MIPS: Allows relocation exception vectors everywhere

Now the exception vector for CPS systems are allocated on-fly
with memblock as well.

It will try to allocate from KSEG1 first, and then try to allocate
in low 4G if possible.

The main reset vector is now generated by uasm, to avoid tons
of patches to the code. Other vectors are copied to the location
later.

move 64bits fix in an other patch
fix cache issue with mips_cps_core_entry
rewrite the patch to reduce the diff stat
move extern in header
use cache address for copying vector

gc: use the new macro CKSEG[0A1]DDR_OR_64BIT()
Signed-off-by: Jiaxun Yang <[e-mail]>
Signed-off-by: Gregory CLEMENT <[e-mail]>
Signed-off-by: Thomas Bogendoerfer <[e-mail]>

arch/mips/include/asm/mips-cm.h

···
 /* GCR_Cx_RESET_BASE - Configure where powered up cores will fetch from */
 GCR_CX_ACCESSOR_RW(32, 0x020, reset_base)
 #define CM_GCR_Cx_RESET_BASE_BEVEXCBASE		GENMASK(31, 12)
+#define CM_GCR_Cx_RESET_BASE_MODE		BIT(1)
 
 /* GCR_Cx_ID - Identify the current core */
 GCR_CX_ACCESSOR_RO(32, 0x028, id)

arch/mips/include/asm/smp-cps.h

···
 
 extern struct core_boot_config *mips_cps_core_bootcfg;
 
-extern void mips_cps_core_entry(void);
+extern void mips_cps_core_boot(int cca, void __iomem *gcr_base);
 extern void mips_cps_core_init(void);
 
 extern void mips_cps_boot_vpes(struct core_boot_config *cfg, unsigned vpe);
···
 extern void mips_cps_pm_save(void);
 extern void mips_cps_pm_restore(void);
 
-extern void *mips_cps_core_entry_patch_end;
+extern void excep_tlbfill(void);
+extern void excep_xtlbfill(void);
+extern void excep_cache(void);
+extern void excep_genex(void);
+extern void excep_intex(void);
+extern void excep_ejtag(void);
 
 #ifdef CONFIG_MIPS_CPS
 

arch/mips/kernel/cps-vec.S

···
  * Author: Paul Burton <[e-mail]>
  */
 
+#include <linux/init.h>
 #include <asm/addrspace.h>
 #include <asm/asm.h>
 #include <asm/asm-offsets.h>
···
 	.endm
 
 
-.balign 0x1000
-
-LEAF(mips_cps_core_entry)
-	/*
-	 * These first several instructions will be patched by cps_smp_setup to load the
-	 * CCA to use into register s0 and GCR base address to register s1.
-	 */
-	.rept   CPS_ENTRY_PATCH_INSNS
-	nop
-	.endr
-
-	.global mips_cps_core_entry_patch_end
-mips_cps_core_entry_patch_end:
-
-	/* Check whether we're here due to an NMI */
-	mfc0	k0, CP0_STATUS
-	and	k0, k0, ST0_NMI
-	beqz	k0, not_nmi
-	 nop
-
-	/* This is an NMI */
-	PTR_LA	k0, nmi_handler
-	jr	k0
-	 nop
-
-not_nmi:
-	/* Setup Cause */
-	li	t0, CAUSEF_IV
-	mtc0	t0, CP0_CAUSE
-
-	/* Setup Status */
-	li	t0, ST0_CU1 | ST0_CU0 | ST0_BEV | STATUS_BITDEPS
-	mtc0	t0, CP0_STATUS
+LEAF(mips_cps_core_boot)
+	/* Save  CCA and GCR base */
+	move   s0, a0
+	move   s1, a1
 
 	/* We don't know how to do coherence setup on earlier ISA */
 #if MIPS_ISA_REV > 0
···
 	PTR_L	sp, VPEBOOTCFG_SP(v1)
 	jr	t1
 	 nop
-	END(mips_cps_core_entry)
+	END(mips_cps_core_boot)
 
-.org 0x200
+	__INIT
 LEAF(excep_tlbfill)
 	DUMP_EXCEP("TLB Fill")
 	b	.
 	 nop
 	END(excep_tlbfill)
 
-.org 0x280
 LEAF(excep_xtlbfill)
 	DUMP_EXCEP("XTLB Fill")
 	b	.
 	 nop
 	END(excep_xtlbfill)
 
-.org 0x300
 LEAF(excep_cache)
 	DUMP_EXCEP("Cache")
 	b	.
 	 nop
 	END(excep_cache)
 
-.org 0x380
 LEAF(excep_genex)
 	DUMP_EXCEP("General")
 	b	.
 	 nop
 	END(excep_genex)
 
-.org 0x400
 LEAF(excep_intex)
 	DUMP_EXCEP("Interrupt")
 	b	.
 	 nop
 	END(excep_intex)
 
