* [PATCH v3 26/45] powerpc/8xx: Manage 512k huge pages as standard pages.
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
At the time being, 512k huge pages are handled through hugepd page
tables. The PMD entry is flagged as a hugepd pointer and it
means that only 512k hugepages can be managed in that 4M block.
However, the hugepd table has the same size as a normal page
table, and 512k entries can therefore be nested with normal pages.
On the 8xx, TLB loading is performed by software and allthough the
page tables are organised to match the L1 and L2 level defined by
the HW, all TLB entries have both L1 and L2 independent entries.
It means that even if two TLB entries are associated with the same
PMD entry, they can be loaded with different values in L1 part.
The L1 entry contains the page size (PS field):
- 00 for 4k and 16 pages
- 01 for 512k pages
- 11 for 8M pages
By adding a flag for hugepages in the PTE (_PAGE_HUGE) and copying it
into the lower bit of PS, we can then manage 512k pages with normal
page tables:
- PMD entry has PS=11 for 8M pages
- PMD entry has PS=00 for other pages.
As a PMD entry covers 4M areas, a PMD will either point to a hugepd
table having a single entry to an 8M page, or the PMD will point to
a standard page table which will have either entries to 4k or 16k or
512k pages. For 512k pages, as the L1 entry will not know it is a
512k page before the PTE is read, there will be 128 entries in the
PTE as if it was 4k pages. But when loading the TLB, it will be
flagged as a 512k page.
Note that we can't use pmd_ptr() in asm/nohash/32/pgtable.h because
it is not defined yet.
In ITLB miss, we keep the possibility to opt it out as when kernel
text is pinned and no user hugepages are used, we can save several
instruction by not using r11.
In DTLB miss, that's just one instruction so it's not worth bothering
with it.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/nohash/32/pgtable.h | 10 ++++++---
arch/powerpc/include/asm/nohash/32/pte-8xx.h | 4 +++-
arch/powerpc/include/asm/nohash/pgtable.h | 2 +-
arch/powerpc/kernel/head_8xx.S | 12 +++++------
arch/powerpc/mm/hugetlbpage.c | 22 +++++++++++++++++---
arch/powerpc/mm/pgtable.c | 10 ++++++++-
6 files changed, 44 insertions(+), 16 deletions(-)
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 1a86d20b58f3..1504af38a9a8 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -229,8 +229,9 @@ static inline void pmd_clear(pmd_t *pmdp)
* those implementations.
*
* On the 8xx, the page tables are a bit special. For 16k pages, we have
- * 4 identical entries. For other page sizes, we have a single entry in the
- * table.
+ * 4 identical entries. For 512k pages, we have 128 entries as if it was
+ * 4k pages, but they are flagged as 512k pages for the hardware.
+ * For other page sizes, we have a single entry in the table.
*/
#ifdef CONFIG_PPC_8xx
static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
@@ -240,13 +241,16 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p
pte_basic_t old = pte_val(*p);
pte_basic_t new = (old & ~(pte_basic_t)clr) | set;
int num, i;
+ pmd_t *pmd = pmd_offset(pud_offset(pgd_offset(mm, addr), addr), addr);
if (!huge)
num = PAGE_SIZE / SZ_4K;
+ else if ((pmd_val(*pmd) & _PMD_PAGE_MASK) != _PMD_PAGE_8M)
+ num = SZ_512K / SZ_4K;
else
num = 1;
- for (i = 0; i < num; i++, entry++)
+ for (i = 0; i < num; i++, entry++, new += SZ_4K)
*entry = new;
return old;
diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
index c9e4b2d90f65..66f403a7da44 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
@@ -46,6 +46,8 @@
#define _PAGE_NA 0x0200 /* Supervisor NA, User no access */
#define _PAGE_RO 0x0600 /* Supervisor RO, User no access */
+#define _PAGE_HUGE 0x0800 /* Copied to L1 PS bit 29 */
+
/* cache related flags non existing on 8xx */
#define _PAGE_COHERENT 0
#define _PAGE_WRITETHRU 0
@@ -128,7 +130,7 @@ static inline pte_t pte_mkuser(pte_t pte)
static inline pte_t pte_mkhuge(pte_t pte)
{
- return __pte(pte_val(pte) | _PAGE_SPS);
+ return __pte(pte_val(pte) | _PAGE_SPS | _PAGE_HUGE);
}
#define pte_mkhuge pte_mkhuge
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 7fed9dc0f147..f27c967d9269 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -267,7 +267,7 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
static inline int hugepd_ok(hugepd_t hpd)
{
#ifdef CONFIG_PPC_8xx
- return ((hpd_val(hpd) & 0x4) != 0);
+ return ((hpd_val(hpd) & _PMD_PAGE_MASK) == _PMD_PAGE_8M);
#else
/* We clear the top bit to indicate hugepd */
return (hpd_val(hpd) && (hpd_val(hpd) & PD_HUGE) == 0);
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index adad8baadcf5..423465b10c82 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -239,7 +239,6 @@ InstructionTLBMiss:
#endif
#ifdef CONFIG_HUGETLBFS
lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */
- mtspr SPRN_MI_TWC, r11 /* Set segment attributes */
mtspr SPRN_MD_TWC, r11
#else
lwz r10, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */
@@ -248,6 +247,10 @@ InstructionTLBMiss:
#endif
mfspr r10, SPRN_MD_TWC
lwz r10, 0(r10) /* Get the pte */
+#ifdef CONFIG_HUGETLBFS
+ rlwimi r11, r10, 32 - 9, _PMD_PAGE_512K
+ mtspr SPRN_MI_TWC, r11
+#endif
#ifdef CONFIG_SWAP
rlwinm r11, r10, 32-5, _PAGE_PRESENT
and r11, r11, r10
@@ -353,6 +356,7 @@ DataStoreTLBMiss:
* above.
*/
rlwimi r11, r10, 0, _PAGE_GUARDED
+ rlwimi r11, r10, 32 - 9, _PMD_PAGE_512K
mtspr SPRN_MD_TWC, r11
/* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set.
@@ -584,7 +588,6 @@ FixupDAR:/* Entry point for dcbx workaround. */
mfspr r11, SPRN_MD_TWC
lwz r11, 0(r11) /* Get the pte */
bt 28,200f /* bit 28 = Large page (8M) */
- bt 29,202f /* bit 29 = Large page (8M or 512K) */
/* concat physical page address(r11) and page offset(r10) */
rlwimi r11, r10, 0, 32 - PAGE_SHIFT, 31
201: lwz r11,0(r11)
@@ -611,11 +614,6 @@ FixupDAR:/* Entry point for dcbx workaround. */
rlwimi r11, r10, 0, 32 - PAGE_SHIFT_8M, 31
b 201b
-202:
- /* concat physical page address(r11) and page offset(r10) */
- rlwimi r11, r10, 0, 32 - PAGE_SHIFT_512K, 31
- b 201b
-
144: mfspr r10, SPRN_DSISR
rlwinm r10, r10,0,7,5 /* Clear store bit for buggy dcbst insn */
mtspr SPRN_DSISR, r10
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index edf511c2a30a..35eb29584b54 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -189,6 +189,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz
if (!hpdp)
return NULL;
+ if (IS_ENABLED(CONFIG_PPC_8xx) && sz == SZ_512K)
+ return pte_alloc_map(mm, (pmd_t *)hpdp, addr);
+
BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp));
if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr,
@@ -331,13 +334,20 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif
if (shift >= pdshift)
hugepd_free(tlb, hugepte);
- else if (IS_ENABLED(CONFIG_PPC_8xx))
- pgtable_free_tlb(tlb, hugepte, 0);
else
pgtable_free_tlb(tlb, hugepte,
get_hugepd_cache_index(pdshift - shift));
}
+static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr)
+{
+ pgtable_t token = pmd_pgtable(*pmd);
+
+ pmd_clear(pmd);
+ pte_free_tlb(tlb, token, addr);
+ mm_dec_nr_ptes(tlb->mm);
+}
+
static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
@@ -353,11 +363,17 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
pmd = pmd_offset(pud, addr);
next = pmd_addr_end(addr, end);
if (!is_hugepd(__hugepd(pmd_val(*pmd)))) {
+ if (pmd_none_or_clear_bad(pmd))
+ continue;
+
/*
* if it is not hugepd pointer, we should already find
* it cleared.
*/
- WARN_ON(!pmd_none_or_clear_bad(pmd));
+ WARN_ON(!IS_ENABLED(CONFIG_PPC_8xx));
+
+ hugetlb_free_pte_range(tlb, pmd, addr);
+
continue;
}
/*
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 214a5f4beb6c..60c4b8ff046c 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -264,6 +264,12 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
#if defined(CONFIG_PPC_8xx)
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
{
+ pmd_t *pmd = pmd_ptr(mm, addr);
+ pte_basic_t val;
+ pte_basic_t *entry = &ptep->pte;
+ int num = is_hugepd(*((hugepd_t *)pmd)) ? 1 : SZ_512K / SZ_4K;
+ int i;
+
/*
* Make sure hardware valid bit is not set. We don't do
* tlb flush for this update.
@@ -274,7 +280,9 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_
pte = set_pte_filter(pte);
- ptep->pte = pte_val(pte);
+ val = pte_val(pte);
+ for (i = 0; i < num; i++, entry++, val += SZ_4K)
+ *entry = val;
}
#endif
#endif /* CONFIG_HUGETLB_PAGE */
--
2.25.0
^ permalink raw reply related
* [PATCH v3 25/45] powerpc/8xx: Prepare handlers for _PAGE_HUGE for 512k pages.
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
Prepare ITLB handler to handle _PAGE_HUGE when CONFIG_HUGETLBFS
is enabled. This means that the L1 entry has to be kept in r11
until L2 entry is read, in order to insert _PAGE_HUGE into it.
Also move pgd_offset helpers before pte_update() as they
will be needed there in next patch.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/nohash/32/pgtable.h | 13 ++++++-------
arch/powerpc/kernel/head_8xx.S | 15 +++++++++------
2 files changed, 15 insertions(+), 13 deletions(-)
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index dd5835354e33..1a86d20b58f3 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -206,6 +206,12 @@ static inline void pmd_clear(pmd_t *pmdp)
}
+/* to find an entry in a kernel page-table-directory */
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+/* to find an entry in a page-table-directory */
+#define pgd_index(address) ((address) >> PGDIR_SHIFT)
+#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address))
/*
* PTE updates. This function is called whenever an existing
@@ -348,13 +354,6 @@ static inline int pte_young(pte_t pte)
pfn_to_page((__pa(pmd_val(pmd)) >> PAGE_SHIFT))
#endif
-/* to find an entry in a kernel page-table-directory */
-#define pgd_offset_k(address) pgd_offset(&init_mm, address)
-
-/* to find an entry in a page-table-directory */
-#define pgd_index(address) ((address) >> PGDIR_SHIFT)
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address))
-
/* Find an entry in the third-level page table.. */
#define pte_index(address) \
(((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 905205c79a25..adad8baadcf5 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -196,7 +196,7 @@ SystemCall:
InstructionTLBMiss:
mtspr SPRN_SPRG_SCRATCH0, r10
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP)
+#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) || defined(CONFIG_HUGETLBFS)
mtspr SPRN_SPRG_SCRATCH1, r11
#endif
@@ -235,16 +235,19 @@ InstructionTLBMiss:
rlwinm r10, r10, 0, 20, 31
oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
3:
+ mtcr r11
#endif
+#ifdef CONFIG_HUGETLBFS
+ lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */
+ mtspr SPRN_MI_TWC, r11 /* Set segment attributes */
+ mtspr SPRN_MD_TWC, r11
+#else
lwz r10, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */
mtspr SPRN_MI_TWC, r10 /* Set segment attributes */
-
mtspr SPRN_MD_TWC, r10
+#endif
mfspr r10, SPRN_MD_TWC
lwz r10, 0(r10) /* Get the pte */
-#ifdef ITLB_MISS_KERNEL
- mtcr r11
-#endif
#ifdef CONFIG_SWAP
rlwinm r11, r10, 32-5, _PAGE_PRESENT
and r11, r11, r10
@@ -263,7 +266,7 @@ InstructionTLBMiss:
/* Restore registers */
0: mfspr r10, SPRN_SPRG_SCRATCH0
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP)
+#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) || defined(CONFIG_HUGETLBFS)
mfspr r11, SPRN_SPRG_SCRATCH1
#endif
rfi
--
2.25.0
^ permalink raw reply related
* [PATCH v3 24/45] powerpc/8xx: Drop CONFIG_8xx_COPYBACK option
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
CONFIG_8xx_COPYBACK was there to help disabling copyback cache mode
for debuging hardware. But nobody will design new boards with 8xx now.
