Re: [PATCH 2/3] RISC-V: Make setup_vm() independent of GCC code model

[Mike Rapoport]

On Tue, Mar 12, 2019 at 10:08:16PM +0000, Anup Patel wrote:
> The setup_vm() must access kernel symbols in a position independent way
> because it will be called from head.S with MMU off.
> 
> If we compile kernel with cmodel=medany then PC-relative addressing will
> be used in setup_vm() to access kernel symbols so it works perfectly fine.
> 
> Although, if we compile kernel with cmodel=medlow then either absolute
> addressing or PC-relative addressing (based on whichever requires fewer
> instructions) is used to access kernel symbols in setup_vm(). This can
> break setup_vm() whenever any absolute addressing is used to access
> kernel symbols.
> 
> With the movement of setup_vm() from kernel/setup.c to mm/init.c, the
> setup_vm() is now broken for cmodel=medlow but it works perfectly fine
> for cmodel=medany.
> 
> This patch fixes setup_vm() and makes it independent of GCC code model
> by accessing kernel symbols relative to kernel load address instead of
> assuming PC-relative addressing.
> 
> Fixes: 6f1e9e946f0b ("RISC-V: Move setup_vm() to mm/init.c")
> Signed-off-by: Anup Patel <anup.patel@xxxxxxx>
> ---
>  arch/riscv/kernel/head.S |  1 +
>  arch/riscv/mm/init.c     | 71 ++++++++++++++++++++++++++--------------
>  2 files changed, 47 insertions(+), 25 deletions(-)
> 
> diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
> index fe884cd69abd..7966262b4f9d 100644
> --- a/arch/riscv/kernel/head.S
> +++ b/arch/riscv/kernel/head.S
> @@ -62,6 +62,7 @@ clear_bss_done:
>  
>  	/* Initialize page tables and relocate to virtual addresses */
>  	la sp, init_thread_union + THREAD_SIZE
> +	la a0, _start
>  	call setup_vm
>  	call relocate
>  
> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
> index b379a75ac6a6..f35299f2f3d5 100644
> --- a/arch/riscv/mm/init.c
> +++ b/arch/riscv/mm/init.c
> @@ -172,55 +172,76 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
>  	}
>  }
>  
> -asmlinkage void __init setup_vm(void)
> +static inline void *__early_va(void *ptr, uintptr_t load_pa)
>  {
>  	extern char _start;
> +	uintptr_t va = (uintptr_t)ptr;
> +	uintptr_t sz = (uintptr_t)(&_end) - (uintptr_t)(&_start);
> +
> +	if (va >= PAGE_OFFSET && va < (PAGE_OFFSET + sz))
> +		return (void *)(load_pa + (va - PAGE_OFFSET));

This is (void *)__pa(va), isn't it?

> +	return (void *)va;

The below usage suggests that __early_va() should be used solely for
addresses inside the kernel. What will happen if the accesses is outside
that range? Isn't it a BUG()?

> +}
> +
> +asmlinkage void __init setup_vm(uintptr_t load_pa)
> +{
>  	uintptr_t i;
> -	uintptr_t pa = (uintptr_t) &_start;
> +#ifndef __PAGETABLE_PMD_FOLDED
> +	pmd_t *pmdp;
> +#endif
> +	pgd_t *pgdp;
> +	phys_addr_t map_pa;
> +	pgprot_t tableprot = __pgprot(_PAGE_TABLE);
>  	pgprot_t prot = __pgprot(pgprot_val(PAGE_KERNEL) | _PAGE_EXEC);
>  
> -	va_pa_offset = PAGE_OFFSET - pa;
> -	pfn_base = PFN_DOWN(pa);
> +	va_pa_offset = PAGE_OFFSET - load_pa;
> +	pfn_base = PFN_DOWN(load_pa);
>  
>  	/* Sanity check alignment and size */
>  	BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0);
> -	BUG_ON((pa % (PAGE_SIZE * PTRS_PER_PTE)) != 0);
> +	BUG_ON((load_pa % (PAGE_SIZE * PTRS_PER_PTE)) != 0);
>  
>  #ifndef __PAGETABLE_PMD_FOLDED
> -	trampoline_pg_dir[(PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD] =
> -		pfn_pgd(PFN_DOWN((uintptr_t)trampoline_pmd),
> -			__pgprot(_PAGE_TABLE));
> -	trampoline_pmd[0] = pfn_pmd(PFN_DOWN(pa), prot);
> +	pgdp = __early_va(trampoline_pg_dir, load_pa);
> +	map_pa = (uintptr_t)__early_va(trampoline_pmd, load_pa);

This reads a bit strange: pa = va()
BTW, I think you could keep the pa local variable instead of introducing
map_pa.

