[v4,3/5] powerpc/mm/slice: Fix hugepage allocation at hint address on 8xx

Message ID 4284868e2b1a4358427e4a5d2feaaff9abf277c5.1518226173.git.christophe.leroy@c-s.fr
State New
Headers show
Series
  • [v4,1/5] powerpc/mm/slice: Remove intermediate bitmap copy
Related show

Commit Message

Christophe LEROY Feb. 10, 2018, 12:54 p.m.
On the 8xx, the page size is set in the PMD entry and applies to
all pages of the page table pointed by the said PMD entry.

When an app has some regular pages allocated (e.g. see below) and tries
to mmap() a huge page at a hint address covered by the same PMD entry,
the kernel accepts the hint allthough the 8xx cannot handle different
page sizes in the same PMD entry.

10000000-10001000 r-xp 00000000 00:0f 2597 /root/malloc
10010000-10011000 rwxp 00000000 00:0f 2597 /root/malloc

mmap(0x10080000, 524288, PROT_READ|PROT_WRITE,
     MAP_PRIVATE|MAP_ANONYMOUS|0x40000, -1, 0) = 0x10080000

This results the app remaining forever in do_page_fault()/hugetlb_fault()
and when interrupting that app, we get the following warning:

[162980.035629] WARNING: CPU: 0 PID: 2777 at arch/powerpc/mm/hugetlbpage.c:354 hugetlb_free_pgd_range+0xc8/0x1e4
[162980.035699] CPU: 0 PID: 2777 Comm: malloc Tainted: G W       4.14.6 #85
[162980.035744] task: c67e2c00 task.stack: c668e000
[162980.035783] NIP:  c000fe18 LR: c00e1eec CTR: c00f90c0
[162980.035830] REGS: c668fc20 TRAP: 0700   Tainted: G W        (4.14.6)
[162980.035854] MSR:  00029032 <EE,ME,IR,DR,RI>  CR: 24044224 XER: 20000000
[162980.036003]
[162980.036003] GPR00: c00e1eec c668fcd0 c67e2c00 00000010 c6869410 10080000 00000000 77fb4000
[162980.036003] GPR08: ffff0001 0683c001 00000000 ffffff80 44028228 10018a34 00004008 418004fc
[162980.036003] GPR16: c668e000 00040100 c668e000 c06c0000 c668fe78 c668e000 c6835ba0 c668fd48
[162980.036003] GPR24: 00000000 73ffffff 74000000 00000001 77fb4000 100fffff 10100000 10100000
[162980.036743] NIP [c000fe18] hugetlb_free_pgd_range+0xc8/0x1e4
[162980.036839] LR [c00e1eec] free_pgtables+0x12c/0x150
[162980.036861] Call Trace:
[162980.036939] [c668fcd0] [c00f0774] unlink_anon_vmas+0x1c4/0x214 (unreliable)
[162980.037040] [c668fd10] [c00e1eec] free_pgtables+0x12c/0x150
[162980.037118] [c668fd40] [c00eabac] exit_mmap+0xe8/0x1b4
[162980.037210] [c668fda0] [c0019710] mmput.part.9+0x20/0xd8
[162980.037301] [c668fdb0] [c001ecb0] do_exit+0x1f0/0x93c
[162980.037386] [c668fe00] [c001f478] do_group_exit+0x40/0xcc
[162980.037479] [c668fe10] [c002a76c] get_signal+0x47c/0x614
[162980.037570] [c668fe70] [c0007840] do_signal+0x54/0x244
[162980.037654] [c668ff30] [c0007ae8] do_notify_resume+0x34/0x88
[162980.037744] [c668ff40] [c000dae8] do_user_signal+0x74/0xc4
[162980.037781] Instruction dump:
[162980.037821] 7fdff378 81370000 54a3463a 80890020 7d24182e 7c841a14 712a0004 4082ff94
[162980.038014] 2f890000 419e0010 712a0ff0 408200e0 <0fe00000> 54a9000a 7f984840 419d0094
[162980.038216] ---[ end trace c0ceeca8e7a5800a ]---
[162980.038754] BUG: non-zero nr_ptes on freeing mm: 1
[162985.363322] BUG: non-zero nr_ptes on freeing mm: -1

In order to fix this, this patch uses the address space "slices"
implemented for BOOK3S/64 and enhanced to support PPC32 by the
preceding patch.

This patch modifies the context.id on the 8xx to be in the range
[1:16] instead of [0:15] in order to identify context.id == 0 as
not initialised contexts as done on BOOK3S

This patch activates CONFIG_PPC_MM_SLICES when CONFIG_HUGETLB_PAGE is
selected for the 8xx

Alltough we could in theory have as many slices as PMD entries, the
current slices implementation limits the number of low slices to 16.
This limitation is not preventing us to fix the initial issue allthough
it is suboptimal. It will be cured in a subsequent patch.