All 8xx platforms select it, so make it the default and remove
the option.
Also remove the Mx_RESETVAL values which are pretty useless and hide
the real value while reading code.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/configs/adder875_defconfig | 1 -
arch/powerpc/configs/ep88xc_defconfig | 1 -
arch/powerpc/configs/mpc866_ads_defconfig | 1 -
arch/powerpc/configs/mpc885_ads_defconfig | 1 -
arch/powerpc/configs/tqm8xx_defconfig | 1 -
arch/powerpc/include/asm/nohash/32/mmu-8xx.h | 2 --
arch/powerpc/kernel/head_8xx.S | 15 +--------------
arch/powerpc/platforms/8xx/Kconfig | 9 ---------
8 files changed, 1 insertion(+), 30 deletions(-)
diff --git a/arch/powerpc/configs/adder875_defconfig b/arch/powerpc/configs/adder875_defconfig
index f55e23cb176c..5326bc739279 100644
--- a/arch/powerpc/configs/adder875_defconfig
+++ b/arch/powerpc/configs/adder875_defconfig
@@ -10,7 +10,6 @@ CONFIG_EXPERT=y
# CONFIG_BLK_DEV_BSG is not set
CONFIG_PARTITION_ADVANCED=y
CONFIG_PPC_ADDER875=y
-CONFIG_8xx_COPYBACK=y
CONFIG_GEN_RTC=y
CONFIG_HZ_1000=y
# CONFIG_SECCOMP is not set
diff --git a/arch/powerpc/configs/ep88xc_defconfig b/arch/powerpc/configs/ep88xc_defconfig
index 0e2e5e81a359..f5c3e72da719 100644
--- a/arch/powerpc/configs/ep88xc_defconfig
+++ b/arch/powerpc/configs/ep88xc_defconfig
@@ -12,7 +12,6 @@ CONFIG_EXPERT=y
# CONFIG_BLK_DEV_BSG is not set
CONFIG_PARTITION_ADVANCED=y
CONFIG_PPC_EP88XC=y
-CONFIG_8xx_COPYBACK=y
CONFIG_GEN_RTC=y
CONFIG_HZ_100=y
# CONFIG_SECCOMP is not set
diff --git a/arch/powerpc/configs/mpc866_ads_defconfig b/arch/powerpc/configs/mpc866_ads_defconfig
index 5320735395e7..5c56d36cdfc5 100644
--- a/arch/powerpc/configs/mpc866_ads_defconfig
+++ b/arch/powerpc/configs/mpc866_ads_defconfig
@@ -12,7 +12,6 @@ CONFIG_EXPERT=y
# CONFIG_BLK_DEV_BSG is not set
CONFIG_PARTITION_ADVANCED=y
CONFIG_MPC86XADS=y
-CONFIG_8xx_COPYBACK=y
CONFIG_GEN_RTC=y
CONFIG_HZ_1000=y
CONFIG_MATH_EMULATION=y
diff --git a/arch/powerpc/configs/mpc885_ads_defconfig b/arch/powerpc/configs/mpc885_ads_defconfig
index 82a008c04eae..949ff9ccda5e 100644
--- a/arch/powerpc/configs/mpc885_ads_defconfig
+++ b/arch/powerpc/configs/mpc885_ads_defconfig
@@ -11,7 +11,6 @@ CONFIG_EXPERT=y
# CONFIG_VM_EVENT_COUNTERS is not set
# CONFIG_BLK_DEV_BSG is not set
CONFIG_PARTITION_ADVANCED=y
-CONFIG_8xx_COPYBACK=y
CONFIG_GEN_RTC=y
CONFIG_HZ_100=y
# CONFIG_SECCOMP is not set
diff --git a/arch/powerpc/configs/tqm8xx_defconfig b/arch/powerpc/configs/tqm8xx_defconfig
index eda8bfb2d0a3..77857d513022 100644
--- a/arch/powerpc/configs/tqm8xx_defconfig
+++ b/arch/powerpc/configs/tqm8xx_defconfig
@@ -15,7 +15,6 @@ CONFIG_MODULE_SRCVERSION_ALL=y
# CONFIG_BLK_DEV_BSG is not set
CONFIG_PARTITION_ADVANCED=y
CONFIG_TQM8XX=y
-CONFIG_8xx_COPYBACK=y
# CONFIG_8xx_CPU15 is not set
CONFIG_GEN_RTC=y
CONFIG_HZ_100=y
diff --git a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
index 76af5b0cb16e..26b7cee34dfe 100644
--- a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
@@ -19,7 +19,6 @@
#define MI_RSV4I 0x08000000 /* Reserve 4 TLB entries */
#define MI_PPCS 0x02000000 /* Use MI_RPN prob/priv state */
#define MI_IDXMASK 0x00001f00 /* TLB index to be loaded */
-#define MI_RESETVAL 0x00000000 /* Value of register at reset */
/* These are the Ks and Kp from the PowerPC books. For proper operation,
* Ks = 0, Kp = 1.
@@ -95,7 +94,6 @@
#define MD_TWAM 0x04000000 /* Use 4K page hardware assist */
#define MD_PPCS 0x02000000 /* Use MI_RPN prob/priv state */
#define MD_IDXMASK 0x00001f00 /* TLB index to be loaded */
-#define MD_RESETVAL 0x04000000 /* Value of register at reset */
#define SPRN_M_CASID 793 /* Address space ID (context) to match */
#define MC_ASIDMASK 0x0000000f /* Bits used for ASID value */
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 073a651787df..905205c79a25 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -779,10 +779,7 @@ start_here:
initial_mmu:
li r8, 0
mtspr SPRN_MI_CTR, r8 /* remove PINNED ITLB entries */
- lis r10, MD_RESETVAL@h
-#ifndef CONFIG_8xx_COPYBACK
- oris r10, r10, MD_WTDEF@h
-#endif
+ lis r10, MD_TWAM@h
mtspr SPRN_MD_CTR, r10 /* remove PINNED DTLB entries */
tlbia /* Invalidate all TLB entries */
@@ -857,17 +854,7 @@ initial_mmu:
mtspr SPRN_DC_CST, r8
lis r8, IDC_ENABLE@h
mtspr SPRN_IC_CST, r8
-#ifdef CONFIG_8xx_COPYBACK
- mtspr SPRN_DC_CST, r8
-#else
- /* For a debug option, I left this here to easily enable
- * the write through cache mode
- */
- lis r8, DC_SFWT@h
mtspr SPRN_DC_CST, r8
- lis r8, IDC_ENABLE@h
- mtspr SPRN_DC_CST, r8
-#endif
/* Disable debug mode entry on breakpoints */
mfspr r8, SPRN_DER
#ifdef CONFIG_PERF_EVENTS
diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig
index e0fe670f06f6..b37de62d7e7f 100644
--- a/arch/powerpc/platforms/8xx/Kconfig
+++ b/arch/powerpc/platforms/8xx/Kconfig
@@ -98,15 +98,6 @@ menu "MPC8xx CPM Options"
# 8xx specific questions.
comment "Generic MPC8xx Options"
-config 8xx_COPYBACK
- bool "Copy-Back Data Cache (else Writethrough)"
- help
- Saying Y here will cause the cache on an MPC8xx processor to be used
- in Copy-Back mode. If you say N here, it is used in Writethrough
- mode.
-
- If in doubt, say Y here.
-
config 8xx_GPIO
bool "GPIO API Support"
select GPIOLIB
--
2.25.0
^ permalink raw reply related
* [PATCH v3 23/45] powerpc/mm: Reduce hugepd size for 8M hugepages on 8xx
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
Commit 55c8fc3f4930 ("powerpc/8xx: reintroduce 16K pages with HW
assistance") redefined pte_t as a struct of 4 pte_basic_t, because
in 16K pages mode there are four identical entries in the page table.
But hugepd entries for 8M pages require only one entry of size
pte_basic_t. So there is no point in creating a cache for 4 entries
page tables.
Calculate PTE_T_ORDER using the size of pte_basic_t instead of pte_t.
Define specific huge_pte helpers (set_huge_pte_at(), huge_pte_clear(),
huge_ptep_set_wrprotect()) to write the pte in a single entry instead
of using set_pte_at() which writes 4 identical entries in 16k pages
mode. Also make sure that __ptep_set_access_flags() properly handle
the huge_pte case.
Define set_pte_filter() inline otherwise GCC doesn't inline it anymore
because it is now used twice, and that gives a pretty suboptimal code
because of pte_t being a struct of 4 entries.
Those functions are also used for 512k pages which only require one
entry as well allthough replicating it four times was harmless as 512k
pages entries are spread every 128 bytes in the table.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
.../include/asm/nohash/32/hugetlb-8xx.h | 20 ++++++++++++++
arch/powerpc/include/asm/nohash/32/pgtable.h | 3 ++-
arch/powerpc/mm/hugetlbpage.c | 3 ++-
arch/powerpc/mm/pgtable.c | 26 ++++++++++++++++---
4 files changed, 46 insertions(+), 6 deletions(-)
diff --git a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
index a46616937d20..785437323576 100644
--- a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
@@ -41,4 +41,24 @@ static inline int check_and_get_huge_psize(int shift)
return shift_to_mmu_psize(shift);
}
+#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte);
+
+#define __HAVE_ARCH_HUGE_PTE_CLEAR
+static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, unsigned long sz)
+{
+ pte_update(mm, addr, ptep, ~0UL, 0, 1);
+}
+
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
+{
+ unsigned long clr = ~pte_val(pte_wrprotect(__pte(~0)));
+ unsigned long set = pte_val(pte_wrprotect(__pte(0)));
+
+ pte_update(mm, addr, ptep, clr, set, 1);
+}
+
#endif /* _ASM_POWERPC_NOHASH_32_HUGETLB_8XX_H */
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 272963a05ab2..dd5835354e33 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -314,8 +314,9 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
pte_t pte_clr = pte_mkyoung(pte_mkdirty(pte_mkwrite(pte_mkexec(__pte(~0)))));
unsigned long set = pte_val(entry) & pte_val(pte_set);
unsigned long clr = ~pte_val(entry) & ~pte_val(pte_clr);
+ int huge = psize > mmu_virtual_psize ? 1 : 0;
- pte_update(vma->vm_mm, address, ptep, clr, set, 0);
+ pte_update(vma->vm_mm, address, ptep, clr, set, huge);
flush_tlb_page(vma, address);
}
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 33b3461d91e8..edf511c2a30a 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -30,7 +30,8 @@ bool hugetlb_disabled = false;
#define hugepd_none(hpd) (hpd_val(hpd) == 0)
-#define PTE_T_ORDER (__builtin_ffs(sizeof(pte_t)) - __builtin_ffs(sizeof(void *)))
+#define PTE_T_ORDER (__builtin_ffs(sizeof(pte_basic_t)) - \
+ __builtin_ffs(sizeof(void *)))
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz)
{
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index e3759b69f81b..214a5f4beb6c 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -100,7 +100,7 @@ static pte_t set_pte_filter_hash(pte_t pte) { return pte; }
* as we don't have two bits to spare for _PAGE_EXEC and _PAGE_HWEXEC so
* instead we "filter out" the exec permission for non clean pages.
