Orange Pi5 kernel

^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   1) // SPDX-License-Identifier: GPL-2.0
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   2) // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   3) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   4) #include <linux/signal.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   5) #include <linux/module.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   6) #include <linux/sched.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   7) #include <linux/interrupt.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   8) #include <linux/kernel.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   9) #include <linux/errno.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  10) #include <linux/string.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  11) #include <linux/types.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  12) #include <linux/ptrace.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  13) #include <linux/mman.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  14) #include <linux/mm.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  15) #include <linux/smp.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  16) #include <linux/version.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  17) #include <linux/vt_kern.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  18) #include <linux/extable.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  19) #include <linux/uaccess.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  20) #include <linux/perf_event.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  21) #include <linux/kprobes.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  22) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  23) #include <asm/hardirq.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  24) #include <asm/mmu_context.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  25) #include <asm/traps.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  26) #include <asm/page.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  27) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  28) int fixup_exception(struct pt_regs *regs)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  29) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  30) 	const struct exception_table_entry *fixup;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  31) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  32) 	fixup = search_exception_tables(instruction_pointer(regs));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  33) 	if (fixup) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  34) 		regs->pc = fixup->nextinsn;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  35) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  36) 		return 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  37) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  38) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  39) 	return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  40) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  41) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  42) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  43)  * This routine handles page faults. It determines the address,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  44)  * and the problem, and then passes it off to one of the appropriate
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  45)  * routines.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  46)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  47) asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  48) 			      unsigned long mmu_meh)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  49) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  50) 	struct vm_area_struct *vma = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  51) 	struct task_struct *tsk = current;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  52) 	struct mm_struct *mm = tsk->mm;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  53) 	int si_code;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  54) 	int fault;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  55) 	unsigned long address = mmu_meh & PAGE_MASK;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  56) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  57) 	if (kprobe_page_fault(regs, tsk->thread.trap_no))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  58) 		return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  59) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  60) 	si_code = SEGV_MAPERR;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  61) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  62) #ifndef CONFIG_CPU_HAS_TLBI
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  63) 	/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  64) 	 * We fault-in kernel-space virtual memory on-demand. The
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  65) 	 * 'reference' page table is init_mm.pgd.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  66) 	 *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  67) 	 * NOTE! We MUST NOT take any locks for this case. We may
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  68) 	 * be in an interrupt or a critical region, and should
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  69) 	 * only copy the information from the master page table,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  70) 	 * nothing more.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  71) 	 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  72) 	if (unlikely(address >= VMALLOC_START) &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  73) 	    unlikely(address <= VMALLOC_END)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  74) 		/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  75) 		 * Synchronize this task's top level page-table
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  76) 		 * with the 'reference' page table.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  77) 		 *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  78) 		 * Do _not_ use "tsk" here. We might be inside
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  79) 		 * an interrupt in the middle of a task switch..
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  80) 		 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  81) 		int offset = pgd_index(address);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  82) 		pgd_t *pgd, *pgd_k;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  83) 		pud_t *pud, *pud_k;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  84) 		pmd_t *pmd, *pmd_k;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  85) 		pte_t *pte_k;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  86) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  87) 		unsigned long pgd_base;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  88) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  89) 		pgd_base = (unsigned long)__va(get_pgd());
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  90) 		pgd = (pgd_t *)pgd_base + offset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  91) 		pgd_k = init_mm.pgd + offset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  92) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  93) 		if (!pgd_present(*pgd_k))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  94) 			goto no_context;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  95) 		set_pgd(pgd, *pgd_k);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  96) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  97) 		pud = (pud_t *)pgd;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  98) 		pud_k = (pud_t *)pgd_k;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  99) 		if (!pud_present(*pud_k))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 100) 			goto no_context;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 101) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 102) 		pmd = pmd_offset(pud, address);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 103) 		pmd_k = pmd_offset(pud_k, address);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 104) 		if (!pmd_present(*pmd_k))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 105) 			goto no_context;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 106) 		set_pmd(pmd, *pmd_k);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 107) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 108) 		pte_k = pte_offset_kernel(pmd_k, address);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 109) 		if (!pte_present(*pte_k))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 110) 			goto no_context;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 111) 		return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 112) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 113) #endif
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 114) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 115) 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 116) 	/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 117) 	 * If we're in an interrupt or have no user
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 118) 	 * context, we must not take the fault..
