work is needed to make these routines robust and featureful to the level of the Ultra-III error handlers. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-30 03:45:11 +08:00
tl0_cee: membar #Sync
TRAP_NOSAVE_7INSNS(__spitfire_cee_trap)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tl0_iamiss:
[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 "itlb_miss.S"
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tl0_damiss:
[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 "dtlb_miss.S"
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tl0_daprot:
#include "dtlb_prot.S"
tl0_fecc: BTRAP(0x70) /* Fast-ECC on Cheetah */
tl0_dcpe: BTRAP(0x71) /* D-cache Parity Error on Cheetah+ */
tl0_icpe: BTRAP(0x72) /* I-cache Parity Error on Cheetah+ */
tl0_resv073: BTRAP(0x73) BTRAP(0x74) BTRAP(0x75)
tl0_resv076: BTRAP(0x76) BTRAP(0x77) BTRAP(0x78) BTRAP(0x79) BTRAP(0x7a) BTRAP(0x7b)
[SPARC64]: Sun4v interrupt handling. Sun4v has 4 interrupt queues: cpu, device, resumable errors, and non-resumable errors. A set of head/tail offset pointers help maintain a work queue in physical memory. The entries are 64-bytes in size. Each queue is allocated then registered with the hypervisor as we bring cpus up. The two error queues each get a kernel side buffer that we use to quickly empty the main interrupt queue before we call up to C code to log the event and possibly take evasive action. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-08 18:53:50 +08:00
tl0_cpu_mondo: TRAP_NOSAVE(sun4v_cpu_mondo)
tl0_dev_mondo: TRAP_NOSAVE(sun4v_dev_mondo)
tl0_res_mondo: TRAP_NOSAVE(sun4v_res_mondo)
tl0_nres_mondo: TRAP_NOSAVE(sun4v_nonres_mondo)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tl0_s0n: SPILL_0_NORMAL
tl0_s1n: SPILL_1_NORMAL
tl0_s2n: SPILL_2_NORMAL
[SPARC64]: Refine register window trap handling. When saving and restoing trap state, do the window spill/fill handling inline so that we never trap deeper than 2 trap levels. This is important for chips like Niagara. The window fixup code is massively simplified, and many more improvements are now possible. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-04 16:10:01 +08:00
tl0_s3n: SPILL_0_NORMAL_ETRAP
tl0_s4n: SPILL_1_GENERIC_ETRAP
tl0_s5n: SPILL_1_GENERIC_ETRAP_FIXUP
tl0_s6n: SPILL_2_GENERIC_ETRAP
tl0_s7n: SPILL_2_GENERIC_ETRAP_FIXUP
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tl0_s0o: SPILL_0_OTHER
tl0_s1o: SPILL_1_OTHER
tl0_s2o: SPILL_2_OTHER
tl0_s3o: SPILL_3_OTHER
tl0_s4o: SPILL_4_OTHER
tl0_s5o: SPILL_5_OTHER
tl0_s6o: SPILL_6_OTHER
tl0_s7o: SPILL_7_OTHER
tl0_f0n: FILL_0_NORMAL
tl0_f1n: FILL_1_NORMAL
tl0_f2n: FILL_2_NORMAL
tl0_f3n: FILL_3_NORMAL
tl0_f4n: FILL_4_NORMAL