*/
-static pte_t set_pte_filter(pte_t pte)
+static inline pte_t set_pte_filter(pte_t pte)
{
struct page *pg;
@@ -249,16 +249,34 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
#else
/*
- * Not used on non book3s64 platforms. But 8xx
- * can possibly use tsize derived from hstate.
+ * Not used on non book3s64 platforms.
+ * 8xx compares it with mmu_virtual_psize to
+ * know if it is a huge page or not.
*/
- psize = 0;
+ psize = MMU_PAGE_COUNT;
#endif
__ptep_set_access_flags(vma, ptep, pte, addr, psize);
}
return changed;
#endif
}
+
+#if defined(CONFIG_PPC_8xx)
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
+{
+ /*
+ * Make sure hardware valid bit is not set. We don't do
+ * tlb flush for this update.
+ */
+ VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
+
+ pte = pte_mkpte(pte);
+
+ pte = set_pte_filter(pte);
+
+ ptep->pte = pte_val(pte);
+}
+#endif
#endif /* CONFIG_HUGETLB_PAGE */
#ifdef CONFIG_DEBUG_VM
--
2.25.0
^ permalink raw reply related
* [PATCH v3 22/45] powerpc/mm: Create a dedicated pte_update() for 8xx
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
pte_update() is a bit special for the 8xx. At the time
being, that's an #ifdef inside the nohash/32 pte_update().
As we are going to make it even more special in the coming
patches, create a dedicated version for pte_update() for 8xx.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/nohash/32/pgtable.h | 29 +++++++++++++++++---
1 file changed, 25 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 75880eb1cb91..272963a05ab2 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -221,7 +221,31 @@ static inline void pmd_clear(pmd_t *pmdp)
* that an executable user mapping was modified, which is needed
* to properly flush the virtually tagged instruction cache of
* those implementations.
+ *
+ * On the 8xx, the page tables are a bit special. For 16k pages, we have
+ * 4 identical entries. For other page sizes, we have a single entry in the
+ * table.
*/
+#ifdef CONFIG_PPC_8xx
+static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
+ unsigned long clr, unsigned long set, int huge)
+{
+ pte_basic_t *entry = &p->pte;
+ pte_basic_t old = pte_val(*p);
+ pte_basic_t new = (old & ~(pte_basic_t)clr) | set;
+ int num, i;
+
+ if (!huge)
+ num = PAGE_SIZE / SZ_4K;
+ else
+ num = 1;
+
+ for (i = 0; i < num; i++, entry++)
+ *entry = new;
+
+ return old;
+}
+#else
static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
unsigned long clr, unsigned long set, int huge)
{
@@ -242,11 +266,7 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p
pte_basic_t old = pte_val(*p);
pte_basic_t new = (old & ~(pte_basic_t)clr) | set;
-#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES)
- p->pte = p->pte1 = p->pte2 = p->pte3 = new;
-#else
*p = __pte(new);
-#endif
#endif /* !PTE_ATOMIC_UPDATES */
#ifdef CONFIG_44x
@@ -255,6 +275,7 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p
#endif
return old;
}
+#endif
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
--
2.25.0
^ permalink raw reply related
* [PATCH v3 21/45] powerpc/mm: Standardise pte_update() prototype between PPC32 and PPC64
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
PPC64 takes 3 additional parameters compared to PPC32:
- mm
- address
- huge
These 3 parameters will be needed in order to perform different
action depending on the page size on the 8xx.
Make pte_update() prototype identical for PPC32 and PPC64.
This allows dropping an #ifdef in huge_ptep_get_and_clear().
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/book3s/32/pgtable.h | 15 ++++++++-------
arch/powerpc/include/asm/hugetlb.h | 4 ----
arch/powerpc/include/asm/nohash/32/pgtable.h | 13 +++++++------
3 files changed, 15 insertions(+), 17 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 8122f0b55d21..f5eab98c4e41 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -218,7 +218,7 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
*/
#define pte_clear(mm, addr, ptep) \
- do { pte_update(ptep, ~_PAGE_HASHPTE, 0); } while (0)
+ do { pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, 0, 0); } while (0)
#define pmd_none(pmd) (!pmd_val(pmd))
#define pmd_bad(pmd) (pmd_val(pmd) & _PMD_BAD)
@@ -254,7 +254,8 @@ extern void flush_hash_entry(struct mm_struct *mm, pte_t *ptep,
* when using atomic updates, only the low part of the PTE is
* accessed atomically.
*/
-static inline pte_basic_t pte_update(pte_t *p, unsigned long clr, unsigned long set)
+static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
+ unsigned long clr, unsigned long set, int huge)
{
pte_basic_t old;
unsigned long tmp;
@@ -292,7 +293,7 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
unsigned long old;
- old = pte_update(ptep, _PAGE_ACCESSED, 0);
+ old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
if (old & _PAGE_HASHPTE) {
unsigned long ptephys = __pa(ptep) & PAGE_MASK;
flush_hash_pages(mm->context.id, addr, ptephys, 1);
@@ -306,14 +307,14 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
- return __pte(pte_update(ptep, ~_PAGE_HASHPTE, 0));
+ return __pte(pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, 0, 0));
}
#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
- pte_update(ptep, _PAGE_RW, 0);
+ pte_update(mm, addr, ptep, _PAGE_RW, 0, 0);
}
static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
@@ -324,7 +325,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long set = pte_val(entry) &
(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
- pte_update(ptep, 0, set);
+ pte_update(vma->vm_mm, address, ptep, 0, set, 0);
flush_tlb_page(vma, address);
}
@@ -522,7 +523,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
| (pte_val(pte) & ~_PAGE_HASHPTE));
else
- pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte));
+ pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, pte_val(pte), 0);
#elif defined(CONFIG_PTE_64BIT)
/* Second case is 32-bit with 64-bit PTE. In this case, we
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index bd6504c28c2f..e4276af034e9 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -40,11 +40,7 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
-#ifdef CONFIG_PPC64
return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1));
-#else
- return __pte(pte_update(ptep, ~0UL, 0));
-#endif
}
#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index ddf681ceb860..75880eb1cb91 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -166,7 +166,7 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
#ifndef __ASSEMBLY__
#define pte_clear(mm, addr, ptep) \
- do { pte_update(ptep, ~0, 0); } while (0)
+ do { pte_update(mm, addr, ptep, ~0, 0, 0); } while (0)
#ifndef pte_mkwrite
static inline pte_t pte_mkwrite(pte_t pte)
@@ -222,7 +222,8 @@ static inline void pmd_clear(pmd_t *pmdp)
* to properly flush the virtually tagged instruction cache of
* those implementations.
*/
-static inline pte_basic_t pte_update(pte_t *p, unsigned long clr, unsigned long set)
+static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
+ unsigned long clr, unsigned long set, int huge)
{
#if defined(PTE_ATOMIC_UPDATES) && !defined(CONFIG_PTE_64BIT)
unsigned long old, tmp;
@@ -260,7 +261,7 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
unsigned long old;
- old = pte_update(ptep, _PAGE_ACCESSED, 0);
+ old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
return (old & _PAGE_ACCESSED) != 0;
}
#define ptep_test_and_clear_young(__vma, __addr, __ptep) \
@@ -270,7 +271,7 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
- return __pte(pte_update(ptep, ~0, 0));
+ return __pte(pte_update(mm, addr, ptep, ~0, 0, 0));
}
#define __HAVE_ARCH_PTEP_SET_WRPROTECT
@@ -280,7 +281,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
unsigned long clr = ~pte_val(pte_wrprotect(__pte(~0)));
unsigned long set = pte_val(pte_wrprotect(__pte(0)));
- pte_update(ptep, clr, set);
+ pte_update(mm, addr, ptep, clr, set, 0);
}
static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
@@ -293,7 +294,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long set = pte_val(entry) & pte_val(pte_set);
unsigned long clr = ~pte_val(entry) & ~pte_val(pte_clr);
- pte_update(ptep, clr, set);
+ pte_update(vma->vm_mm, address, ptep, clr, set, 0);
flush_tlb_page(vma, address);
}
--
2.25.0
^ permalink raw reply related
* [PATCH v3 20/45] powerpc/mm: Standardise __ptep_test_and_clear_young() params between PPC32 and PPC64
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
On PPC32, __ptep_test_and_clear_young() takes the mm->context.id
In preparation of standardising pte_update() params between PPC32 and
PPC64, __ptep_test_and_clear_young() need mm instead of mm->context.id
Replace context param by mm.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/book3s/32/pgtable.h | 7 ++++---
arch/powerpc/include/asm/nohash/32/pgtable.h | 5 +++--
2 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index d1108d25e2e5..8122f0b55d21 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -288,18 +288,19 @@ static inline pte_basic_t pte_update(pte_t *p, unsigned long clr, unsigned long
* for our hash-based implementation, we fix that up here.
*/
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-static inline int __ptep_test_and_clear_young(unsigned int context, unsigned long addr, pte_t *ptep)
+static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
{
unsigned long old;
old = pte_update(ptep, _PAGE_ACCESSED, 0);
if (old & _PAGE_HASHPTE) {
unsigned long ptephys = __pa(ptep) & PAGE_MASK;
- flush_hash_pages(context, addr, ptephys, 1);
+ flush_hash_pages(mm->context.id, addr, ptephys, 1);
}
return (old & _PAGE_ACCESSED) != 0;
}
#define ptep_test_and_clear_young(__vma, __addr, __ptep) \
- __ptep_test_and_clear_young((__vma)->vm_mm->context.id, __addr, __ptep)
+ __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep)
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 9eaf386a747b..ddf681ceb860 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -256,14 +256,15 @@ static inline pte_basic_t pte_update(pte_t *p, unsigned long clr, unsigned long
}
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-static inline int __ptep_test_and_clear_young(unsigned int context, unsigned long addr, pte_t *ptep)
+static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
{
unsigned long old;
old = pte_update(ptep, _PAGE_ACCESSED, 0);
return (old & _PAGE_ACCESSED) != 0;
}
#define ptep_test_and_clear_young(__vma, __addr, __ptep) \
- __ptep_test_and_clear_young((__vma)->vm_mm->context.id, __addr, __ptep)
+ __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep)
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
--
2.25.0
^ permalink raw reply related
* [PATCH v3 19/45] powerpc/mm: Refactor pte_update() on book3s/32
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
When CONFIG_PTE_64BIT is set, pte_update() operates on
'unsigned long long'
When CONFIG_PTE_64BIT is not set, pte_update() operates on
'unsigned long'
In asm/page.h, we have pte_basic_t which is 'unsigned long long'
when CONFIG_PTE_64BIT is set and 'unsigned long' otherwise.
