ASR_BASE
Change-Id: Icf3719cc0afe3eeb3edc7fa80a2eb5199ca9dda1
diff --git a/marvell/linux/arch/hexagon/kernel/vm_entry.S b/marvell/linux/arch/hexagon/kernel/vm_entry.S
new file mode 100644
index 0000000..4023fdb
--- /dev/null
+++ b/marvell/linux/arch/hexagon/kernel/vm_entry.S
@@ -0,0 +1,380 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Event entry/exit for Hexagon
+ *
+ * Copyright (c) 2010-2013, The Linux Foundation. All rights reserved.
+ */
+
+#include <asm/asm-offsets.h> /* assembly-safer versions of C defines */
+#include <asm/mem-layout.h> /* sigh, except for page_offset */
+#include <asm/hexagon_vm.h>
+#include <asm/thread_info.h>
+
+/*
+ * Entry into guest-mode Linux under Hexagon Virtual Machine.
+ * Stack pointer points to event record - build pt_regs on top of it,
+ * set up a plausible C stack frame, and dispatch to the C handler.
+ * On return, do vmrte virtual instruction with SP where we started.
+ *
+ * VM Spec 0.5 uses a trap to fetch HVM record now.
+ */
+
+/*
+ * Save full register state, while setting up thread_info struct
+ * pointer derived from kernel stack pointer in THREADINFO_REG
+ * register, putting prior thread_info.regs pointer in a callee-save
+ * register (R24, which had better not ever be assigned to THREADINFO_REG),
+ * and updating thread_info.regs to point to current stack frame,
+ * so as to support nested events in kernel mode.
+ *
+ * As this is common code, we set the pt_regs system call number
+ * to -1 for all events. It will be replaced with the system call
+ * number in the case where we decode a system call (trap0(#1)).
+ */
+
+#if CONFIG_HEXAGON_ARCH_VERSION < 4
+#define save_pt_regs()\
+ memd(R0 + #_PT_R3130) = R31:30; \
+ { memw(R0 + #_PT_R2928) = R28; \
+ R31 = memw(R0 + #_PT_ER_VMPSP); }\
+ { memw(R0 + #(_PT_R2928 + 4)) = R31; \
+ R31 = ugp; } \
+ { memd(R0 + #_PT_R2726) = R27:26; \
+ R30 = gp ; } \
+ memd(R0 + #_PT_R2524) = R25:24; \
+ memd(R0 + #_PT_R2322) = R23:22; \
+ memd(R0 + #_PT_R2120) = R21:20; \
+ memd(R0 + #_PT_R1918) = R19:18; \
+ memd(R0 + #_PT_R1716) = R17:16; \
+ memd(R0 + #_PT_R1514) = R15:14; \
+ memd(R0 + #_PT_R1312) = R13:12; \
+ { memd(R0 + #_PT_R1110) = R11:10; \
+ R15 = lc0; } \
+ { memd(R0 + #_PT_R0908) = R9:8; \
+ R14 = sa0; } \
+ { memd(R0 + #_PT_R0706) = R7:6; \
+ R13 = lc1; } \
+ { memd(R0 + #_PT_R0504) = R5:4; \
+ R12 = sa1; } \
+ { memd(R0 + #_PT_GPUGP) = R31:30; \
+ R11 = m1; \
+ R2.H = #HI(_THREAD_SIZE); } \
+ { memd(R0 + #_PT_LC0SA0) = R15:14; \
+ R10 = m0; \
+ R2.L = #LO(_THREAD_SIZE); } \
+ { memd(R0 + #_PT_LC1SA1) = R13:12; \
+ R15 = p3:0; \
+ R2 = neg(R2); } \
+ { memd(R0 + #_PT_M1M0) = R11:10; \
+ R14 = usr; \
+ R2 = and(R0,R2); } \