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 119) 	 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 120) 	if (in_atomic() || !mm)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 121) 		goto bad_area_nosemaphore;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 122) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 123) 	mmap_read_lock(mm);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 124) 	vma = find_vma(mm, address);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 125) 	if (!vma)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 126) 		goto bad_area;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 127) 	if (vma->vm_start <= address)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 128) 		goto good_area;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 129) 	if (!(vma->vm_flags & VM_GROWSDOWN))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 130) 		goto bad_area;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 131) 	if (expand_stack(vma, address))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 132) 		goto bad_area;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 133) 	/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 134) 	 * Ok, we have a good vm_area for this memory access, so
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 135) 	 * we can handle it..
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 136) 	 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 137) good_area:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 138) 	si_code = SEGV_ACCERR;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 139) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 140) 	if (write) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 141) 		if (!(vma->vm_flags & VM_WRITE))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 142) 			goto bad_area;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 143) 	} else {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 144) 		if (unlikely(!vma_is_accessible(vma)))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 145) 			goto bad_area;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 146) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 147) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 148) 	/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 149) 	 * If for any reason at all we couldn't handle the fault,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 150) 	 * make sure we exit gracefully rather than endlessly redo
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 151) 	 * the fault.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 152) 	 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 153) 	fault = handle_mm_fault(vma, address, write ? FAULT_FLAG_WRITE : 0,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 154) 				regs);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 155) 	if (unlikely(fault & VM_FAULT_ERROR)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 156) 		if (fault & VM_FAULT_OOM)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 157) 			goto out_of_memory;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 158) 		else if (fault & VM_FAULT_SIGBUS)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 159) 			goto do_sigbus;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 160) 		else if (fault & VM_FAULT_SIGSEGV)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 161) 			goto bad_area;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 162) 		BUG();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 163) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 164) 	mmap_read_unlock(mm);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 165) 	return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 166) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 167) 	/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 168) 	 * Something tried to access memory that isn't in our memory map..
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 169) 	 * Fix it, but check if it's kernel or user first..
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 170) 	 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 171) bad_area:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 172) 	mmap_read_unlock(mm);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 173) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 174) bad_area_nosemaphore:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 175) 	/* User mode accesses just cause a SIGSEGV */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 176) 	if (user_mode(regs)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 177) 		tsk->thread.trap_no = trap_no(regs);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 178) 		force_sig_fault(SIGSEGV, si_code, (void __user *)address);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 179) 		return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 180) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 181) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 182) no_context:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 183) 	tsk->thread.trap_no = trap_no(regs);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 184) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 185) 	/* Are we prepared to handle this kernel fault? */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 186) 	if (fixup_exception(regs))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 187) 		return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 188) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 189) 	/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 190) 	 * Oops. The kernel tried to access some bad page. We'll have to
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 191) 	 * terminate things with extreme prejudice.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 192) 	 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 193) 	bust_spinlocks(1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 194) 	pr_alert("Unable to handle kernel paging request at virtual "
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 195) 		 "address 0x%08lx, pc: 0x%08lx\n", address, regs->pc);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 196) 	die(regs, "Oops");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 197) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 198) out_of_memory:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 199) 	tsk->thread.trap_no = trap_no(regs);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 200) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 201) 	/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 202) 	 * We ran out of memory, call the OOM killer, and return the userspace
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 203) 	 * (which will retry the fault, or kill us if we got oom-killed).
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 204) 	 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 205) 	pagefault_out_of_memory();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 206) 	return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 207) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 208) do_sigbus:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 209) 	tsk->thread.trap_no = trap_no(regs);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 210) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 211) 	mmap_read_unlock(mm);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 212) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 213) 	/* Kernel mode? Handle exceptions or die */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 214) 	if (!user_mode(regs))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 215) 		goto no_context;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 216) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 217) 	force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 218) }