Refactor pte_update() using pte_basic_t.
While we are at it, drop the comment on 44x which is not applicable
to book3s version of pte_update().
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/book3s/32/pgtable.h | 58 +++++++-------------
1 file changed, 20 insertions(+), 38 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 7549393c4c43..d1108d25e2e5 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -253,53 +253,35 @@ extern void flush_hash_entry(struct mm_struct *mm, pte_t *ptep,
* and the PTE may be either 32 or 64 bit wide. In the later case,
* when using atomic updates, only the low part of the PTE is
* accessed atomically.
- *
- * In addition, on 44x, we also maintain a global flag indicating
- * that an executable user mapping was modified, which is needed
- * to properly flush the virtually tagged instruction cache of
- * those implementations.
*/
-#ifndef CONFIG_PTE_64BIT
-static inline unsigned long pte_update(pte_t *p,
- unsigned long clr,
- unsigned long set)
+static inline pte_basic_t pte_update(pte_t *p, unsigned long clr, unsigned long set)
{
- unsigned long old, tmp;
-
- __asm__ __volatile__("\
-1: lwarx %0,0,%3\n\
- andc %1,%0,%4\n\
- or %1,%1,%5\n"
-" stwcx. %1,0,%3\n\
- bne- 1b"
- : "=&r" (old), "=&r" (tmp), "=m" (*p)
- : "r" (p), "r" (clr), "r" (set), "m" (*p)
- : "cc" );
-
- return old;
-}
-#else /* CONFIG_PTE_64BIT */
-static inline unsigned long long pte_update(pte_t *p,
- unsigned long clr,
- unsigned long set)
-{
- unsigned long long old;
+ pte_basic_t old;
unsigned long tmp;
- __asm__ __volatile__("\
-1: lwarx %L0,0,%4\n\
- lwzx %0,0,%3\n\
- andc %1,%L0,%5\n\
- or %1,%1,%6\n"
-" stwcx. %1,0,%4\n\
- bne- 1b"
+ __asm__ __volatile__(
+#ifndef CONFIG_PTE_64BIT
+"1: lwarx %0, 0, %3\n"
+" andc %1, %0, %4\n"
+#else
+"1: lwarx %L0, 0, %3\n"
+" lwz %0, -4(%3)\n"
+" andc %1, %L0, %4\n"
+#endif
+" or %1, %1, %5\n"
+" stwcx. %1, 0, %3\n"
+" bne- 1b"
: "=&r" (old), "=&r" (tmp), "=m" (*p)
- : "r" (p), "r" ((unsigned long)(p) + 4), "r" (clr), "r" (set), "m" (*p)
+#ifndef CONFIG_PTE_64BIT
+ : "r" (p),
+#else
+ : "b" ((unsigned long)(p) + 4),
+#endif
+ "r" (clr), "r" (set), "m" (*p)
: "cc" );
return old;
}
-#endif /* CONFIG_PTE_64BIT */
/*
* 2.6 calls this without flushing the TLB entry; this is wrong
--
2.25.0
^ permalink raw reply related
* [PATCH v3 18/45] powerpc/mm: Refactor pte_update() on nohash/32
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
When CONFIG_PTE_64BIT is set, pte_update() operates on
'unsigned long long'
When CONFIG_PTE_64BIT is not set, pte_update() operates on
'unsigned long'
In asm/page.h, we have pte_basic_t which is 'unsigned long long'
when CONFIG_PTE_64BIT is set and 'unsigned long' otherwise.
Refactor pte_update() using pte_basic_t.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/nohash/32/pgtable.h | 26 +++-----------------
1 file changed, 4 insertions(+), 22 deletions(-)
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 523c4c3876c5..9eaf386a747b 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -222,12 +222,9 @@ static inline void pmd_clear(pmd_t *pmdp)
* to properly flush the virtually tagged instruction cache of
* those implementations.
*/
-#ifndef CONFIG_PTE_64BIT
-static inline unsigned long pte_update(pte_t *p,
- unsigned long clr,
- unsigned long set)
+static inline pte_basic_t pte_update(pte_t *p, unsigned long clr, unsigned long set)
{
-#ifdef PTE_ATOMIC_UPDATES
+#if defined(PTE_ATOMIC_UPDATES) && !defined(CONFIG_PTE_64BIT)
unsigned long old, tmp;
__asm__ __volatile__("\
@@ -241,8 +238,8 @@ static inline unsigned long pte_update(pte_t *p,
: "r" (p), "r" (clr), "r" (set), "m" (*p)
: "cc" );
#else /* PTE_ATOMIC_UPDATES */
- unsigned long old = pte_val(*p);
- unsigned long new = (old & ~clr) | set;
+ pte_basic_t old = pte_val(*p);
+ pte_basic_t new = (old & ~(pte_basic_t)clr) | set;
#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES)
p->pte = p->pte1 = p->pte2 = p->pte3 = new;
@@ -257,21 +254,6 @@ static inline unsigned long pte_update(pte_t *p,
#endif
return old;
}
-#else /* CONFIG_PTE_64BIT */
-static inline unsigned long long pte_update(pte_t *p,
- unsigned long clr,
- unsigned long set)
-{
- unsigned long long old = pte_val(*p);
- *p = __pte((old & ~(unsigned long long)clr) | set);
-
-#ifdef CONFIG_44x
- if ((old & _PAGE_USER) && (old & _PAGE_EXEC))
- icache_44x_need_flush = 1;
-#endif
- return old;
-}
-#endif /* CONFIG_PTE_64BIT */
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
static inline int __ptep_test_and_clear_young(unsigned int context, unsigned long addr, pte_t *ptep)
--
2.25.0
^ permalink raw reply related
* [PATCH v3 17/45] powerpc/mm: PTE_ATOMIC_UPDATES is only for 40x
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
Only 40x still uses PTE_ATOMIC_UPDATES.
40x cannot not select CONFIG_PTE64_BIT.
Drop handling of PTE_ATOMIC_UPDATES:
- In nohash/64
- In nohash/32 for CONFIG_PTE_64BIT
Keep PTE_ATOMIC_UPDATES only for nohash/32 for !CONFIG_PTE_64BIT
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/nohash/32/pgtable.h | 17 ------------
arch/powerpc/include/asm/nohash/64/pgtable.h | 28 +-------------------
2 files changed, 1 insertion(+), 44 deletions(-)
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index b04ba257fddb..523c4c3876c5 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -262,25 +262,8 @@ static inline unsigned long long pte_update(pte_t *p,
unsigned long clr,
unsigned long set)
{
-#ifdef PTE_ATOMIC_UPDATES
- unsigned long long old;
- unsigned long tmp;
-
- __asm__ __volatile__("\
-1: lwarx %L0,0,%4\n\
- lwzx %0,0,%3\n\
- andc %1,%L0,%5\n\
- or %1,%1,%6\n"
- PPC405_ERR77(0,%3)
-" stwcx. %1,0,%4\n\
- bne- 1b"
- : "=&r" (old), "=&r" (tmp), "=m" (*p)
- : "r" (p), "r" ((unsigned long)(p) + 4), "r" (clr), "r" (set), "m" (*p)
- : "cc" );
-#else /* PTE_ATOMIC_UPDATES */
unsigned long long old = pte_val(*p);
*p = __pte((old & ~(unsigned long long)clr) | set);
-#endif /* !PTE_ATOMIC_UPDATES */
#ifdef CONFIG_44x
if ((old & _PAGE_USER) && (old & _PAGE_EXEC))
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index 9a33b8bd842d..9c703b140d64 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -211,22 +211,9 @@ static inline unsigned long pte_update(struct mm_struct *mm,
unsigned long set,
int huge)
{
-#ifdef PTE_ATOMIC_UPDATES
- unsigned long old, tmp;
-
- __asm__ __volatile__(
- "1: ldarx %0,0,%3 # pte_update\n\
- andc %1,%0,%4 \n\
- or %1,%1,%6\n\
- stdcx. %1,0,%3 \n\
- bne- 1b"
- : "=&r" (old), "=&r" (tmp), "=m" (*ptep)
- : "r" (ptep), "r" (clr), "m" (*ptep), "r" (set)
- : "cc" );
-#else
unsigned long old = pte_val(*ptep);
*ptep = __pte((old & ~clr) | set);
-#endif
+
/* huge pages use the old page table lock */
if (!huge)
assert_pte_locked(mm, addr);
@@ -310,21 +297,8 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long bits = pte_val(entry) &
(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
-#ifdef PTE_ATOMIC_UPDATES
- unsigned long old, tmp;
-
- __asm__ __volatile__(
- "1: ldarx %0,0,%4\n\
- or %0,%3,%0\n\
- stdcx. %0,0,%4\n\
- bne- 1b"
- :"=&r" (old), "=&r" (tmp), "=m" (*ptep)
- :"r" (bits), "r" (ptep), "m" (*ptep)
- :"cc");
-#else
unsigned long old = pte_val(*ptep);
*ptep = __pte(old | bits);
-#endif
flush_tlb_page(vma, address);
}
--
2.25.0
^ permalink raw reply related
* [PATCH v3 16/45] powerpc/mm: Fix conditions to perform MMU specific management by blocks on PPC32.
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
Setting init mem to NX shall depend on sinittext being mapped by
block, not on stext being mapped by block.
Setting text and rodata to RO shall depend on stext being mapped by
block, not on sinittext being mapped by block.
Fixes: 63b2bc619565 ("powerpc/mm/32s: Use BATs for STRICT_KERNEL_RWX")
Cc: stable@vger.kernel.org
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/mm/pgtable_32.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 9934659cb871..bd0cb6e3573e 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -185,7 +185,7 @@ void mark_initmem_nx(void)
unsigned long numpages = PFN_UP((unsigned long)_einittext) -
PFN_DOWN((unsigned long)_sinittext);
- if (v_block_mapped((unsigned long)_stext + 1))
+ if (v_block_mapped((unsigned long)_sinittext))
mmu_mark_initmem_nx();
else
change_page_attr(page, numpages, PAGE_KERNEL);
@@ -197,7 +197,7 @@ void mark_rodata_ro(void)
struct page *page;
unsigned long numpages;
- if (v_block_mapped((unsigned long)_sinittext)) {
+ if (v_block_mapped((unsigned long)_stext + 1)) {
mmu_mark_rodata_ro();
ptdump_check_wx();
return;
--
2.25.0
^ permalink raw reply related
* [PATCH v3 15/45] powerpc/mm: Allocate static page tables for fixmap
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
Allocate static page tables for the fixmap area. This allows
setting mappings through page tables before memblock is ready.
