Commit 16f1c746 authored by Benjamin Herrenschmidt's avatar Benjamin Herrenschmidt Committed by Paul Mackerras
Browse files

[POWERPC] Small fixes & cleanups in segment page size demotion 



The code for demoting segments to 4K had some issues, like for example,
when using _PAGE_4K_PFN flag, the first CPU to hit it would do the
demotion, but other CPUs hitting the same page wouldn't properly flush
their SLBs if mmu_ci_restriction isn't set.  There are also potential
issues with hash_preload not handling _PAGE_4K_PFN.  All of these are
non issues on current hardware but might bite us in the future.

This patch thus fixes it by:

 - Taking the test comparing the mm and current CPU context page
sizes to decide to flush SLBs out of the mmu_ci_restrictions test
since that can also be triggered by _PAGE_4K_PFN pages

 - Due to the above being done all the time, demote_segment_4k
doesn't need update the context and flush the SLB

 - demote_segment_4k can be static and doesn't need an EXPORT_SYMBOL

 - Making hash_preload ignore anything that has either _PAGE_4K_PFN
or _PAGE_NO_CACHE set, thus avoiding duplication of the complicated
logic in hash_page() (and possibly making hash_preload a little bit
faster for the normal case).

Signed-off-by: default avatarBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: default avatarPaul Mackerras <paulus@samba.org>
parent b15f792f

arch/powerpc/mm/hash_utils_64.c

+46 −41
Original line number Diff line number Diff line
@@ -596,22 +596,18 @@ unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap) 
 * Demote a segment to using 4k pages.

 * For now this makes the whole process use 4k pages.

 */

void demote_segment_4k(struct mm_struct *mm, unsigned long addr)

{

#ifdef CONFIG_PPC_64K_PAGES

static void demote_segment_4k(struct mm_struct *mm, unsigned long addr)

{

	if (mm->context.user_psize == MMU_PAGE_4K)

		return;

	mm->context.user_psize = MMU_PAGE_4K;

	mm->context.sllp = SLB_VSID_USER | mmu_psize_defs[MMU_PAGE_4K].sllp;

	get_paca()->context = mm->context;

	slb_flush_and_rebolt();

#ifdef CONFIG_SPE_BASE

	spu_flush_all_slbs(mm);

#endif

#endif

}



EXPORT_SYMBOL_GPL(demote_segment_4k);

#endif /* CONFIG_PPC_64K_PAGES */



/* Result code is:

 *  0 - handled
@@ -711,9 +707,10 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) 
		psize = MMU_PAGE_4K;

	}



	if (mmu_ci_restrictions) {

		/* If this PTE is non-cacheable, switch to 4k */

		if (psize == MMU_PAGE_64K &&

	/* If this PTE is non-cacheable and we have restrictions on

	 * using non cacheable large pages, then we switch to 4k

	 */

	if (mmu_ci_restrictions && psize == MMU_PAGE_64K &&

	    (pte_val(*ptep) & _PAGE_NO_CACHE)) {

		if (user_region) {

			demote_segment_4k(mm, ea);
@@ -728,14 +725,15 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) 
			       "to 4kB pages because of "

			       "non-cacheable mapping\n");

			psize = mmu_vmalloc_psize = MMU_PAGE_4K;

			}

#ifdef CONFIG_SPE_BASE

			spu_flush_all_slbs(mm);

#endif

		}

	}

	if (user_region) {

		if (psize != get_paca()->context.user_psize) {

				get_paca()->context = mm->context;

			get_paca()->context.user_psize =

				mm->context.user_psize;

			slb_flush_and_rebolt();

		}

	} else if (get_paca()->vmalloc_sllp !=
@@ -744,7 +742,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) 
			mmu_psize_defs[mmu_vmalloc_psize].sllp;

		slb_flush_and_rebolt();

	}

	}



	if (psize == MMU_PAGE_64K)

		rc = __hash_page_64K(ea, access, vsid, ptep, trap, local);

	else
@@ -780,13 +778,26 @@ void hash_preload(struct mm_struct *mm, unsigned long ea, 
	DBG_LOW("hash_preload(mm=%p, mm->pgdir=%p, ea=%016lx, access=%lx,"

		" trap=%lx\n", mm, mm->pgd, ea, access, trap);



	/* Get PTE, VSID, access mask */

	/* Get Linux PTE if available */

	pgdir = mm->pgd;

	if (pgdir == NULL)

		return;

	ptep = find_linux_pte(pgdir, ea);

	if (!ptep)

		return;



#ifdef CONFIG_PPC_64K_PAGES

	/* If either _PAGE_4K_PFN or _PAGE_NO_CACHE is set (and we are on

	 * a 64K kernel), then we don't preload, hash_page() will take

	 * care of it once we actually try to access the page.

	 * That way we don't have to duplicate all of the logic for segment

	 * page size demotion here

	 */

	if (pte_val(*ptep) & (_PAGE_4K_PFN | _PAGE_NO_CACHE))

		return;

#endif /* CONFIG_PPC_64K_PAGES */



	/* Get VSID */

	vsid = get_vsid(mm->context.id, ea);



	/* Hash it in */
@@ -797,12 +808,6 @@ void hash_preload(struct mm_struct *mm, unsigned long ea, 
#ifndef CONFIG_PPC_64K_PAGES

	__hash_page_4K(ea, access, vsid, ptep, trap, local);

#else

	if (mmu_ci_restrictions) {

		/* If this PTE is non-cacheable, switch to 4k */

		if (mm->context.user_psize == MMU_PAGE_64K &&

		    (pte_val(*ptep) & _PAGE_NO_CACHE))

			demote_segment_4k(mm, ea);

	}

	if (mm->context.user_psize == MMU_PAGE_64K)

		__hash_page_64K(ea, access, vsid, ptep, trap, local);

	else

CRA Git | Maintained and supported by SUSTech CRA and CCSE