+ { memd(R0 + #_PT_PREDSUSR) = R15:14; \
+ THREADINFO_REG = R2; } \
+ { r24 = memw(THREADINFO_REG + #_THREAD_INFO_PT_REGS); \
+ memw(THREADINFO_REG + #_THREAD_INFO_PT_REGS) = R0; \
+ R2 = #-1; } \
+ { memw(R0 + #_PT_SYSCALL_NR) = R2; \
+ R30 = #0; }
+#else
+/* V4+ */
+/* the # ## # syntax inserts a literal ## */
+#define save_pt_regs()\
+ { memd(R0 + #_PT_R3130) = R31:30; \
+ R30 = memw(R0 + #_PT_ER_VMPSP); }\
+ { memw(R0 + #_PT_R2928) = R28; \
+ memw(R0 + #(_PT_R2928 + 4)) = R30; }\
+ { R31:30 = C11:10; \
+ memd(R0 + #_PT_R2726) = R27:26; \
+ memd(R0 + #_PT_R2524) = R25:24; }\
+ { memd(R0 + #_PT_R2322) = R23:22; \
+ memd(R0 + #_PT_R2120) = R21:20; }\
+ { memd(R0 + #_PT_R1918) = R19:18; \
+ memd(R0 + #_PT_R1716) = R17:16; }\
+ { memd(R0 + #_PT_R1514) = R15:14; \
+ memd(R0 + #_PT_R1312) = R13:12; \
+ R17:16 = C13:12; }\
+ { memd(R0 + #_PT_R1110) = R11:10; \
+ memd(R0 + #_PT_R0908) = R9:8; \
+ R15:14 = C1:0; } \
+ { memd(R0 + #_PT_R0706) = R7:6; \
+ memd(R0 + #_PT_R0504) = R5:4; \
+ R13:12 = C3:2; } \
+ { memd(R0 + #_PT_GPUGP) = R31:30; \
+ memd(R0 + #_PT_LC0SA0) = R15:14; \
+ R11:10 = C7:6; }\
+ { THREADINFO_REG = and(R0, # ## #-_THREAD_SIZE); \
+ memd(R0 + #_PT_LC1SA1) = R13:12; \
+ R15 = p3:0; }\
+ { memd(R0 + #_PT_M1M0) = R11:10; \
+ memw(R0 + #_PT_PREDSUSR + 4) = R15; }\
+ { r24 = memw(THREADINFO_REG + #_THREAD_INFO_PT_REGS); \
+ memw(THREADINFO_REG + #_THREAD_INFO_PT_REGS) = R0; \
+ R2 = #-1; } \
+ { memw(R0 + #_PT_SYSCALL_NR) = R2; \
+ memd(R0 + #_PT_CS1CS0) = R17:16; \
+ R30 = #0; }
+#endif
+
+/*
+ * Restore registers and thread_info.regs state. THREADINFO_REG
+ * is assumed to still be sane, and R24 to have been correctly
+ * preserved. Don't restore R29 (SP) until later.
+ */
+
+#if CONFIG_HEXAGON_ARCH_VERSION < 4
+#define restore_pt_regs() \
+ { memw(THREADINFO_REG + #_THREAD_INFO_PT_REGS) = R24; \
+ R15:14 = memd(R0 + #_PT_PREDSUSR); } \
+ { R11:10 = memd(R0 + #_PT_M1M0); \
+ p3:0 = R15; } \
+ { R13:12 = memd(R0 + #_PT_LC1SA1); \
+ usr = R14; } \
+ { R15:14 = memd(R0 + #_PT_LC0SA0); \
+ m1 = R11; } \
+ { R3:2 = memd(R0 + #_PT_R0302); \
+ m0 = R10; } \
+ { R5:4 = memd(R0 + #_PT_R0504); \
+ lc1 = R13; } \
+ { R7:6 = memd(R0 + #_PT_R0706); \
+ sa1 = R12; } \
+ { R9:8 = memd(R0 + #_PT_R0908); \
+ lc0 = R15; } \
+ { R11:10 = memd(R0 + #_PT_R1110); \
+ sa0 = R14; } \
+ { R13:12 = memd(R0 + #_PT_R1312); \
+ R15:14 = memd(R0 + #_PT_R1514); } \
+ { R17:16 = memd(R0 + #_PT_R1716); \
+ R19:18 = memd(R0 + #_PT_R1918); } \
+ { R21:20 = memd(R0 + #_PT_R2120); \
+ R23:22 = memd(R0 + #_PT_R2322); } \
+ { R25:24 = memd(R0 + #_PT_R2524); \
+ R27:26 = memd(R0 + #_PT_R2726); } \
+ R31:30 = memd(R0 + #_PT_GPUGP); \
