linux-kernel - Re: [patch V163 28/51] x86/mm/pti: Add functions to clone kernel PMDs

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20171218130821.prwomtvi6fgu6drc@hirez.programming.kicks-ass.net>
Date:   Mon, 18 Dec 2017 14:08:21 +0100
From:   Peter Zijlstra <peterz@...radead.org>
To:     Thomas Gleixner <tglx@...utronix.de>
Cc:     LKML <linux-kernel@...r.kernel.org>, x86@...nel.org,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Andy Lutomirsky <luto@...nel.org>,
        Dave Hansen <dave.hansen@...el.com>,
        Borislav Petkov <bpetkov@...e.de>,
        Greg KH <gregkh@...uxfoundation.org>, keescook@...gle.com,
        hughd@...gle.com, Brian Gerst <brgerst@...il.com>,
        Josh Poimboeuf <jpoimboe@...hat.com>,
        Denys Vlasenko <dvlasenk@...hat.com>,
        Rik van Riel <riel@...hat.com>,
        Boris Ostrovsky <boris.ostrovsky@...cle.com>,
        Juergen Gross <jgross@...e.com>,
        David Laight <David.Laight@...lab.com>,
        Eduardo Valentin <eduval@...zon.com>, aliguori@...zon.com,
        Will Deacon <will.deacon@....com>, daniel.gruss@...k.tugraz.at,
        Ingo Molnar <mingo@...nel.org>, Borislav Petkov <bp@...en8.de>,
        Dave Hansen <dave.hansen@...ux.intel.com>,
        "H. Peter Anvin" <hpa@...or.com>
Subject: Re: [patch V163 28/51] x86/mm/pti: Add functions to clone kernel PMDs

On Mon, Dec 18, 2017 at 12:42:43PM +0100, Thomas Gleixner wrote:
> @@ -106,6 +111,128 @@ pgd_t __pti_set_user_pgd(pgd_t *pgdp, pg
>  }
>  
>  /*
> + * Walk the user copy of the page tables (optionally) trying to allocate
> + * page table pages on the way down.
> + *
> + * Returns a pointer to a P4D on success, or NULL on failure.
> + */
> +static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
> +{
> +	pgd_t *pgd = kernel_to_user_pgdp(pgd_offset_k(address));
> +	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
> +
> +	if (address < PAGE_OFFSET) {
> +		WARN_ONCE(1, "attempt to walk user address\n");
> +		return NULL;
> +	}
> +
> +	if (pgd_none(*pgd)) {
> +		unsigned long new_p4d_page = __get_free_page(gfp);
> +		if (!new_p4d_page)
> +			return NULL;
> +
> +		if (pgd_none(*pgd)) {
> +			set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page)));
> +			new_p4d_page = 0;
> +		}
> +		if (new_p4d_page)
> +			free_page(new_p4d_page);
> +	}
> +	BUILD_BUG_ON(pgd_large(*pgd) != 0);
> +
> +	return p4d_offset(pgd, address);
> +}
> +
> +/*
> + * Walk the user copy of the page tables (optionally) trying to allocate
> + * page table pages on the way down.
> + *
> + * Returns a pointer to a PMD on success, or NULL on failure.
> + */
> +static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
> +{
> +	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
> +	p4d_t *p4d = pti_user_pagetable_walk_p4d(address);
> +	pud_t *pud;
> +
> +	BUILD_BUG_ON(p4d_large(*p4d) != 0);
> +	if (p4d_none(*p4d)) {
> +		unsigned long new_pud_page = __get_free_page(gfp);
> +		if (!new_pud_page)
> +			return NULL;
> +
> +		if (p4d_none(*p4d)) {
> +			set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page)));
> +			new_pud_page = 0;
> +		}
> +		if (new_pud_page)
> +			free_page(new_pud_page);
> +	}
> +
> +	pud = pud_offset(p4d, address);
> +	/* The user page tables do not use large mappings: */

Hmmm? HugeTLB does 1G pages, no?

> +	if (pud_large(*pud)) {
> +		WARN_ON(1);
> +		return NULL;
> +	}
> +	if (pud_none(*pud)) {
> +		unsigned long new_pmd_page = __get_free_page(gfp);
> +		if (!new_pmd_page)
> +			return NULL;
> +
> +		if (pud_none(*pud)) {
> +			set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
> +			new_pmd_page = 0;
> +		}
> +		if (new_pmd_page)
> +			free_page(new_pmd_page);
> +	}
> +
> +	return pmd_offset(pud, address);
> +}
> +
> +static void __init
> +pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear)
> +{
> +	unsigned long addr;
> +
> +	/*
> +	 * Clone the populated PMDs which cover start to end. These PMD areas
> +	 * can have holes.
> +	 */
> +	for (addr = start; addr < end; addr += PMD_SIZE) {
> +		pmd_t *pmd, *target_pmd;
> +		pgd_t *pgd;
> +		p4d_t *p4d;
> +		pud_t *pud;
> +
> +		pgd = pgd_offset_k(addr);
> +		if (WARN_ON(pgd_none(*pgd)))
> +			return;
> +		p4d = p4d_offset(pgd, addr);
> +		if (WARN_ON(p4d_none(*p4d)))
> +			return;
> +		pud = pud_offset(p4d, addr);
> +		if (pud_none(*pud))
> +			continue;
> +		pmd = pmd_offset(pud, addr);
> +		if (pmd_none(*pmd))
> +			continue;
> +
> +		target_pmd = pti_user_pagetable_walk_pmd(addr);
> +		if (WARN_ON(!target_pmd))
> +			return;
> +
> +		/*
> +		 * Copy the PMD.  That is, the kernelmode and usermode
> +		 * tables will share the last-level page tables of this
> +		 * address range
> +		 */
> +		*target_pmd = pmd_clear_flags(*pmd, clear);
> +	}
> +}

Also, I'm seeing a distinct lack of p.._bad() calls here, do we want
those?