-.org 0x480
 LEAF(excep_ejtag)
 	PTR_LA	k0, ejtag_debug_handler
 	jr	k0
 	 nop
 	END(excep_ejtag)
+	__FINIT
 
 LEAF(mips_cps_core_init)
 #ifdef CONFIG_MIPS_MT_SMP

arch/mips/kernel/smp-cps.c

···
 #include <linux/cpu.h>
 #include <linux/delay.h>
 #include <linux/io.h>
+#include <linux/memblock.h>
 #include <linux/sched/task_stack.h>
 #include <linux/sched/hotplug.h>
 #include <linux/slab.h>
···
 #include <asm/mipsregs.h>
 #include <asm/pm-cps.h>
 #include <asm/r4kcache.h>
+#include <asm/regdef.h>
 #include <asm/smp.h>
 #include <asm/smp-cps.h>
 #include <asm/time.h>
 #include <asm/uasm.h>
 
+#define BEV_VEC_SIZE	0x500
+#define BEV_VEC_ALIGN	0x1000
+
+enum label_id {
+	label_not_nmi = 1,
+};
+
+UASM_L_LA(_not_nmi)
+
 static DECLARE_BITMAP(core_power, NR_CPUS);
+static uint32_t core_entry_reg;
+static phys_addr_t cps_vec_pa;
 
 struct core_boot_config *mips_cps_core_bootcfg;
 
···
 	return min(smp_max_threads, mips_cps_numvps(cluster, core));
 }
 
+static void __init *mips_cps_build_core_entry(void *addr)
+{
+	extern void (*nmi_handler)(void);
+	u32 *p = addr;
+	u32 val;
+	struct uasm_label labels[2];
+	struct uasm_reloc relocs[2];
+	struct uasm_label *l = labels;
+	struct uasm_reloc *r = relocs;
+
+	memset(labels, 0, sizeof(labels));
+	memset(relocs, 0, sizeof(relocs));
+
+	uasm_i_mfc0(&p, GPR_K0, C0_STATUS);
+	UASM_i_LA(&p, GPR_T9, ST0_NMI);
+	uasm_i_and(&p, GPR_K0, GPR_K0, GPR_T9);
+
+	uasm_il_bnez(&p, &r, GPR_K0, label_not_nmi);
+	uasm_i_nop(&p);
+	UASM_i_LA(&p, GPR_K0, (long)&nmi_handler);
+
+	uasm_l_not_nmi(&l, p);
+
+	val = CAUSEF_IV;
+	uasm_i_lui(&p, GPR_K0, val >> 16);
+	uasm_i_ori(&p, GPR_K0, GPR_K0, val & 0xffff);
+	uasm_i_mtc0(&p, GPR_K0, C0_CAUSE);
+	val = ST0_CU1 | ST0_CU0 | ST0_BEV | ST0_KX_IF_64;
+	uasm_i_lui(&p, GPR_K0, val >> 16);
+	uasm_i_ori(&p, GPR_K0, GPR_K0, val & 0xffff);
+	uasm_i_mtc0(&p, GPR_K0, C0_STATUS);
+	uasm_i_ehb(&p);
+	uasm_i_ori(&p, GPR_A0, 0, read_c0_config() & CONF_CM_CMASK);
+	UASM_i_LA(&p, GPR_A1, (long)mips_gcr_base);
+#if defined(KBUILD_64BIT_SYM32) || defined(CONFIG_32BIT)
+	UASM_i_LA(&p, GPR_T9, CKSEG1ADDR(__pa_symbol(mips_cps_core_boot)));
+#else
+	UASM_i_LA(&p, GPR_T9, TO_UNCAC(__pa_symbol(mips_cps_core_boot)));
+#endif
+	uasm_i_jr(&p, GPR_T9);
+	uasm_i_nop(&p);
+
+	uasm_resolve_relocs(relocs, labels);
+
+	return p;
+}
+
+static int __init allocate_cps_vecs(void)
+{
+	/* Try to allocate in KSEG1 first */
+	cps_vec_pa = memblock_phys_alloc_range(BEV_VEC_SIZE, BEV_VEC_ALIGN,
+						0x0, CSEGX_SIZE - 1);
+
+	if (cps_vec_pa)
+		core_entry_reg = CKSEG1ADDR(cps_vec_pa) &
+					CM_GCR_Cx_RESET_BASE_BEVEXCBASE;
+
+	if (!cps_vec_pa && mips_cm_is64) {
+		cps_vec_pa = memblock_phys_alloc_range(BEV_VEC_SIZE, BEV_VEC_ALIGN,
+							0x0, SZ_4G - 1);
+		if (cps_vec_pa)
+			core_entry_reg = (cps_vec_pa & CM_GCR_Cx_RESET_BASE_BEVEXCBASE) |
+					CM_GCR_Cx_RESET_BASE_MODE;
+	}
+
+	if (!cps_vec_pa)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void __init setup_cps_vecs(void)
+{
+	void *cps_vec;
+
+	cps_vec = (void *)CKSEG1ADDR_OR_64BIT(cps_vec_pa);
+	mips_cps_build_core_entry(cps_vec);
+
+	memcpy(cps_vec + 0x200, &excep_tlbfill, 0x80);
+	memcpy(cps_vec + 0x280, &excep_xtlbfill, 0x80);
+	memcpy(cps_vec + 0x300, &excep_cache, 0x80);
+	memcpy(cps_vec + 0x380, &excep_genex, 0x80);
+	memcpy(cps_vec + 0x400, &excep_intex, 0x80);
+	memcpy(cps_vec + 0x480, &excep_ejtag, 0x80);
+
+	/* Make sure no prefetched data in cache */
+	blast_inv_dcache_range(CKSEG0ADDR_OR_64BIT(cps_vec_pa), CKSEG0ADDR_OR_64BIT(cps_vec_pa) + BEV_VEC_SIZE);
+	bc_inv(CKSEG0ADDR_OR_64BIT(cps_vec_pa), BEV_VEC_SIZE);
+	__sync();
+}
+
 static void __init cps_smp_setup(void)
 {
 	unsigned int nclusters, ncores, nvpes, core_vpes;
-	unsigned long core_entry;
 	int cl, c, v;
 