[SPARC64]: Refine register window trap handling. When saving and restoing trap state, do the window spill/fill handling inline so that we never trap deeper than 2 trap levels. This is important for chips like Niagara. The window fixup code is massively simplified, and many more improvements are now possible. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-04 16:10:01 +08:00
tl0_f5n: FILL_0_NORMAL_RTRAP
tl0_f6n: FILL_1_GENERIC_RTRAP
tl0_f7n: FILL_2_GENERIC_RTRAP
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tl0_f0o: FILL_0_OTHER
tl0_f1o: FILL_1_OTHER
tl0_f2o: FILL_2_OTHER
tl0_f3o: FILL_3_OTHER
tl0_f4o: FILL_4_OTHER
tl0_f5o: FILL_5_OTHER
tl0_f6o: FILL_6_OTHER
tl0_f7o: FILL_7_OTHER
tl0_sunos: SUNOS_SYSCALL_TRAP
tl0_bkpt: BREAKPOINT_TRAP
tl0_divz: TRAP(do_div0)
tl0_flushw: FLUSH_WINDOW_TRAP
tl0_resv104: BTRAP(0x104) BTRAP(0x105) BTRAP(0x106) BTRAP(0x107)
.globl tl0_solaris
tl0_solaris: SOLARIS_SYSCALL_TRAP
[SPARC64]: Elminate all usage of hard-coded trap globals. UltraSPARC has special sets of global registers which are switched to for certain trap types. There is one set for MMU related traps, one set of Interrupt Vector processing, and another set (called the Alternate globals) for all other trap types. For what seems like forever we've hard coded the values in some of these trap registers. Some examples include: 1) Interrupt Vector global %g6 holds current processors interrupt work struct where received interrupts are managed for IRQ handler dispatch. 2) MMU global %g7 holds the base of the page tables of the currently active address space. 3) Alternate global %g6 held the current_thread_info() value. Such hardcoding has resulted in some serious issues in many areas. There are some code sequences where having another register available would help clean up the implementation. Taking traps such as cross-calls from the OBP firmware requires some trick code sequences wherein we have to save away and restore all of the special sets of global registers when we enter/exit OBP. We were also using the IMMU TSB register on SMP to hold the per-cpu area base address, which doesn't work any longer now that we actually use the TSB facility of the cpu. The implementation is pretty straight forward. One tricky bit is getting the current processor ID as that is different on different cpu variants. We use a stub with a fancy calling convention which we patch at boot time. The calling convention is that the stub is branched to and the (PC - 4) to return to is in register %g1. The cpu number is left in %g6. This stub can be invoked by using the __GET_CPUID macro. We use an array of per-cpu trap state to store the current thread and physical address of the current address space's page tables. The TRAP_LOAD_THREAD_REG loads %g6 with the current thread from this table, it uses __GET_CPUID and also clobbers %g1. TRAP_LOAD_IRQ_WORK is used by the interrupt vector processing to load the current processor's IRQ software state into %g6. It also uses __GET_CPUID and clobbers %g1. Finally, TRAP_LOAD_PGD_PHYS loads the physical address base of the current address space's page tables into %g7, it clobbers %g1 and uses __GET_CPUID. Many refinements are possible, as well as some tuning, with this stuff in place. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-27 15:24:22 +08:00
tl0_resv109: BTRAP(0x109)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tl0_resv10a: BTRAP(0x10a) BTRAP(0x10b) BTRAP(0x10c) BTRAP(0x10d) BTRAP(0x10e)
tl0_resv10f: BTRAP(0x10f)
tl0_linux32: LINUX_32BIT_SYSCALL_TRAP
tl0_oldlinux64: LINUX_64BIT_SYSCALL_TRAP
tl0_resv112: TRAP_UTRAP(UT_TRAP_INSTRUCTION_18,0x112) TRAP_UTRAP(UT_TRAP_INSTRUCTION_19,0x113)
tl0_resv114: TRAP_UTRAP(UT_TRAP_INSTRUCTION_20,0x114) TRAP_UTRAP(UT_TRAP_INSTRUCTION_21,0x115)
tl0_resv116: TRAP_UTRAP(UT_TRAP_INSTRUCTION_22,0x116) TRAP_UTRAP(UT_TRAP_INSTRUCTION_23,0x117)
tl0_resv118: TRAP_UTRAP(UT_TRAP_INSTRUCTION_24,0x118) TRAP_UTRAP(UT_TRAP_INSTRUCTION_25,0x119)
tl0_resv11a: TRAP_UTRAP(UT_TRAP_INSTRUCTION_26,0x11a) TRAP_UTRAP(UT_TRAP_INSTRUCTION_27,0x11b)
tl0_resv11c: TRAP_UTRAP(UT_TRAP_INSTRUCTION_28,0x11c) TRAP_UTRAP(UT_TRAP_INSTRUCTION_29,0x11d)
tl0_resv11e: TRAP_UTRAP(UT_TRAP_INSTRUCTION_30,0x11e) TRAP_UTRAP(UT_TRAP_INSTRUCTION_31,0x11f)
tl0_getcc: GETCC_TRAP
tl0_setcc: SETCC_TRAP
tl0_getpsr: TRAP(do_getpsr)
tl0_resv123: BTRAP(0x123) BTRAP(0x124) BTRAP(0x125) BTRAP(0x126)
tl0_solindir: INDIRECT_SOLARIS_SYSCALL(156)
tl0_resv128: BTRAP(0x128) BTRAP(0x129) BTRAP(0x12a) BTRAP(0x12b) BTRAP(0x12c)
tl0_resv12d: BTRAP(0x12d) BTRAP(0x12e) BTRAP(0x12f) BTRAP(0x130) BTRAP(0x131)
tl0_resv132: BTRAP(0x132) BTRAP(0x133) BTRAP(0x134) BTRAP(0x135) BTRAP(0x136)
tl0_resv137: BTRAP(0x137) BTRAP(0x138) BTRAP(0x139) BTRAP(0x13a) BTRAP(0x13b)
tl0_resv13c: BTRAP(0x13c) BTRAP(0x13d) BTRAP(0x13e) BTRAP(0x13f) BTRAP(0x140)
tl0_resv141: BTRAP(0x141) BTRAP(0x142) BTRAP(0x143) BTRAP(0x144) BTRAP(0x145)
tl0_resv146: BTRAP(0x146) BTRAP(0x147) BTRAP(0x148) BTRAP(0x149) BTRAP(0x14a)
tl0_resv14b: BTRAP(0x14b) BTRAP(0x14c) BTRAP(0x14d) BTRAP(0x14e) BTRAP(0x14f)
tl0_resv150: BTRAP(0x150) BTRAP(0x151) BTRAP(0x152) BTRAP(0x153) BTRAP(0x154)
tl0_resv155: BTRAP(0x155) BTRAP(0x156) BTRAP(0x157) BTRAP(0x158) BTRAP(0x159)
tl0_resv15a: BTRAP(0x15a) BTRAP(0x15b) BTRAP(0x15c) BTRAP(0x15d) BTRAP(0x15e)
tl0_resv15f: BTRAP(0x15f) BTRAP(0x160) BTRAP(0x161) BTRAP(0x162) BTRAP(0x163)
tl0_resv164: BTRAP(0x164) BTRAP(0x165) BTRAP(0x166) BTRAP(0x167) BTRAP(0x168)
tl0_resv169: BTRAP(0x169) BTRAP(0x16a) BTRAP(0x16b) BTRAP(0x16c)
tl0_linux64: LINUX_64BIT_SYSCALL_TRAP
tl0_gsctx: TRAP(sparc64_get_context) TRAP(sparc64_set_context)
tl0_resv170: KPROBES_TRAP(0x170) KPROBES_TRAP(0x171) BTRAP(0x172)