> +	pgdp[(PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD] =
> +		pfn_pgd(PFN_DOWN(map_pa), tableprot);
> +	trampoline_pmd[0] = pfn_pmd(PFN_DOWN(load_pa), prot);
> +
> +	pgdp = __early_va(swapper_pg_dir, load_pa);
>  
>  	for (i = 0; i < (-PAGE_OFFSET)/PGDIR_SIZE; ++i) {
>  		size_t o = (PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
>  
> -		swapper_pg_dir[o] =
> -			pfn_pgd(PFN_DOWN((uintptr_t)swapper_pmd) + i,
> -				__pgprot(_PAGE_TABLE));
> +		map_pa = (uintptr_t)__early_va(swapper_pmd, load_pa);
> +		pgdp[o] = pfn_pgd(PFN_DOWN(map_pa) + i, tableprot);
>  	}
> +	pmdp = __early_va(swapper_pmd, load_pa);
>  	for (i = 0; i < ARRAY_SIZE(swapper_pmd); i++)
> -		swapper_pmd[i] = pfn_pmd(PFN_DOWN(pa + i * PMD_SIZE), prot);
> +		pmdp[i] = pfn_pmd(PFN_DOWN(load_pa + i * PMD_SIZE), prot);
>  
> -	swapper_pg_dir[(FIXADDR_START >> PGDIR_SHIFT) % PTRS_PER_PGD] =
> -		pfn_pgd(PFN_DOWN((uintptr_t)fixmap_pmd),
> -				__pgprot(_PAGE_TABLE));
> +	map_pa = (uintptr_t)__early_va(fixmap_pmd, load_pa);
> +	pgdp[(FIXADDR_START >> PGDIR_SHIFT) % PTRS_PER_PGD] =
> +		pfn_pgd(PFN_DOWN(map_pa), tableprot);
> +	pmdp = __early_va(fixmap_pmd, load_pa);
> +	map_pa = (uintptr_t)__early_va(fixmap_pte, load_pa);
>  	fixmap_pmd[(FIXADDR_START >> PMD_SHIFT) % PTRS_PER_PMD] =
> -		pfn_pmd(PFN_DOWN((uintptr_t)fixmap_pte),
> -				__pgprot(_PAGE_TABLE));
> +		pfn_pmd(PFN_DOWN(map_pa), tableprot);
>  #else
> -	trampoline_pg_dir[(PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD] =
> -		pfn_pgd(PFN_DOWN(pa), prot);
> +	pgdp = __early_va(trampoline_pg_dir, load_pa);
> +	pgdp[(PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD] =
> +		pfn_pgd(PFN_DOWN(load_pa), prot);
> +
> +	pgdp = __early_va(swapper_pg_dir, load_pa);
>  
>  	for (i = 0; i < (-PAGE_OFFSET)/PGDIR_SIZE; ++i) {
>  		size_t o = (PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
>  
> -		swapper_pg_dir[o] =
> -			pfn_pgd(PFN_DOWN(pa + i * PGDIR_SIZE), prot);
> +		pgdp[o] = pfn_pgd(PFN_DOWN(load_pa + i * PGDIR_SIZE), prot);
>  	}
>  
> -	swapper_pg_dir[(FIXADDR_START >> PGDIR_SHIFT) % PTRS_PER_PGD] =
> -		pfn_pgd(PFN_DOWN((uintptr_t)fixmap_pte),
> -				__pgprot(_PAGE_TABLE));
> +	map_pa = (uintptr_t)__early_va(fixmap_pte, load_pa);
> +	pgdp[(FIXADDR_START >> PGDIR_SHIFT) % PTRS_PER_PGD] =
> +		pfn_pgd(PFN_DOWN(map_pa), tableprot);
>  #endif
>  }
> -- 
> 2.17.1
> 

-- 
Sincerely yours,
Mike.