That's needed to use early_ioremap() early and to use standard
page mappings with fixmap.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/fixmap.h | 4 ++++
arch/powerpc/kernel/setup_32.c | 2 +-
arch/powerpc/mm/pgtable_32.c | 16 ++++++++++++++++
3 files changed, 21 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h
index 2ef155a3c821..ccbe2e83c950 100644
--- a/arch/powerpc/include/asm/fixmap.h
+++ b/arch/powerpc/include/asm/fixmap.h
@@ -86,6 +86,10 @@ enum fixed_addresses {
#define __FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT)
#define FIXADDR_START (FIXADDR_TOP - __FIXADDR_SIZE)
+#define FIXMAP_ALIGNED_SIZE (ALIGN(FIXADDR_TOP, PGDIR_SIZE) - \
+ ALIGN_DOWN(FIXADDR_START, PGDIR_SIZE))
+#define FIXMAP_PTE_SIZE (FIXMAP_ALIGNED_SIZE / PGDIR_SIZE * PTE_TABLE_SIZE)
+
#define FIXMAP_PAGE_NOCACHE PAGE_KERNEL_NCG
#define FIXMAP_PAGE_IO PAGE_KERNEL_NCG
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 305ca89d856f..fee167d2701f 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -80,7 +80,7 @@ notrace void __init machine_init(u64 dt_ptr)
/* Configure static keys first, now that we're relocated. */
setup_feature_keys();
- early_ioremap_setup();
+ early_ioremap_init();
/* Enable early debugging if any specified (see udbg.h) */
udbg_early_init();
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index f62de06e3d07..9934659cb871 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -29,11 +29,27 @@
#include <asm/fixmap.h>
#include <asm/setup.h>
#include <asm/sections.h>
+#include <asm/early_ioremap.h>
#include <mm/mmu_decl.h>
extern char etext[], _stext[], _sinittext[], _einittext[];
+static u8 early_fixmap_pagetable[FIXMAP_PTE_SIZE] __page_aligned_data;
+
+notrace void __init early_ioremap_init(void)
+{
+ unsigned long addr = ALIGN_DOWN(FIXADDR_START, PGDIR_SIZE);
+ pte_t *ptep = (pte_t *)early_fixmap_pagetable;
+ pmd_t *pmdp = pmd_ptr_k(addr);
+
+ for (; (s32)(FIXADDR_TOP - addr) > 0;
+ addr += PGDIR_SIZE, ptep += PTRS_PER_PTE, pmdp++)
+ pmd_populate_kernel(&init_mm, pmdp, ptep);
+
+ early_ioremap_setup();
+}
+
static void __init *early_alloc_pgtable(unsigned long size)
{
void *ptr = memblock_alloc(size, size);
--
2.25.0
^ permalink raw reply related
* [PATCH v3 14/45] powerpc/32s: Don't warn when mapping RO data ROX.
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
Mapping RO data as ROX is not an issue since that data
cannot be modified to introduce an exploit.
PPC64 accepts to have RO data mapped ROX, as a trade off
between kernel size and strictness of protection.
On PPC32, kernel size is even more critical as amount of
memory is usually small.
Depending on the number of available IBATs, the last IBATs
might overflow the end of text. Only warn if it crosses
the end of RO data.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/mm/book3s32/mmu.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
index 39ba53ca5bb5..a9b2cbc74797 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -187,6 +187,7 @@ void mmu_mark_initmem_nx(void)
int i;
unsigned long base = (unsigned long)_stext - PAGE_OFFSET;
unsigned long top = (unsigned long)_etext - PAGE_OFFSET;
+ unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET;
unsigned long size;
if (IS_ENABLED(CONFIG_PPC_BOOK3S_601))
@@ -201,9 +202,10 @@ void mmu_mark_initmem_nx(void)
size = block_size(base, top);
size = max(size, 128UL << 10);
if ((top - base) > size) {
- if (strict_kernel_rwx_enabled())
- pr_warn("Kernel _etext not properly aligned\n");
size <<= 1;
+ if (strict_kernel_rwx_enabled() && base + size > border)
+ pr_warn("Some RW data is getting mapped X. "
+ "Adjust CONFIG_DATA_SHIFT to avoid that.\n");
}
setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT);
base += size;
--
2.25.0
^ permalink raw reply related
* [PATCH v3 13/45] powerpc/ptdump: Handle hugepd at PGD level
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
The 8xx is about to map kernel linear space and IMMR using huge
pages.
In order to display those pages properly, ptdump needs to handle
hugepd tables at PGD level.
For the time being do it only at PGD level. Further patches may
add handling of hugepd tables at lower level for other platforms
when needed in the future.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v3: notepage() now takes page size instead of page shift
---
arch/powerpc/mm/ptdump/ptdump.c | 29 ++++++++++++++++++++++++++---
1 file changed, 26 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index 98d82dcf6f0b..5fc880e30175 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -23,6 +23,7 @@
#include <linux/const.h>
#include <asm/page.h>
#include <asm/pgalloc.h>
+#include <asm/hugetlb.h>
#include <mm/mmu_decl.h>
@@ -269,6 +270,26 @@ static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
}
}
+static void walk_hugepd(struct pg_state *st, hugepd_t *phpd, unsigned long start,
+ int pdshift, int level)
+{
+#ifdef CONFIG_ARCH_HAS_HUGEPD
+ unsigned int i;
+ int shift = hugepd_shift(*phpd);
+ int ptrs_per_hpd = pdshift - shift > 0 ? 1 << (pdshift - shift) : 1;
+
+ if (start & ((1 << shift) - 1))
+ return;
+
+ for (i = 0; i < ptrs_per_hpd; i++) {
+ unsigned long addr = start + (i << shift);
+ pte_t *pte = hugepte_offset(*phpd, addr, pdshift);
+
+ note_page(st, addr, level + 1, pte_val(*pte), 1 << shift);
+ }
+#endif
+}
+
static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
{
pmd_t *pmd = pmd_offset(pud, 0);
@@ -312,11 +333,13 @@ static void walk_pagetables(struct pg_state *st)
* the hash pagetable.
*/
for (i = pgd_index(addr); i < PTRS_PER_PGD; i++, pgd++, addr += PGDIR_SIZE) {
- if (!pgd_none(*pgd) && !pgd_is_leaf(*pgd))
+ if (pgd_none(*pgd) || pgd_is_leaf(*pgd))
+ note_page(st, addr, 1, pgd_val(*pgd), PGDIR_SIZE);
+ else if (is_hugepd(__hugepd(pgd_val(*pgd))))
+ walk_hugepd(st, (hugepd_t *)pgd, addr, PGDIR_SHIFT, 1);
+ else
/* pgd exists */
walk_pud(st, pgd, addr);
- else
- note_page(st, addr, 1, pgd_val(*pgd), PGDIR_SIZE);
}
}
--
2.25.0
^ permalink raw reply related
* [PATCH v3 06/45] powerpc/kasan: Declare kasan_init_region() weak
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
In order to alloc sub-arches to alloc KASAN regions using optimised
methods (Huge pages on 8xx, BATs on BOOK3S, ...), declare
kasan_init_region() weak.
Also make kasan_init_shadow_page_tables() accessible from outside,
so that it can be called from the specific kasan_init_region()
functions if needed.
And populate remaining KASAN address space only once performed
the region mapping, to allow 8xx to allocate hugepd instead of
standard page tables for mapping via 8M hugepages.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/kasan.h | 3 +++
arch/powerpc/mm/kasan/kasan_init_32.c | 21 +++++++++++----------
2 files changed, 14 insertions(+), 10 deletions(-)
diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h
index 4769bbf7173a..107a24c3f7b3 100644
--- a/arch/powerpc/include/asm/kasan.h
+++ b/arch/powerpc/include/asm/kasan.h
@@ -34,5 +34,8 @@ static inline void kasan_init(void) { }
static inline void kasan_late_init(void) { }
#endif
+int kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end);
+int kasan_init_region(void *start, size_t size);
+
#endif /* __ASSEMBLY */
#endif
diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c
index 10481d904fea..76d418af4ce8 100644
--- a/arch/powerpc/mm/kasan/kasan_init_32.c
+++ b/arch/powerpc/mm/kasan/kasan_init_32.c
@@ -28,7 +28,7 @@ static void __init kasan_populate_pte(pte_t *ptep, pgprot_t prot)
__set_pte_at(&init_mm, va, ptep, pfn_pte(PHYS_PFN(pa), prot), 0);
}
-static int __init kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end)
+int __init kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end)
{
pmd_t *pmd;
unsigned long k_cur, k_next;
@@ -52,7 +52,7 @@ static int __init kasan_init_shadow_page_tables(unsigned long k_start, unsigned
return 0;
}
-static int __init kasan_init_region(void *start, size_t size)
+int __init __weak kasan_init_region(void *start, size_t size)
{
unsigned long k_start = (unsigned long)kasan_mem_to_shadow(start);
unsigned long k_end = (unsigned long)kasan_mem_to_shadow(start + size);
@@ -122,14 +122,6 @@ static void __init kasan_mmu_init(void)
int ret;
struct memblock_region *reg;
- if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE) ||
- IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
- ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END);
-
- if (ret)
- panic("kasan: kasan_init_shadow_page_tables() failed");
- }
-
for_each_memblock(memory, reg) {
phys_addr_t base = reg->base;
phys_addr_t top = min(base + reg->size, total_lowmem);
@@ -141,6 +133,15 @@ static void __init kasan_mmu_init(void)
if (ret)
panic("kasan: kasan_init_region() failed");
}
+
+ if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE) ||
+ IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
+ ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END);
+
+ if (ret)
+ panic("kasan: kasan_init_shadow_page_tables() failed");
+ }
+
}
void __init kasan_init(void)
--
2.25.0
^ permalink raw reply related
* [PATCH v3 12/45] powerpc/ptdump: Properly handle non standard page size
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
In order to properly display information regardless of the page size,
it is necessary to take into account real page size.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Fixes: cabe8138b23c ("powerpc: dump as a single line areas mapping a single physical page.")