tl0_resv173: BTRAP(0x173) BTRAP(0x174) BTRAP(0x175) BTRAP(0x176) BTRAP(0x177)
tl0_resv178: BTRAP(0x178) BTRAP(0x179) BTRAP(0x17a) BTRAP(0x17b) BTRAP(0x17c)
tl0_resv17d: BTRAP(0x17d) BTRAP(0x17e) BTRAP(0x17f)
#define BTRAPS(x) BTRAP(x) BTRAP(x+1) BTRAP(x+2) BTRAP(x+3) BTRAP(x+4) BTRAP(x+5) BTRAP(x+6) BTRAP(x+7)
tl0_resv180: BTRAPS(0x180) BTRAPS(0x188)
tl0_resv190: BTRAPS(0x190) BTRAPS(0x198)
tl0_resv1a0: BTRAPS(0x1a0) BTRAPS(0x1a8)
tl0_resv1b0: BTRAPS(0x1b0) BTRAPS(0x1b8)
tl0_resv1c0: BTRAPS(0x1c0) BTRAPS(0x1c8)
tl0_resv1d0: BTRAPS(0x1d0) BTRAPS(0x1d8)
tl0_resv1e0: BTRAPS(0x1e0) BTRAPS(0x1e8)
tl0_resv1f0: BTRAPS(0x1f0) BTRAPS(0x1f8)
sparc64_ttable_tl1:
tl1_resv000: BOOT_KERNEL BTRAPTL1(0x1) BTRAPTL1(0x2) BTRAPTL1(0x3)
tl1_resv004: BTRAPTL1(0x4) BTRAPTL1(0x5) BTRAPTL1(0x6) BTRAPTL1(0x7)
[SPARC64]: Revamp Spitfire error trap handling. Current uncorrectable error handling was poor enough that the processor could just loop taking the same trap over and over again. Fix things up so that we at least get a log message and perhaps even some register state. In the process, much consolidation became possible, particularly with the correctable error handler. Prefix assembler and C function names with "spitfire" to indicate that these are for Ultra-I/II/IIi/IIe only. More work is needed to make these routines robust and featureful to the level of the Ultra-III error handlers. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-30 03:45:11 +08:00
tl1_iax: TRAP_NOSAVE(__spitfire_insn_access_exception_tl1)
[SPARC64]: Put SUN4V ITSB miss into correct trap table entry. It's 0x9 not 0xb. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-18 02:28:24 +08:00
tl1_itsb_4v: SUN4V_ITSB_MISS
[SPARC64]: Revamp Spitfire error trap handling. Current uncorrectable error handling was poor enough that the processor could just loop taking the same trap over and over again. Fix things up so that we at least get a log message and perhaps even some register state. In the process, much consolidation became possible, particularly with the correctable error handler. Prefix assembler and C function names with "spitfire" to indicate that these are for Ultra-I/II/IIi/IIe only. More work is needed to make these routines robust and featureful to the level of the Ultra-III error handlers. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-30 03:45:11 +08:00
tl1_iae: membar #Sync
TRAP_NOSAVE_7INSNS(__spitfire_access_error)
[SPARC64]: Put SUN4V ITSB miss into correct trap table entry. It's 0x9 not 0xb. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-18 02:28:24 +08:00
tl1_resv00b: BTRAPTL1(0xb) BTRAPTL1(0xc) BTRAPTL1(0xd) BTRAPTL1(0xe) BTRAPTL1(0xf)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tl1_ill: TRAPTL1(do_ill_tl1)
tl1_privop: BTRAPTL1(0x11)
