| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20200206030900.147032-4-leonardo@linux.ibm.com>
Date: Thu, 6 Feb 2020 00:08:52 -0300
From: Leonardo Bras <leonardo@...ux.ibm.com>
To: Benjamin Herrenschmidt <benh@...nel.crashing.org>,
Paul Mackerras <paulus@...ba.org>,
Michael Ellerman <mpe@...erman.id.au>,
Arnd Bergmann <arnd@...db.de>,
Andrew Morton <akpm@...ux-foundation.org>,
"Aneesh Kumar K.V" <aneesh.kumar@...ux.ibm.com>,
Nicholas Piggin <npiggin@...il.com>,
Christophe Leroy <christophe.leroy@....fr>,
Steven Price <steven.price@....com>,
Robin Murphy <robin.murphy@....com>,
Leonardo Bras <leonardo@...ux.ibm.com>,
Mahesh Salgaonkar <mahesh@...ux.vnet.ibm.com>,
Balbir Singh <bsingharora@...il.com>,
Reza Arbab <arbab@...ux.ibm.com>,
Thomas Gleixner <tglx@...utronix.de>,
Allison Randal <allison@...utok.net>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
Mike Rapoport <rppt@...ux.ibm.com>,
Michal Suchanek <msuchanek@...e.de>
Cc: linuxppc-dev@...ts.ozlabs.org, linux-kernel@...r.kernel.org,
kvm-ppc@...r.kernel.org, linux-arch@...r.kernel.org,
linux-mm@...ck.org
Subject: [PATCH v6 03/11] powerpc/mm: Adds arch-specificic functions to track lockless pgtable walks
On powerpc, we need to do some lockless pagetable walks from functions
that already have disabled interrupts, specially from real mode with
MSR[EE=0].
In these contexts, disabling/enabling interrupts can be very troubling.
So, this arch-specific implementation features functions with an extra
argument that allows interrupt enable/disable to be skipped:
__begin_lockless_pgtbl_walk() and __end_lockless_pgtbl_walk().
Functions similar to the generic ones are also exported, by calling
the above functions with parameter {en,dis}able_irq = true.
Signed-off-by: Leonardo Bras <leonardo@...ux.ibm.com>
---
arch/powerpc/include/asm/book3s/64/pgtable.h | 6 ++
arch/powerpc/mm/book3s64/pgtable.c | 86 +++++++++++++++++++-
2 files changed, 91 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 201a69e6a355..78f6ffb1bb3e 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -1375,5 +1375,11 @@ static inline bool pgd_is_leaf(pgd_t pgd)
return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PTE));
}
+#define __HAVE_ARCH_LOCKLESS_PGTBL_WALK_CONTROL
+unsigned long begin_lockless_pgtbl_walk(void);
+unsigned long __begin_lockless_pgtbl_walk(bool disable_irq);
+void end_lockless_pgtbl_walk(unsigned long irq_mask);
+void __end_lockless_pgtbl_walk(unsigned long irq_mask, bool enable_irq);
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 2bf7e1b4fd82..535613030363 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -82,6 +82,7 @@ static void do_nothing(void *unused)
{
}
+
/*
* Serialize against find_current_mm_pte which does lock-less
* lookup in page tables with local interrupts disabled. For huge pages
@@ -98,6 +99,89 @@ void serialize_against_pte_lookup(struct mm_struct *mm)
smp_call_function_many(mm_cpumask(mm), do_nothing, NULL, 1);
}
+/* begin_lockless_pgtbl_walk: Must be inserted before a function call that does
+ * lockless pagetable walks, such as __find_linux_pte().
+ * This version allows setting disable_irq=false, so irqs are not touched, which
+ * is quite useful for running when ints are already disabled (like real-mode)
+ */
+inline
+unsigned long __begin_lockless_pgtbl_walk(bool disable_irq)
+{
+ unsigned long irq_mask = 0;
+
+ /*
+ * Interrupts must be disabled during the lockless page table walk.
+ * That's because the deleting or splitting involves flushing TLBs,
+ * which in turn issues interrupts, that will block when disabled.
+ *
+ * When this function is called from realmode with MSR[EE=0],
+ * it's not needed to touch irq, since it's already disabled.
+ */
+ if (disable_irq)
+ local_irq_save(irq_mask);
+
+ /*
+ * This memory barrier pairs with any code that is either trying to
+ * delete page tables, or split huge pages. Without this barrier,
+ * the page tables could be read speculatively outside of interrupt
+ * disabling or reference counting.
+ */
+ smp_mb();
+
+ return irq_mask;
+}
+EXPORT_SYMBOL(__begin_lockless_pgtbl_walk);
+
+/* begin_lockless_pgtbl_walk: Must be inserted before a function call that does
+ * lockless pagetable walks, such as __find_linux_pte().
+ * This version is used by generic code, and always assume irqs will be disabled
+ */
+unsigned long begin_lockless_pgtbl_walk(void)
+{
+ return __begin_lockless_pgtbl_walk(true);
+}
+EXPORT_SYMBOL(begin_lockless_pgtbl_walk);
+
+/*
+ * __end_lockless_pgtbl_walk: Must be inserted after the last use of a pointer
+ * returned by a lockless pagetable walk, such as __find_linux_pte()
+ * This version allows setting enable_irq=false, so irqs are not touched, which
+ * is quite useful for running when ints are already disabled (like real-mode)
+ */
+inline void __end_lockless_pgtbl_walk(unsigned long irq_mask, bool enable_irq)
+{
+ /*
+ * This memory barrier pairs with any code that is either trying to
+ * delete page tables, or split huge pages. Without this barrier,
+ * the page tables could be read speculatively outside of interrupt
+ * disabling or reference counting.
+ */
+ smp_mb();
+
+ /*
+ * Interrupts must be disabled during the lockless page table walk.
+ * That's because the deleting or splitting involves flushing TLBs,
+ * which in turn issues interrupts, that will block when disabled.
+ *
+ * When this function is called from realmode with MSR[EE=0],
+ * it's not needed to touch irq, since it's already disabled.
+ */
+ if (enable_irq)
+ local_irq_restore(irq_mask);
+}
+EXPORT_SYMBOL(__end_lockless_pgtbl_walk);
+
+/*
+ * end_lockless_pgtbl_walk: Must be inserted after the last use of a pointer
+ * returned by a lockless pagetable walk, such as __find_linux_pte()
+ * This version is used by generic code, and always assume irqs will be enabled
+ */
+void end_lockless_pgtbl_walk(unsigned long irq_mask)
+{
+ __end_lockless_pgtbl_walk(irq_mask, true);
+}
+EXPORT_SYMBOL(end_lockless_pgtbl_walk);
+
/*
* We use this to invalidate a pmdp entry before switching from a
* hugepte to regular pmd entry.
@@ -487,7 +571,7 @@ static int __init setup_disable_tlbie(char *str)
tlbie_capable = false;
tlbie_enabled = false;
- return 1;
+ return 1;
}
__setup("disable_tlbie", setup_disable_tlbie);
--
2.24.1
Powered by blists - more mailing lists