Cc: stable@vger.kernel.org
---
v3: Fixed sizes which were shifted one level (went unoticed on PPC32 as PMD and PUD level don't exist)
---
arch/powerpc/mm/ptdump/ptdump.c | 21 ++++++++++++---------
1 file changed, 12 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index 1f97668853e3..98d82dcf6f0b 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -60,6 +60,7 @@ struct pg_state {
unsigned long start_address;
unsigned long start_pa;
unsigned long last_pa;
+ unsigned long page_size;
unsigned int level;
u64 current_flags;
bool check_wx;
@@ -168,9 +169,9 @@ static void dump_addr(struct pg_state *st, unsigned long addr)
#endif
pt_dump_seq_printf(st->seq, REG "-" REG " ", st->start_address, addr - 1);
- if (st->start_pa == st->last_pa && st->start_address + PAGE_SIZE != addr) {
+ if (st->start_pa == st->last_pa && st->start_address + st->page_size != addr) {
pt_dump_seq_printf(st->seq, "[" REG "]", st->start_pa);
- delta = PAGE_SIZE >> 10;
+ delta = st->page_size >> 10;
} else {
pt_dump_seq_printf(st->seq, " " REG " ", st->start_pa);
delta = (addr - st->start_address) >> 10;
@@ -195,7 +196,7 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr)
}
static void note_page(struct pg_state *st, unsigned long addr,
- unsigned int level, u64 val)
+ unsigned int level, u64 val, unsigned long page_size)
{
u64 flag = val & pg_level[level].mask;
u64 pa = val & PTE_RPN_MASK;
@@ -207,6 +208,7 @@ static void note_page(struct pg_state *st, unsigned long addr,
st->start_address = addr;
st->start_pa = pa;
st->last_pa = pa;
+ st->page_size = page_size;
pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
/*
* Dump the section of virtual memory when:
@@ -218,7 +220,7 @@ static void note_page(struct pg_state *st, unsigned long addr,
*/
} else if (flag != st->current_flags || level != st->level ||
addr >= st->marker[1].start_address ||
- (pa != st->last_pa + PAGE_SIZE &&
+ (pa != st->last_pa + st->page_size &&
(pa != st->start_pa || st->start_pa != st->last_pa))) {
/* Check the PTE flags */
@@ -246,6 +248,7 @@ static void note_page(struct pg_state *st, unsigned long addr,
st->start_address = addr;
st->start_pa = pa;
st->last_pa = pa;
+ st->page_size = page_size;
st->current_flags = flag;
st->level = level;
} else {
@@ -261,7 +264,7 @@ static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
for (i = 0; i < PTRS_PER_PTE; i++, pte++) {
addr = start + i * PAGE_SIZE;
- note_page(st, addr, 4, pte_val(*pte));
+ note_page(st, addr, 4, pte_val(*pte), PAGE_SIZE);
}
}
@@ -278,7 +281,7 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
/* pmd exists */
walk_pte(st, pmd, addr);
else
- note_page(st, addr, 3, pmd_val(*pmd));
+ note_page(st, addr, 3, pmd_val(*pmd), PMD_SIZE);
}
}
@@ -294,7 +297,7 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
/* pud exists */
walk_pmd(st, pud, addr);
else
- note_page(st, addr, 2, pud_val(*pud));
+ note_page(st, addr, 2, pud_val(*pud), PUD_SIZE);
}
}
@@ -313,7 +316,7 @@ static void walk_pagetables(struct pg_state *st)
/* pgd exists */
walk_pud(st, pgd, addr);
else
- note_page(st, addr, 1, pgd_val(*pgd));
+ note_page(st, addr, 1, pgd_val(*pgd), PGDIR_SIZE);
}
}
@@ -368,7 +371,7 @@ static int ptdump_show(struct seq_file *m, void *v)
/* Traverse kernel page tables */
walk_pagetables(&st);
- note_page(&st, 0, 0, 0);
+ note_page(&st, 0, 0, 0, 0);
return 0;
}
--
2.25.0
^ permalink raw reply related
* [PATCH v3 09/45] powerpc/ptdump: Add _PAGE_COHERENT flag
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
For platforms using shared.c (4xx, Book3e, Book3s/32),
also handle the _PAGE_COHERENT flag with corresponds to the
M bit of the WIMG flags.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/mm/ptdump/shared.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/arch/powerpc/mm/ptdump/shared.c b/arch/powerpc/mm/ptdump/shared.c
index dab5d8028a9b..634b83aa3487 100644
--- a/arch/powerpc/mm/ptdump/shared.c
+++ b/arch/powerpc/mm/ptdump/shared.c
@@ -40,6 +40,11 @@ static const struct flag_info flag_array[] = {
.val = _PAGE_NO_CACHE,
.set = "i",
.clear = " ",
+ }, {
+ .mask = _PAGE_COHERENT,
+ .val = _PAGE_COHERENT,
+ .set = "m",
+ .clear = " ",
}, {
.mask = _PAGE_GUARDED,
.val = _PAGE_GUARDED,
--
2.25.0
^ permalink raw reply related
* [PATCH v3 07/45] powerpc/ptdump: Limit size of flags text to 1/2 chars on PPC32
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
In order to have all flags fit on a 80 chars wide screen,
reduce the flags to 1 char (2 where ambiguous).
No cache is 'i'
User is 'ur' (Supervisor would be sr)
Shared (for 8xx) becomes 'sh' (it was 'user' when not shared but
that was ambiguous because that's not entirely right)
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/mm/ptdump/8xx.c | 33 ++++++++++++++++---------------
arch/powerpc/mm/ptdump/shared.c | 35 +++++++++++++++++----------------
2 files changed, 35 insertions(+), 33 deletions(-)
diff --git a/arch/powerpc/mm/ptdump/8xx.c b/arch/powerpc/mm/ptdump/8xx.c
index 9e2d8e847d6e..ca9ce94672f5 100644
--- a/arch/powerpc/mm/ptdump/8xx.c
+++ b/arch/powerpc/mm/ptdump/8xx.c
@@ -12,9 +12,9 @@
static const struct flag_info flag_array[] = {
{
.mask = _PAGE_SH,
- .val = 0,
- .set = "user",
- .clear = " ",
+ .val = _PAGE_SH,
+ .set = "sh",
+ .clear = " ",
}, {
.mask = _PAGE_RO | _PAGE_NA,
.val = 0,
@@ -30,37 +30,38 @@ static const struct flag_info flag_array[] = {
}, {
.mask = _PAGE_EXEC,
.val = _PAGE_EXEC,
- .set = " X ",
- .clear = " ",
+ .set = "x",
+ .clear = " ",
}, {
.mask = _PAGE_PRESENT,
.val = _PAGE_PRESENT,
- .set = "present",
- .clear = " ",
+ .set = "p",
+ .clear = " ",
}, {
.mask = _PAGE_GUARDED,
.val = _PAGE_GUARDED,
- .set = "guarded",
- .clear = " ",
+ .set = "g",
+ .clear = " ",
}, {
.mask = _PAGE_DIRTY,
.val = _PAGE_DIRTY,
- .set = "dirty",
- .clear = " ",
+ .set = "d",
+ .clear = " ",
}, {
.mask = _PAGE_ACCESSED,
.val = _PAGE_ACCESSED,
- .set = "accessed",
- .clear = " ",
+ .set = "a",
+ .clear = " ",
}, {
.mask = _PAGE_NO_CACHE,
.val = _PAGE_NO_CACHE,
- .set = "no cache",
- .clear = " ",
+ .set = "i",
+ .clear = " ",
}, {
.mask = _PAGE_SPECIAL,
.val = _PAGE_SPECIAL,
- .set = "special",
+ .set = "s",
+ .clear = " ",
}
};
diff --git a/arch/powerpc/mm/ptdump/shared.c b/arch/powerpc/mm/ptdump/shared.c
index f7ed2f187cb0..44a8a64a664f 100644
--- a/arch/powerpc/mm/ptdump/shared.c
+++ b/arch/powerpc/mm/ptdump/shared.c
@@ -13,8 +13,8 @@ static const struct flag_info flag_array[] = {
{
.mask = _PAGE_USER,
.val = _PAGE_USER,
- .set = "user",
- .clear = " ",
+ .set = "ur",
+ .clear = " ",
}, {
.mask = _PAGE_RW,
.val = _PAGE_RW,
@@ -23,42 +23,43 @@ static const struct flag_info flag_array[] = {
}, {
.mask = _PAGE_EXEC,
.val = _PAGE_EXEC,
- .set = " X ",
- .clear = " ",
+ .set = "x",
+ .clear = " ",
}, {
.mask = _PAGE_PRESENT,
.val = _PAGE_PRESENT,
- .set = "present",
- .clear = " ",
+ .set = "p",
+ .clear = " ",
}, {
.mask = _PAGE_GUARDED,
.val = _PAGE_GUARDED,
- .set = "guarded",
- .clear = " ",
+ .set = "g",
+ .clear = " ",
}, {
.mask = _PAGE_DIRTY,
.val = _PAGE_DIRTY,
- .set = "dirty",
- .clear = " ",
+ .set = "d",
+ .clear = " ",
}, {
.mask = _PAGE_ACCESSED,
.val = _PAGE_ACCESSED,
- .set = "accessed",
- .clear = " ",
+ .set = "a",
+ .clear = " ",
}, {
.mask = _PAGE_WRITETHRU,
.val = _PAGE_WRITETHRU,
- .set = "write through",
- .clear = " ",
+ .set = "w",
+ .clear = " ",
}, {
.mask = _PAGE_NO_CACHE,
.val = _PAGE_NO_CACHE,
- .set = "no cache",
- .clear = " ",
+ .set = "i",
+ .clear = " ",
}, {
.mask = _PAGE_SPECIAL,
.val = _PAGE_SPECIAL,
- .set = "special",
+ .set = "s",
+ .clear = " ",
}
};
--
2.25.0
^ permalink raw reply related
* [PATCH v3 05/45] powerpc/kasan: Refactor update of early shadow mappings
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
kasan_remap_early_shadow_ro() and kasan_unmap_early_shadow_vmalloc()
are both updating the early shadow mapping: the first one sets
the mapping read-only while the other clears the mapping.
Refactor and create kasan_update_early_region()
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/mm/kasan/kasan_init_32.c | 39 +++++++++++++--------------
1 file changed, 18 insertions(+), 21 deletions(-)
diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c
index 91e2ade75192..10481d904fea 100644
--- a/arch/powerpc/mm/kasan/kasan_init_32.c
+++ b/arch/powerpc/mm/kasan/kasan_init_32.c
@@ -79,45 +79,42 @@ static int __init kasan_init_region(void *start, size_t size)
return 0;
}
-static void __init kasan_remap_early_shadow_ro(void)
+static void __init
+kasan_update_early_region(unsigned long k_start, unsigned long k_end, pte_t pte)
{
- pgprot_t prot = kasan_prot_ro();
- unsigned long k_start = KASAN_SHADOW_START;
- unsigned long k_end = KASAN_SHADOW_END;
unsigned long k_cur;
phys_addr_t pa = __pa(kasan_early_shadow_page);
- kasan_populate_pte(kasan_early_shadow_pte, prot);
-
- for (k_cur = k_start & PAGE_MASK; k_cur != k_end; k_cur += PAGE_SIZE) {
+ for (k_cur = k_start; k_cur != k_end; k_cur += PAGE_SIZE) {
pmd_t *pmd = pmd_ptr_k(k_cur);
pte_t *ptep = pte_offset_kernel(pmd, k_cur);
if ((pte_val(*ptep) & PTE_RPN_MASK) != pa)
continue;
- __set_pte_at(&init_mm, k_cur, ptep, pfn_pte(PHYS_PFN(pa), prot), 0);
+ __set_pte_at(&init_mm, k_cur, ptep, pte, 0);
}
- flush_tlb_kernel_range(KASAN_SHADOW_START, KASAN_SHADOW_END);
+
+ flush_tlb_kernel_range(k_start, k_end);
}
-static void __init kasan_unmap_early_shadow_vmalloc(void)
+static void __init kasan_remap_early_shadow_ro(void)
{
- unsigned long k_start = (unsigned long)kasan_mem_to_shadow((void *)VMALLOC_START);
- unsigned long k_end = (unsigned long)kasan_mem_to_shadow((void *)VMALLOC_END);