Fixes: 4b91428699477 ("powerpc/8xx: Implement support of hugepages")
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 v2: First patch of v1 serie split in two parts
 v3: No changes
 v4: No changes

 arch/powerpc/include/asm/mmu-8xx.h     |  6 ++++++
 arch/powerpc/kernel/setup-common.c     |  2 ++
 arch/powerpc/mm/8xx_mmu.c              |  2 +-
 arch/powerpc/mm/hugetlbpage.c          |  2 ++
 arch/powerpc/mm/mmu_context_nohash.c   | 18 ++++++++++++++++--
 arch/powerpc/platforms/Kconfig.cputype |  1 +
 6 files changed, 28 insertions(+), 3 deletions(-)

Patch

diff --git a/arch/powerpc/include/asm/mmu-8xx.h b/arch/powerpc/include/asm/mmu-8xx.h
index 2f806e329648..b324ab46d838 100644
--- a/arch/powerpc/include/asm/mmu-8xx.h
+++ b/arch/powerpc/include/asm/mmu-8xx.h
@@ -191,6 +191,12 @@  typedef struct {
 	unsigned int id;
 	unsigned int active;
 	unsigned long vdso_base;
+#ifdef CONFIG_PPC_MM_SLICES
+	u16 user_psize;		/* page size index */
+	u64 low_slices_psize;	/* page size encodings */
+	unsigned char high_slices_psize[0];
+	unsigned long slb_addr_limit;
+#endif
 } mm_context_t;
 
 #define PHYS_IMMR_BASE (mfspr(SPRN_IMMR) & 0xfff80000)
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index d73ec518ef80..a6002f9449b1 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -919,6 +919,8 @@  void __init setup_arch(char **cmdline_p)
 #ifdef CONFIG_PPC64
 	if (!radix_enabled())
 		init_mm.context.slb_addr_limit = DEFAULT_MAP_WINDOW_USER64;
+#elif defined(CONFIG_PPC_8xx)
+	init_mm.context.slb_addr_limit = DEFAULT_MAP_WINDOW;
 #else
 #error	"context.addr_limit not initialized."
 #endif
diff --git a/arch/powerpc/mm/8xx_mmu.c b/arch/powerpc/mm/8xx_mmu.c
index 849f50cd62f2..cf77d755246d 100644
--- a/arch/powerpc/mm/8xx_mmu.c
+++ b/arch/powerpc/mm/8xx_mmu.c
@@ -192,7 +192,7 @@  void set_context(unsigned long id, pgd_t *pgd)
 	mtspr(SPRN_M_TW, __pa(pgd) - offset);
 
 	/* Update context */
-	mtspr(SPRN_M_CASID, id);
+	mtspr(SPRN_M_CASID, id - 1);
 	/* sync */
 	mb();
 }
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 876da2bc1796..590be3fa0ce2 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -553,9 +553,11 @@  unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	struct hstate *hstate = hstate_file(file);
 	int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
 
+#ifdef CONFIG_PPC_RADIX_MMU
 	if (radix_enabled())
 		return radix__hugetlb_get_unmapped_area(file, addr, len,
 						       pgoff, flags);
+#endif
 	return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1);
 }
 #endif
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index 4554d6527682..d98f7e5c141b 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -331,6 +331,20 @@  int init_new_context(struct task_struct *t, struct mm_struct *mm)
 {
 	pr_hard("initing context for mm @%p\n", mm);
 
+#ifdef	CONFIG_PPC_MM_SLICES
+	if (!mm->context.slb_addr_limit)
+		mm->context.slb_addr_limit = DEFAULT_MAP_WINDOW;
+
+	/*
+	 * We have MMU_NO_CONTEXT set to be ~0. Hence check
+	 * explicitly against context.id == 0. This ensures that we properly
+	 * initialize context slice details for newly allocated mm's (which will
+	 * have id == 0) and don't alter context slice inherited via fork (which
+	 * will have id != 0).
+	 */
+	if (mm->context.id == 0)
+		slice_set_user_psize(mm, mmu_virtual_psize);
+#endif
 	mm->context.id = MMU_NO_CONTEXT;
 	mm->context.active = 0;
 	return 0;
@@ -428,8 +442,8 @@  void __init mmu_context_init(void)
 	 *      -- BenH
 	 */
 	if (mmu_has_feature(MMU_FTR_TYPE_8xx)) {
-		first_context = 0;
-		last_context = 15;
+		first_context = 1;
+		last_context = 16;
 		no_selective_tlbil = true;
 	} else if (mmu_has_feature(MMU_FTR_TYPE_47x)) {
 		first_context = 1;
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index a429d859f15d..5a8b1bf1e819 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -326,6 +326,7 @@  config PPC_BOOK3E_MMU
 config PPC_MM_SLICES
 	bool
 	default y if PPC_BOOK3S_64
+	default y if PPC_8xx && HUGETLB_PAGE
 	default n
 
 config PPC_HAVE_PMU_SUPPORT