tl1_resv012: BTRAPTL1(0x12) BTRAPTL1(0x13) BTRAPTL1(0x14) BTRAPTL1(0x15)
tl1_resv016: BTRAPTL1(0x16) BTRAPTL1(0x17) BTRAPTL1(0x18) BTRAPTL1(0x19)
tl1_resv01a: BTRAPTL1(0x1a) BTRAPTL1(0x1b) BTRAPTL1(0x1c) BTRAPTL1(0x1d)
tl1_resv01e: BTRAPTL1(0x1e) BTRAPTL1(0x1f)
tl1_fpdis: TRAP_NOSAVE(do_fpdis)
tl1_fpieee: TRAPTL1(do_fpieee_tl1)
tl1_fpother: TRAPTL1(do_fpother_tl1)
tl1_tof: TRAPTL1(do_tof_tl1)
tl1_cwin: CLEAN_WINDOW
tl1_div0: TRAPTL1(do_div0_tl1)
tl1_resv029: BTRAPTL1(0x29) BTRAPTL1(0x2a) BTRAPTL1(0x2b) BTRAPTL1(0x2c)
tl1_resv02d: BTRAPTL1(0x2d) BTRAPTL1(0x2e) BTRAPTL1(0x2f)
[SPARC64]: Revamp Spitfire error trap handling. Current uncorrectable error handling was poor enough that the processor could just loop taking the same trap over and over again. Fix things up so that we at least get a log message and perhaps even some register state. In the process, much consolidation became possible, particularly with the correctable error handler. Prefix assembler and C function names with "spitfire" to indicate that these are for Ultra-I/II/IIi/IIe only. More work is needed to make these routines robust and featureful to the level of the Ultra-III error handlers. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-30 03:45:11 +08:00
tl1_dax: TRAP_NOSAVE(__spitfire_data_access_exception_tl1)
[SPARC64]: Implement sun4v TSB miss handlers. When we register a TSB with the hypervisor, so that it or hardware can handle TLB misses and do the TSB walk for us, the hypervisor traps down to these trap when it incurs a TSB miss. Processing is simple, we load the missing virtual address and context, and do a full page table walk. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-10 08:12:22 +08:00
tl1_dtsb_4v: SUN4V_DTSB_MISS
[SPARC64]: Revamp Spitfire error trap handling. Current uncorrectable error handling was poor enough that the processor could just loop taking the same trap over and over again. Fix things up so that we at least get a log message and perhaps even some register state. In the process, much consolidation became possible, particularly with the correctable error handler. Prefix assembler and C function names with "spitfire" to indicate that these are for Ultra-I/II/IIi/IIe only. More work is needed to make these routines robust and featureful to the level of the Ultra-III error handlers. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-30 03:45:11 +08:00
tl1_dae: membar #Sync
TRAP_NOSAVE_7INSNS(__spitfire_access_error)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tl1_resv033: BTRAPTL1(0x33)
tl1_mna: TRAP_NOSAVE(do_mna)
tl1_lddfmna: TRAPTL1(do_lddfmna_tl1)
tl1_stdfmna: TRAPTL1(do_stdfmna_tl1)
tl1_privact: BTRAPTL1(0x37)
tl1_resv038: BTRAPTL1(0x38) BTRAPTL1(0x39) BTRAPTL1(0x3a) BTRAPTL1(0x3b)
tl1_resv03c: BTRAPTL1(0x3c) BTRAPTL1(0x3d) BTRAPTL1(0x3e) BTRAPTL1(0x3f)
tl1_resv040: BTRAPTL1(0x40)
tl1_irq1: TRAP_IRQ(do_irq_tl1, 1) TRAP_IRQ(do_irq_tl1, 2) TRAP_IRQ(do_irq_tl1, 3)
tl1_irq4: TRAP_IRQ(do_irq_tl1, 4) TRAP_IRQ(do_irq_tl1, 5) TRAP_IRQ(do_irq_tl1, 6)
tl1_irq7: TRAP_IRQ(do_irq_tl1, 7) TRAP_IRQ(do_irq_tl1, 8) TRAP_IRQ(do_irq_tl1, 9)
tl1_irq10: TRAP_IRQ(do_irq_tl1, 10) TRAP_IRQ(do_irq_tl1, 11)
tl1_irq12: TRAP_IRQ(do_irq_tl1, 12) TRAP_IRQ(do_irq_tl1, 13)
tl1_irq14: TRAP_IRQ(do_irq_tl1, 14) TRAP_IRQ(do_irq_tl1, 15)
tl1_resv050: BTRAPTL1(0x50) BTRAPTL1(0x51) BTRAPTL1(0x52) BTRAPTL1(0x53)
tl1_resv054: BTRAPTL1(0x54) BTRAPTL1(0x55) BTRAPTL1(0x56) BTRAPTL1(0x57)
tl1_resv058: BTRAPTL1(0x58) BTRAPTL1(0x59) BTRAPTL1(0x5a) BTRAPTL1(0x5b)
tl1_resv05c: BTRAPTL1(0x5c) BTRAPTL1(0x5d) BTRAPTL1(0x5e) BTRAPTL1(0x5f)
tl1_ivec: TRAP_IVEC
tl1_paw: TRAPTL1(do_paw_tl1)
tl1_vaw: TRAPTL1(do_vaw_tl1)
[SPARC64]: Correctable ECC errors cannot occur at trap level > 0. The are distrupting, which by the sparc v9 definition means they can only occur when interrupts are enabled in the %pstate register. This never occurs in any of the trap handling code running at trap levels > 0. So just mark it as an unexpected trap. This allows us to kill off the cee_stuff member of struct thread_info. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-02 17:20:18 +08:00
tl1_cee: BTRAPTL1(0x63)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tl1_iamiss: BTRAPTL1(0x64) BTRAPTL1(0x65) BTRAPTL1(0x66) BTRAPTL1(0x67)
tl1_damiss:
[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 "dtlb_miss.S"
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tl1_daprot:
#include "dtlb_prot.S"
tl1_fecc: BTRAPTL1(0x70) /* Fast-ECC on Cheetah */
tl1_dcpe: BTRAPTL1(0x71) /* D-cache Parity Error on Cheetah+ */
tl1_icpe: BTRAPTL1(0x72) /* I-cache Parity Error on Cheetah+ */
tl1_resv073: BTRAPTL1(0x73)
tl1_resv074: BTRAPTL1(0x74) BTRAPTL1(0x75) BTRAPTL1(0x76) BTRAPTL1(0x77)
tl1_resv078: BTRAPTL1(0x78) BTRAPTL1(0x79) BTRAPTL1(0x7a) BTRAPTL1(0x7b)
tl1_resv07c: BTRAPTL1(0x7c) BTRAPTL1(0x7d) BTRAPTL1(0x7e) BTRAPTL1(0x7f)
tl1_s0n: SPILL_0_NORMAL
tl1_s1n: SPILL_1_NORMAL
tl1_s2n: SPILL_2_NORMAL
tl1_s3n: SPILL_3_NORMAL
tl1_s4n: SPILL_4_NORMAL
tl1_s5n: SPILL_5_NORMAL
tl1_s6n: SPILL_6_NORMAL
tl1_s7n: SPILL_7_NORMAL
tl1_s0o: SPILL_0_OTHER
tl1_s1o: SPILL_1_OTHER
tl1_s2o: SPILL_2_OTHER
tl1_s3o: SPILL_3_OTHER
tl1_s4o: SPILL_4_OTHER
tl1_s5o: SPILL_5_OTHER
tl1_s6o: SPILL_6_OTHER
tl1_s7o: SPILL_7_OTHER
tl1_f0n: FILL_0_NORMAL
tl1_f1n: FILL_1_NORMAL
tl1_f2n: FILL_2_NORMAL
tl1_f3n: FILL_3_NORMAL
tl1_f4n: FILL_4_NORMAL
tl1_f5n: FILL_5_NORMAL
tl1_f6n: FILL_6_NORMAL
tl1_f7n: FILL_7_NORMAL
tl1_f0o: FILL_0_OTHER
tl1_f1o: FILL_1_OTHER
tl1_f2o: FILL_2_OTHER
tl1_f3o: FILL_3_OTHER
tl1_f4o: FILL_4_OTHER
tl1_f5o: FILL_5_OTHER
tl1_f6o: FILL_6_OTHER
tl1_f7o: FILL_7_OTHER
Copy Permalink