- unsigned long k_cur;
+ pgprot_t prot = kasan_prot_ro();
phys_addr_t pa = __pa(kasan_early_shadow_page);
- for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) {
- pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur);
- pte_t *ptep = pte_offset_kernel(pmd, k_cur);
+ kasan_populate_pte(kasan_early_shadow_pte, prot);
- if ((pte_val(*ptep) & PTE_RPN_MASK) != pa)
- continue;
+ kasan_update_early_region(KASAN_SHADOW_START, KASAN_SHADOW_END,
+ pfn_pte(PHYS_PFN(pa), prot));
+}
- __set_pte_at(&init_mm, k_cur, ptep, __pte(0), 0);
- }
- flush_tlb_kernel_range(k_start, k_end);
+static void __init kasan_unmap_early_shadow_vmalloc(void)
+{
+ unsigned long k_start = (unsigned long)kasan_mem_to_shadow((void *)VMALLOC_START);
+ unsigned long k_end = (unsigned long)kasan_mem_to_shadow((void *)VMALLOC_END);
+
+ kasan_update_early_region(k_start, k_end, __pte(0));
}
static void __init kasan_mmu_init(void)
--
2.25.0
^ permalink raw reply related
* [PATCH v3 08/45] powerpc/ptdump: Reorder flags
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
Reorder flags in a more logical way:
- Page size (huge) first
- User
- RWX
- Present
- WIMG
- Special
- Dirty and Accessed
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/mm/ptdump/8xx.c | 30 +++++++++++++++---------------
arch/powerpc/mm/ptdump/shared.c | 30 +++++++++++++++---------------
2 files changed, 30 insertions(+), 30 deletions(-)
diff --git a/arch/powerpc/mm/ptdump/8xx.c b/arch/powerpc/mm/ptdump/8xx.c
index ca9ce94672f5..a3169677dced 100644
--- a/arch/powerpc/mm/ptdump/8xx.c
+++ b/arch/powerpc/mm/ptdump/8xx.c
@@ -11,11 +11,6 @@
static const struct flag_info flag_array[] = {
{
- .mask = _PAGE_SH,
- .val = _PAGE_SH,
- .set = "sh",
- .clear = " ",
- }, {
.mask = _PAGE_RO | _PAGE_NA,
.val = 0,
.set = "rw",
@@ -37,11 +32,26 @@ static const struct flag_info flag_array[] = {
.val = _PAGE_PRESENT,
.set = "p",
.clear = " ",
+ }, {
+ .mask = _PAGE_NO_CACHE,
+ .val = _PAGE_NO_CACHE,
+ .set = "i",
+ .clear = " ",
}, {
.mask = _PAGE_GUARDED,
.val = _PAGE_GUARDED,
.set = "g",
.clear = " ",
+ }, {
+ .mask = _PAGE_SH,
+ .val = _PAGE_SH,
+ .set = "sh",
+ .clear = " ",
+ }, {
+ .mask = _PAGE_SPECIAL,
+ .val = _PAGE_SPECIAL,
+ .set = "s",
+ .clear = " ",
}, {
.mask = _PAGE_DIRTY,
.val = _PAGE_DIRTY,
@@ -52,16 +62,6 @@ static const struct flag_info flag_array[] = {
.val = _PAGE_ACCESSED,
.set = "a",
.clear = " ",
- }, {
- .mask = _PAGE_NO_CACHE,
- .val = _PAGE_NO_CACHE,
- .set = "i",
- .clear = " ",
- }, {
- .mask = _PAGE_SPECIAL,
- .val = _PAGE_SPECIAL,
- .set = "s",
- .clear = " ",
}
};
diff --git a/arch/powerpc/mm/ptdump/shared.c b/arch/powerpc/mm/ptdump/shared.c
index 44a8a64a664f..dab5d8028a9b 100644
--- a/arch/powerpc/mm/ptdump/shared.c
+++ b/arch/powerpc/mm/ptdump/shared.c
@@ -30,21 +30,6 @@ static const struct flag_info flag_array[] = {
.val = _PAGE_PRESENT,
.set = "p",
.clear = " ",
- }, {
- .mask = _PAGE_GUARDED,
- .val = _PAGE_GUARDED,
- .set = "g",
- .clear = " ",
- }, {
- .mask = _PAGE_DIRTY,
- .val = _PAGE_DIRTY,
- .set = "d",
- .clear = " ",
- }, {
- .mask = _PAGE_ACCESSED,
- .val = _PAGE_ACCESSED,
- .set = "a",
- .clear = " ",
}, {
.mask = _PAGE_WRITETHRU,
.val = _PAGE_WRITETHRU,
@@ -55,11 +40,26 @@ static const struct flag_info flag_array[] = {
.val = _PAGE_NO_CACHE,
.set = "i",
.clear = " ",
+ }, {
+ .mask = _PAGE_GUARDED,
+ .val = _PAGE_GUARDED,
+ .set = "g",
+ .clear = " ",
}, {
.mask = _PAGE_SPECIAL,
.val = _PAGE_SPECIAL,
.set = "s",
.clear = " ",
+ }, {
+ .mask = _PAGE_DIRTY,
+ .val = _PAGE_DIRTY,
+ .set = "d",
+ .clear = " ",
+ }, {
+ .mask = _PAGE_ACCESSED,
+ .val = _PAGE_ACCESSED,
+ .set = "a",
+ .clear = " ",
}
};
--
2.25.0
^ permalink raw reply related
* [PATCH v3 11/45] powerpc/ptdump: Standardise display of BAT flags
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
Display BAT flags the same way as page flags: rwx and wimg
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/mm/ptdump/bats.c | 37 ++++++++++++++---------------------
1 file changed, 15 insertions(+), 22 deletions(-)
diff --git a/arch/powerpc/mm/ptdump/bats.c b/arch/powerpc/mm/ptdump/bats.c
index d6c660f63d71..cebb58c7e289 100644
--- a/arch/powerpc/mm/ptdump/bats.c
+++ b/arch/powerpc/mm/ptdump/bats.c
@@ -15,12 +15,12 @@
static char *pp_601(int k, int pp)
{
if (pp == 0)
- return k ? "NA" : "RWX";
+ return k ? " " : "rwx";
if (pp == 1)
- return k ? "ROX" : "RWX";
+ return k ? "r x" : "rwx";
if (pp == 2)
- return k ? "RWX" : "RWX";
- return k ? "ROX" : "ROX";
+ return "rwx";
+ return "r x";
}
static void bat_show_601(struct seq_file *m, int idx, u32 lower, u32 upper)
@@ -48,12 +48,9 @@ static void bat_show_601(struct seq_file *m, int idx, u32 lower, u32 upper)
seq_printf(m, "Kernel %s User %s", pp_601(k & 2, pp), pp_601(k & 1, pp));
- if (lower & _PAGE_WRITETHRU)
- seq_puts(m, "write through ");
- if (lower & _PAGE_NO_CACHE)
- seq_puts(m, "no cache ");
- if (lower & _PAGE_COHERENT)
- seq_puts(m, "coherent ");
+ seq_puts(m, lower & _PAGE_WRITETHRU ? "w " : " ");
+ seq_puts(m, lower & _PAGE_NO_CACHE ? "i " : " ");
+ seq_puts(m, lower & _PAGE_COHERENT ? "m " : " ");
seq_puts(m, "\n");
}
@@ -101,20 +98,16 @@ static void bat_show_603(struct seq_file *m, int idx, u32 lower, u32 upper, bool
seq_puts(m, "Kernel/User ");
if (lower & BPP_RX)
- seq_puts(m, is_d ? "RO " : "EXEC ");
+ seq_puts(m, is_d ? "r " : " x ");
else if (lower & BPP_RW)
- seq_puts(m, is_d ? "RW " : "EXEC ");
+ seq_puts(m, is_d ? "rw " : " x ");
else
- seq_puts(m, is_d ? "NA " : "NX ");
-
- if (lower & _PAGE_WRITETHRU)
- seq_puts(m, "write through ");
- if (lower & _PAGE_NO_CACHE)
- seq_puts(m, "no cache ");
- if (lower & _PAGE_COHERENT)
- seq_puts(m, "coherent ");
- if (lower & _PAGE_GUARDED)
- seq_puts(m, "guarded ");
+ seq_puts(m, is_d ? " " : " ");
+
+ seq_puts(m, lower & _PAGE_WRITETHRU ? "w " : " ");
+ seq_puts(m, lower & _PAGE_NO_CACHE ? "i " : " ");
+ seq_puts(m, lower & _PAGE_COHERENT ? "m " : " ");
+ seq_puts(m, lower & _PAGE_GUARDED ? "g " : " ");
seq_puts(m, "\n");
}
--
2.25.0
^ permalink raw reply related
* [PATCH v3 10/45] powerpc/ptdump: Display size of BATs
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
Display the size of areas mapped with BATs.
For that, the size display for pages is refactorised.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v2: Add missing include of linux/seq_file.h (Thanks to kbuild test robot)
---
arch/powerpc/mm/ptdump/bats.c | 4 ++++
arch/powerpc/mm/ptdump/ptdump.c | 23 ++++++++++++++---------
arch/powerpc/mm/ptdump/ptdump.h | 3 +++
3 files changed, 21 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/mm/ptdump/bats.c b/arch/powerpc/mm/ptdump/bats.c
index d3a5d6b318d1..d6c660f63d71 100644
--- a/arch/powerpc/mm/ptdump/bats.c
+++ b/arch/powerpc/mm/ptdump/bats.c
@@ -10,6 +10,8 @@
#include <asm/pgtable.h>
#include <asm/cpu_has_feature.h>
+#include "ptdump.h"
+
static char *pp_601(int k, int pp)
{
if (pp == 0)
@@ -42,6 +44,7 @@ static void bat_show_601(struct seq_file *m, int idx, u32 lower, u32 upper)
#else
seq_printf(m, "0x%08x ", pbn);
#endif
+ pt_dump_size(m, size);
seq_printf(m, "Kernel %s User %s", pp_601(k & 2, pp), pp_601(k & 1, pp));
@@ -88,6 +91,7 @@ static void bat_show_603(struct seq_file *m, int idx, u32 lower, u32 upper, bool
#else
seq_printf(m, "0x%08x ", brpn);
#endif
+ pt_dump_size(m, size);
if (k == 1)
seq_puts(m, "User ");
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index d92bb8ea229c..1f97668853e3 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -112,6 +112,19 @@ static struct addr_marker address_markers[] = {
seq_putc(m, c); \
})
+void pt_dump_size(struct seq_file *m, unsigned long size)
+{
+ static const char units[] = "KMGTPE";
+ const char *unit = units;
+
+ /* Work out what appropriate unit to use */
+ while (!(size & 1023) && unit[1]) {
+ size >>= 10;
+ unit++;
+ }
+ pt_dump_seq_printf(m, "%9lu%c ", size, *unit);
+}
+
static void dump_flag_info(struct pg_state *st, const struct flag_info
*flag, u64 pte, int num)
{
@@ -146,8 +159,6 @@ static void dump_flag_info(struct pg_state *st, const struct flag_info
static void dump_addr(struct pg_state *st, unsigned long addr)
{
- static const char units[] = "KMGTPE";
- const char *unit = units;
unsigned long delta;
#ifdef CONFIG_PPC64
@@ -164,13 +175,7 @@ static void dump_addr(struct pg_state *st, unsigned long addr)
pt_dump_seq_printf(st->seq, " " REG " ", st->start_pa);
delta = (addr - st->start_address) >> 10;
}
- /* Work out what appropriate unit to use */
- while (!(delta & 1023) && unit[1]) {
- delta >>= 10;
- unit++;
- }
- pt_dump_seq_printf(st->seq, "%9lu%c", delta, *unit);
-
+ pt_dump_size(st->seq, delta);
}
static void note_prot_wx(struct pg_state *st, unsigned long addr)
diff --git a/arch/powerpc/mm/ptdump/ptdump.h b/arch/powerpc/mm/ptdump/ptdump.h
index 5d513636de73..154efae96ae0 100644
--- a/arch/powerpc/mm/ptdump/ptdump.h
+++ b/arch/powerpc/mm/ptdump/ptdump.h
@@ -1,5 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/types.h>
+#include <linux/seq_file.h>
struct flag_info {
u64 mask;
@@ -17,3 +18,5 @@ struct pgtable_level {
};
extern struct pgtable_level pg_level[5];
+
+void pt_dump_size(struct seq_file *m, unsigned long delta);
--
2.25.0
^ permalink raw reply related
* [PATCH v3 00/45] Use hugepages to map kernel mem on 8xx
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
The main purpose of this big series is to:
- reorganise huge page handling to avoid using mm_slices.
- use huge pages to map kernel memory on the 8xx.
The 8xx supports 4 page sizes: 4k, 16k, 512k and 8M.