+ { R28 = memw(R0 + #_PT_R2928); \
+ ugp = R31; } \
+ { R31:30 = memd(R0 + #_PT_R3130); \
+ gp = R30; }
+#else
+/* V4+ */
+#define restore_pt_regs() \
+ { memw(THREADINFO_REG + #_THREAD_INFO_PT_REGS) = R24; \
+ R15:14 = memd(R0 + #_PT_PREDSUSR); } \
+ { R11:10 = memd(R0 + #_PT_M1M0); \
+ R13:12 = memd(R0 + #_PT_LC1SA1); \
+ p3:0 = R15; } \
+ { R15:14 = memd(R0 + #_PT_LC0SA0); \
+ R3:2 = memd(R0 + #_PT_R0302); \
+ usr = R14; } \
+ { R5:4 = memd(R0 + #_PT_R0504); \
+ R7:6 = memd(R0 + #_PT_R0706); \
+ C7:6 = R11:10; }\
+ { R9:8 = memd(R0 + #_PT_R0908); \
+ R11:10 = memd(R0 + #_PT_R1110); \
+ C3:2 = R13:12; }\
+ { R13:12 = memd(R0 + #_PT_R1312); \
+ R15:14 = memd(R0 + #_PT_R1514); \
+ C1:0 = R15:14; }\
+ { R17:16 = memd(R0 + #_PT_R1716); \
+ R19:18 = memd(R0 + #_PT_R1918); } \
+ { R21:20 = memd(R0 + #_PT_R2120); \
+ R23:22 = memd(R0 + #_PT_R2322); } \
+ { R25:24 = memd(R0 + #_PT_R2524); \
+ R27:26 = memd(R0 + #_PT_R2726); } \
+ R31:30 = memd(R0 + #_PT_CS1CS0); \
+ { C13:12 = R31:30; \
+ R31:30 = memd(R0 + #_PT_GPUGP) ; \
+ R28 = memw(R0 + #_PT_R2928); }\
+ { C11:10 = R31:30; \
+ R31:30 = memd(R0 + #_PT_R3130); }
+#endif
+
+ /*
+ * Clears off enough space for the rest of pt_regs; evrec is a part
+ * of pt_regs in HVM mode. Save R0/R1, set handler's address in R1.
+ * R0 is the address of pt_regs and is the parameter to save_pt_regs.
+ */
+
+/*
+ * Since the HVM isn't automagically pushing the EVREC onto the stack anymore,
+ * we'll subract the entire size out and then fill it in ourselves.
+ * Need to save off R0, R1, R2, R3 immediately.
+ */
+
+#if CONFIG_HEXAGON_ARCH_VERSION < 4
+#define vm_event_entry(CHandler) \
+ { \
+ R29 = add(R29, #-(_PT_REGS_SIZE)); \
+ memd(R29 + #(_PT_R0100 + -_PT_REGS_SIZE)) = R1:0; \
+ } \
+ { \
+ memd(R29 +#_PT_R0302) = R3:2; \
+ } \
+ trap1(#HVM_TRAP1_VMGETREGS); \
+ { \
+ memd(R29 + #_PT_ER_VMEL) = R1:0; \
+ R0 = R29; \
+ R1.L = #LO(CHandler); \
+ } \
+ { \
+ memd(R29 + #_PT_ER_VMPSP) = R3:2; \
+ R1.H = #HI(CHandler); \
+ jump event_dispatch; \
+ }
+#else
+/* V4+ */
+/* turn on I$ prefetch early */
+/* the # ## # syntax inserts a literal ## */
+#define vm_event_entry(CHandler) \
+ { \
+ R29 = add(R29, #-(_PT_REGS_SIZE)); \
+ memd(R29 + #(_PT_R0100 + -_PT_REGS_SIZE)) = R1:0; \
+ memd(R29 + #(_PT_R0302 + -_PT_REGS_SIZE)) = R3:2; \
+ R0 = usr; \
+ } \
+ { \
+ memw(R29 + #_PT_PREDSUSR) = R0; \
+ R0 = setbit(R0, #16); \
+ } \
+ usr = R0; \
+ R1:0 = G1:0; \
+ { \
+ memd(R29 + #_PT_ER_VMEL) = R1:0; \
+ R1 = # ## #(CHandler); \
+ R3:2 = G3:2; \
+ } \
+ { \
+ R0 = R29; \
+ memd(R29 + #_PT_ER_VMPSP) = R3:2; \
+ jump event_dispatch; \
+ }
+#endif
+
+.text
+ /*
+ * Do bulk save/restore in one place.
+ * Adds a jump to dispatch latency, but
+ * saves hundreds of bytes.
+ */
+
+event_dispatch:
+ save_pt_regs()
+ callr r1
+
+ /*
+ * Coming back from the C-world, our thread info pointer
+ * should be in the designated register (usually R19)
+ *
+ * If we were in kernel mode, we don't need to check scheduler
+ * or signals if CONFIG_PREEMPT is not set. If set, then it has
+ * to jump to a need_resched kind of block.
+ * BTW, CONFIG_PREEMPT is not supported yet.
+ */
+
+#ifdef CONFIG_PREEMPT
+ R0 = #VM_INT_DISABLE
+ trap1(#HVM_TRAP1_VMSETIE)
+#endif
+
+ /* "Nested control path" -- if the previous mode was kernel */
+ {
+ R0 = memw(R29 + #_PT_ER_VMEST);
+ R26.L = #LO(do_work_pending);
+ }
+ {
+ P0 = tstbit(R0, #HVM_VMEST_UM_SFT);
+ if (!P0.new) jump:nt restore_all;
+ R26.H = #HI(do_work_pending);
+ R0 = #VM_INT_DISABLE;
+ }
+
+ /*
+ * Check also the return from fork/system call, normally coming back from
+ * user mode
+ *
+ * R26 needs to have do_work_pending, and R0 should have VM_INT_DISABLE
+ */
+
+check_work_pending:
+ /* Disable interrupts while checking TIF */
+ trap1(#HVM_TRAP1_VMSETIE)
+ {
+ R0 = R29; /* regs should still be at top of stack */
+ R1 = memw(THREADINFO_REG + #_THREAD_INFO_FLAGS);
+ callr R26;
+ }
+
+ {
+ P0 = cmp.eq(R0, #0); if (!P0.new) jump:nt check_work_pending;
+ R0 = #VM_INT_DISABLE;
+ }
+
+restore_all:
+ /*
+ * Disable interrupts, if they weren't already, before reg restore.
+ * R0 gets preloaded with #VM_INT_DISABLE before we get here.
+ */
+ trap1(#HVM_TRAP1_VMSETIE)
+
+ /* do the setregs here for VM 0.5 */
+ /* R29 here should already be pointing at pt_regs */
+ {
+ R1:0 = memd(R29 + #_PT_ER_VMEL);
+ R3:2 = memd(R29 + #_PT_ER_VMPSP);
+ }
+#if CONFIG_HEXAGON_ARCH_VERSION < 4
+ trap1(#HVM_TRAP1_VMSETREGS);
+#else
+ G1:0 = R1:0;
+ G3:2 = R3:2;
+#endif
+
+ R0 = R29
+ restore_pt_regs()
+ {
+ R1:0 = memd(R29 + #_PT_R0100);
+ R29 = add(R29, #_PT_REGS_SIZE);
+ }
+ trap1(#HVM_TRAP1_VMRTE)
+ /* Notreached */
+
+
+ .globl _K_enter_genex
+_K_enter_genex:
+ vm_event_entry(do_genex)
+
+ .globl _K_enter_interrupt
+_K_enter_interrupt:
+ vm_event_entry(arch_do_IRQ)
+
+ .globl _K_enter_trap0
+_K_enter_trap0:
+ vm_event_entry(do_trap0)
+
+ .globl _K_enter_machcheck
+_K_enter_machcheck:
+ vm_event_entry(do_machcheck)
+
+ .globl _K_enter_debug
+_K_enter_debug:
+ vm_event_entry(do_debug_exception)
+
+ .globl ret_from_fork
+ret_from_fork:
+ {
+ call schedule_tail
+ R26.H = #HI(do_work_pending);
+ }
+ {
+ P0 = cmp.eq(R24, #0);
+ R26.L = #LO(do_work_pending);
+ R0 = #VM_INT_DISABLE;
+ }
+ if (P0) jump check_work_pending
+ {
+ R0 = R25;
+ callr R24
+ }
+ {
+ jump check_work_pending
+ R0 = #VM_INT_DISABLE;
+ }