 	/* Detect & record VPE topology */
···
 	/* Make core 0 coherent with everything */
 	write_gcr_cl_coherence(0xff);
 
-	if (mips_cm_revision() >= CM_REV_CM3) {
-		core_entry = CKSEG1ADDR((unsigned long)mips_cps_core_entry);
-		write_gcr_bev_base(core_entry);
-	}
+	if (allocate_cps_vecs())
+		pr_err("Failed to allocate CPS vectors\n");
+
+	if (core_entry_reg && mips_cm_revision() >= CM_REV_CM3)
+		write_gcr_bev_base(core_entry_reg);
 
 #ifdef CONFIG_MIPS_MT_FPAFF
 	/* If we have an FPU, enroll ourselves in the FPU-full mask */
···
 {
 	unsigned ncores, core_vpes, c, cca;
 	bool cca_unsuitable, cores_limited;
-	u32 *entry_code;
 
 	mips_mt_set_cpuoptions();
+
+	if (!core_entry_reg) {
+		pr_err("core_entry address unsuitable, disabling smp-cps\n");
+		goto err_out;
+	}
 
 	/* Detect whether the CCA is unsuited to multi-core SMP */
 	cca = read_c0_config() & CONF_CM_CMASK;
···
 			(cca_unsuitable && cpu_has_dc_aliases) ? " & " : "",
 			cpu_has_dc_aliases ? "dcache aliasing" : "");
 
-	/*
-	 * Patch the start of mips_cps_core_entry to provide:
-	 *
-	 * s0 = kseg0 CCA
-	 */
-	entry_code = (u32 *)&mips_cps_core_entry;
-	uasm_i_addiu(&entry_code, 16, 0, cca);
-	UASM_i_LA(&entry_code, 17, (long)mips_gcr_base);
-	BUG_ON((void *)entry_code > (void *)&mips_cps_core_entry_patch_end);
-	blast_dcache_range((unsigned long)&mips_cps_core_entry,
-			   (unsigned long)entry_code);
-	bc_wback_inv((unsigned long)&mips_cps_core_entry,
-		     (void *)entry_code - (void *)&mips_cps_core_entry);
-	__sync();
+	setup_cps_vecs();
 
 	/* Allocate core boot configuration structs */
 	ncores = mips_cps_numcores(0);
···
 	mips_cm_lock_other(0, core, 0, CM_GCR_Cx_OTHER_BLOCK_LOCAL);
 
 	/* Set its reset vector */
-	write_gcr_co_reset_base(CKSEG1ADDR((unsigned long)mips_cps_core_entry));
+	write_gcr_co_reset_base(core_entry_reg);
 
 	/* Ensure its coherency is disabled */
 	write_gcr_co_coherence(0);
···
 	unsigned vpe_id = cpu_vpe_id(&cpu_data[cpu]);
 	struct core_boot_config *core_cfg = &mips_cps_core_bootcfg[core];
 	struct vpe_boot_config *vpe_cfg = &core_cfg->vpe_config[vpe_id];
-	unsigned long core_entry;
 	unsigned int remote;
 	int err;
 
···
 
 	if (cpu_has_vp) {
 		mips_cm_lock_other(0, core, vpe_id, CM_GCR_Cx_OTHER_BLOCK_LOCAL);
-		core_entry = CKSEG1ADDR((unsigned long)mips_cps_core_entry);
-		write_gcr_co_reset_base(core_entry);
+		write_gcr_co_reset_base(core_entry_reg);
 		mips_cm_unlock_other();
 	}