It uses 2 Level page tables, PGD having 1024 entries, each entry
covering 4M address space. Then each page table has 1024 entries.
At the time being, page sizes are managed in PGD entries, implying
the use of mm_slices as it can't mix several pages of the same size
in one page table.
The first purpose of this series is to reorganise things so that
standard page tables can also handle 512k pages. This is done by
adding a new _PAGE_HUGE flag which will be copied into the Level 1
entry in the TLB miss handler. That done, we have 2 types of pages:
- PGD entries to regular page tables handling 4k/16k and 512k pages
- PGD entries to hugepd tables handling 8M pages.
There is no need to mix 8M pages with other sizes, because a 8M page
will use more than what a single PGD covers.
Then comes the second purpose of this series. At the time being, the
8xx has implemented special handling in the TLB miss handlers in order
to transparently map kernel linear address space and the IMMR using
huge pages by building the TLB entries in assembly at the time of the
exception.
As mm_slices is only for user space pages, and also because it would
anyway not be convenient to slice kernel address space, it was not
possible to use huge pages for kernel address space. But after step
one of the series, it is now more flexible to use huge pages.
This series drop all assembly 'just in time' handling of huge pages
and use huge pages in page tables instead.
Once the above is done, then comes the cherry on cake:
- Use huge pages for KASAN shadow mapping
- Allow pinned TLBs with strict kernel rwx
- Allow pinned TLBs with debug pagealloc
Then, last but not least, those modifications for the 8xx allows the
following improvement on book3s/32:
- Mapping KASAN shadow with BATs
- Allowing BATs with debug pagealloc
All this allows to considerably simplify TLB miss handlers and associated
initialisation. The overhead of reading page tables is negligible
compared to the reduction of the miss handlers.
While we were at touching pte_update(), some cleanup was done
there too.
Tested widely on 8xx and 832x. Boot tested on QEMU MAC99.
Changes in v3:
- Fixed the handling of leaf pages page size which didn't build on PPC64 and was invisibily bogus on PPC32 (patch 12)
Changes in v2:
- Selecting HUGETLBFS instead of HUGETLB_PAGE which leads to link failure.
- Rebase on latest powerpc/merge branch
- Reworked the way TLB 28 to 31 are pinned because it was not working.
Christophe Leroy (45):
powerpc/kasan: Fix error detection on memory allocation
powerpc/kasan: Fix issues by lowering KASAN_SHADOW_END
powerpc/kasan: Fix shadow pages allocation failure
powerpc/kasan: Remove unnecessary page table locking
powerpc/kasan: Refactor update of early shadow mappings
powerpc/kasan: Declare kasan_init_region() weak
powerpc/ptdump: Limit size of flags text to 1/2 chars on PPC32
powerpc/ptdump: Reorder flags
powerpc/ptdump: Add _PAGE_COHERENT flag
powerpc/ptdump: Display size of BATs
powerpc/ptdump: Standardise display of BAT flags
powerpc/ptdump: Properly handle non standard page size
powerpc/ptdump: Handle hugepd at PGD level
powerpc/32s: Don't warn when mapping RO data ROX.
powerpc/mm: Allocate static page tables for fixmap
powerpc/mm: Fix conditions to perform MMU specific management by
blocks on PPC32.
powerpc/mm: PTE_ATOMIC_UPDATES is only for 40x
powerpc/mm: Refactor pte_update() on nohash/32
powerpc/mm: Refactor pte_update() on book3s/32
powerpc/mm: Standardise __ptep_test_and_clear_young() params between
PPC32 and PPC64
powerpc/mm: Standardise pte_update() prototype between PPC32 and PPC64
powerpc/mm: Create a dedicated pte_update() for 8xx
powerpc/mm: Reduce hugepd size for 8M hugepages on 8xx
powerpc/8xx: Drop CONFIG_8xx_COPYBACK option
powerpc/8xx: Prepare handlers for _PAGE_HUGE for 512k pages.
powerpc/8xx: Manage 512k huge pages as standard pages.
powerpc/8xx: Only 8M pages are hugepte pages now
powerpc/8xx: MM_SLICE is not needed anymore
powerpc/8xx: Move PPC_PIN_TLB options into 8xx Kconfig
powerpc/8xx: Add function to set pinned TLBs
powerpc/8xx: Don't set IMMR map anymore at boot
powerpc/8xx: Always pin TLBs at startup.
powerpc/8xx: Drop special handling of Linear and IMMR mappings in I/D
TLB handlers
powerpc/8xx: Remove now unused TLB miss functions
powerpc/8xx: Move DTLB perf handling closer.
powerpc/mm: Don't be too strict with _etext alignment on PPC32
powerpc/8xx: Refactor kernel address boundary comparison
powerpc/8xx: Add a function to early map kernel via huge pages
powerpc/8xx: Map IMMR with a huge page
powerpc/8xx: Map linear memory with huge pages
powerpc/8xx: Allow STRICT_KERNEL_RwX with pinned TLB
powerpc/8xx: Allow large TLBs with DEBUG_PAGEALLOC
powerpc/8xx: Implement dedicated kasan_init_region()
powerpc/32s: Allow mapping with BATs with DEBUG_PAGEALLOC
powerpc/32s: Implement dedicated kasan_init_region()
arch/powerpc/Kconfig | 62 +--
arch/powerpc/configs/adder875_defconfig | 1 -
arch/powerpc/configs/ep88xc_defconfig | 1 -
arch/powerpc/configs/mpc866_ads_defconfig | 1 -
arch/powerpc/configs/mpc885_ads_defconfig | 1 -
arch/powerpc/configs/tqm8xx_defconfig | 1 -
arch/powerpc/include/asm/book3s/32/pgtable.h | 78 ++--
arch/powerpc/include/asm/fixmap.h | 4 +
arch/powerpc/include/asm/hugetlb.h | 4 -
arch/powerpc/include/asm/kasan.h | 10 +-
.../include/asm/nohash/32/hugetlb-8xx.h | 32 +-
arch/powerpc/include/asm/nohash/32/mmu-8xx.h | 74 +---
arch/powerpc/include/asm/nohash/32/pgtable.h | 104 +++--
arch/powerpc/include/asm/nohash/32/pte-8xx.h | 4 +-
arch/powerpc/include/asm/nohash/32/slice.h | 20 -
arch/powerpc/include/asm/nohash/64/pgtable.h | 28 +-
arch/powerpc/include/asm/nohash/pgtable.h | 2 +-
arch/powerpc/include/asm/pgtable.h | 2 +
arch/powerpc/include/asm/slice.h | 2 -
arch/powerpc/kernel/head_8xx.S | 354 ++++++++----------
arch/powerpc/kernel/setup_32.c | 2 +-
arch/powerpc/kernel/vmlinux.lds.S | 3 +-
arch/powerpc/mm/book3s32/mmu.c | 12 +-
arch/powerpc/mm/hugetlbpage.c | 41 +-
arch/powerpc/mm/init_32.c | 12 +-
arch/powerpc/mm/kasan/8xx.c | 74 ++++
arch/powerpc/mm/kasan/Makefile | 2 +
arch/powerpc/mm/kasan/book3s_32.c | 57 +++
arch/powerpc/mm/kasan/kasan_init_32.c | 88 ++---
arch/powerpc/mm/mmu_decl.h | 4 +
arch/powerpc/mm/nohash/8xx.c | 226 ++++++-----
arch/powerpc/mm/pgtable.c | 34 +-
arch/powerpc/mm/pgtable_32.c | 22 +-
arch/powerpc/mm/ptdump/8xx.c | 52 +--
arch/powerpc/mm/ptdump/bats.c | 41 +-
arch/powerpc/mm/ptdump/ptdump.c | 71 +++-
arch/powerpc/mm/ptdump/ptdump.h | 3 +
arch/powerpc/mm/ptdump/shared.c | 58 +--
arch/powerpc/perf/8xx-pmu.c | 10 -
arch/powerpc/platforms/8xx/Kconfig | 50 ++-
arch/powerpc/platforms/Kconfig.cputype | 2 +-
arch/powerpc/sysdev/cpm_common.c | 2 +
42 files changed, 853 insertions(+), 798 deletions(-)
delete mode 100644 arch/powerpc/include/asm/nohash/32/slice.h
create mode 100644 arch/powerpc/mm/kasan/8xx.c
create mode 100644 arch/powerpc/mm/kasan/book3s_32.c
--
2.25.0
^ permalink raw reply
* [PATCH v3 02/45] powerpc/kasan: Fix issues by lowering KASAN_SHADOW_END
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
At the time being, KASAN_SHADOW_END is 0x100000000, which
is 0 in 32 bits representation.
This leads to a couple of issues:
- kasan_remap_early_shadow_ro() does nothing because the comparison
k_cur < k_end is always false.
- In ptdump, address comparison for markers display fails and the
marker's name is printed at the start of the KASAN area instead of
being printed at the end.
However, there is no need to shadow the KASAN shadow area itself,
so the KASAN shadow area can stop shadowing memory at the start
of itself.
With a PAGE_OFFSET set to 0xc0000000, KASAN shadow area is then going
from 0xf8000000 to 0xff000000.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Fixes: cbd18991e24f ("powerpc/mm: Fix an Oops in kasan_mmu_init()")
Cc: stable@vger.kernel.org
---
arch/powerpc/include/asm/kasan.h | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h
index fbff9ff9032e..fc900937f653 100644
--- a/arch/powerpc/include/asm/kasan.h
+++ b/arch/powerpc/include/asm/kasan.h
@@ -23,9 +23,7 @@
#define KASAN_SHADOW_OFFSET ASM_CONST(CONFIG_KASAN_SHADOW_OFFSET)
-#define KASAN_SHADOW_END 0UL
-
-#define KASAN_SHADOW_SIZE (KASAN_SHADOW_END - KASAN_SHADOW_START)
+#define KASAN_SHADOW_END (-(-KASAN_SHADOW_START >> KASAN_SHADOW_SCALE_SHIFT))
#ifdef CONFIG_KASAN
void kasan_early_init(void);
--
2.25.0
^ permalink raw reply related
* [PATCH v3 01/45] powerpc/kasan: Fix error detection on memory allocation
From: Christophe Leroy @ 2020-05-11 11:25 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1589196133.git.christophe.leroy@csgroup.eu>
In case (k_start & PAGE_MASK) doesn't equal (kstart), 'va' will never be
NULL allthough 'block' is NULL
Check the return of memblock_alloc() directly instead of
the resulting address in the loop.
Fixes: 509cd3f2b473 ("powerpc/32: Simplify KASAN init")
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/mm/kasan/kasan_init_32.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c
index cbcad369fcb2..8b15fe09b967 100644
--- a/arch/powerpc/mm/kasan/kasan_init_32.c
+++ b/arch/powerpc/mm/kasan/kasan_init_32.c
@@ -76,15 +76,14 @@ static int __init kasan_init_region(void *start, size_t size)
return ret;
block = memblock_alloc(k_end - k_start, PAGE_SIZE);
+ if (!block)
+ return -ENOMEM;
for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) {
pmd_t *pmd = pmd_ptr_k(k_cur);
void *va = block + k_cur - k_start;
pte_t pte = pfn_pte(PHYS_PFN(__pa(va)), PAGE_KERNEL);
- if (!va)
- return -ENOMEM;
-
__set_pte_at(&init_mm, k_cur, pte_offset_kernel(pmd, k_cur), pte, 0);
}
flush_tlb_kernel_range(k_start, k_end);
--
2.25.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox