Re: Linux 4.4.148
From: Greg KH
Date: Thu Aug 16 2018 - 06:16:37 EST
diff --git a/Makefile b/Makefile
index ee92a12e3a4b..9b795164122e 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
VERSION = 4
PATCHLEVEL = 4
-SUBLEVEL = 147
+SUBLEVEL = 148
EXTRAVERSION =
NAME = Blurry Fish Butt
diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi
index 167f77b3bd43..6963dff815dc 100644
--- a/arch/arm/boot/dts/imx6sx.dtsi
+++ b/arch/arm/boot/dts/imx6sx.dtsi
@@ -1250,7 +1250,7 @@
/* non-prefetchable memory */
0x82000000 0 0x08000000 0x08000000 0 0x00f00000>;
num-lanes = <1>;
- interrupts = <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&clks IMX6SX_CLK_PCIE_REF_125M>,
<&clks IMX6SX_CLK_PCIE_AXI>,
<&clks IMX6SX_CLK_LVDS1_OUT>,
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 729f89163bc3..210b3d675261 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -177,7 +177,7 @@ config PREFETCH
config MLONGCALLS
bool "Enable the -mlong-calls compiler option for big kernels"
- def_bool y if (!MODULES)
+ default y
depends on PA8X00
help
If you configure the kernel to include many drivers built-in instead
diff --git a/arch/parisc/include/asm/barrier.h b/arch/parisc/include/asm/barrier.h
new file mode 100644
index 000000000000..dbaaca84f27f
--- /dev/null
+++ b/arch/parisc/include/asm/barrier.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_BARRIER_H
+#define __ASM_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+/* The synchronize caches instruction executes as a nop on systems in
+ which all memory references are performed in order. */
+#define synchronize_caches() __asm__ __volatile__ ("sync" : : : "memory")
+
+#if defined(CONFIG_SMP)
+#define mb() do { synchronize_caches(); } while (0)
+#define rmb() mb()
+#define wmb() mb()
+#define dma_rmb() mb()
+#define dma_wmb() mb()
+#else
+#define mb() barrier()
+#define rmb() barrier()
+#define wmb() barrier()
+#define dma_rmb() barrier()
+#define dma_wmb() barrier()
+#endif
+
+#define __smp_mb() mb()
+#define __smp_rmb() mb()
+#define __smp_wmb() mb()
+
+#include <asm-generic/barrier.h>
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __ASM_BARRIER_H */
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 5dc831955de5..13cb2461fef5 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -481,6 +481,8 @@
/* Release pa_tlb_lock lock without reloading lock address. */
.macro tlb_unlock0 spc,tmp
#ifdef CONFIG_SMP
+ or,COND(=) %r0,\spc,%r0
+ sync
or,COND(=) %r0,\spc,%r0
stw \spc,0(\tmp)
#endif
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index 16073f472118..b3434a7fd3c9 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -354,6 +354,7 @@ ENDPROC(flush_data_cache_local)
.macro tlb_unlock la,flags,tmp
#ifdef CONFIG_SMP
ldi 1,\tmp
+ sync
stw \tmp,0(\la)
mtsm \flags
#endif
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index 9f22195b90ed..f68eedc72484 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -631,6 +631,7 @@ cas_action:
sub,<> %r28, %r25, %r0
2: stw,ma %r24, 0(%r26)
/* Free lock */
+ sync
stw,ma %r20, 0(%sr2,%r20)
#if ENABLE_LWS_DEBUG
/* Clear thread register indicator */
@@ -645,6 +646,7 @@ cas_action:
3:
/* Error occurred on load or store */
/* Free lock */
+ sync
stw %r20, 0(%sr2,%r20)
#if ENABLE_LWS_DEBUG
stw %r0, 4(%sr2,%r20)
@@ -846,6 +848,7 @@ cas2_action:
cas2_end:
/* Free lock */
+ sync
stw,ma %r20, 0(%sr2,%r20)
/* Enable interrupts */
ssm PSW_SM_I, %r0
@@ -856,6 +859,7 @@ cas2_end:
22:
/* Error occurred on load or store */
/* Free lock */
+ sync
stw %r20, 0(%sr2,%r20)
ssm PSW_SM_I, %r0
ldo 1(%r0),%r28
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index f4b175db70f4..dd2269dcbc47 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -193,12 +193,12 @@
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
+#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
+
#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */
-#define X86_FEATURE_RETPOLINE ( 7*32+29) /* "" Generic Retpoline mitigation for Spectre variant 2 */
-#define X86_FEATURE_RETPOLINE_AMD ( 7*32+30) /* "" AMD Retpoline mitigation for Spectre variant 2 */
-
#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
#define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */
@@ -214,7 +214,7 @@
#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */
#define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */
#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
-
+#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
@@ -310,6 +310,7 @@
#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */
#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */
@@ -331,5 +332,6 @@
#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */
+#define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 0056bc945cd1..cb7f04981c6b 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -8,6 +8,8 @@
* Interrupt control:
*/
+/* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */
+extern inline unsigned long native_save_fl(void);
extern inline unsigned long native_save_fl(void)
{
unsigned long flags;
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index 3a52ee0e726d..bfceb5cc6347 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -27,8 +27,13 @@
#define N_EXCEPTION_STACKS 1
#ifdef CONFIG_X86_PAE
-/* 44=32+12, the limit we can fit into an unsigned long pfn */
-#define __PHYSICAL_MASK_SHIFT 44
+/*
+ * This is beyond the 44 bit limit imposed by the 32bit long pfns,
+ * but we need the full mask to make sure inverted PROT_NONE
+ * entries have all the host bits set in a guest.
+ * The real limit is still 44 bits.
+ */
+#define __PHYSICAL_MASK_SHIFT 52
#define __VIRTUAL_MASK_SHIFT 32
#else /* !CONFIG_X86_PAE */
diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index fd74a11959de..89c50332a71e 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -77,4 +77,21 @@ static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshi
#define __pte_to_swp_entry(pte) ((swp_entry_t) { (pte).pte_low })
#define __swp_entry_to_pte(x) ((pte_t) { .pte = (x).val })
+/* No inverted PFNs on 2 level page tables */
+
+static inline u64 protnone_mask(u64 val)
+{
+ return 0;
+}
+
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask)
+{
+ return val;
+}
+
+static inline bool __pte_needs_invert(u64 val)
+{
+ return false;
+}
+
#endif /* _ASM_X86_PGTABLE_2LEVEL_H */
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index cdaa58c9b39e..5c686382d84b 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -177,11 +177,44 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
#endif
/* Encode and de-code a swap entry */
+#define SWP_TYPE_BITS 5
+
+#define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1)
+
+/* We always extract/encode the offset by shifting it all the way up, and then down again */
+#define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT + SWP_TYPE_BITS)
+
#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5)
#define __swp_type(x) (((x).val) & 0x1f)
#define __swp_offset(x) ((x).val >> 5)
#define __swp_entry(type, offset) ((swp_entry_t){(type) | (offset) << 5})
-#define __pte_to_swp_entry(pte) ((swp_entry_t){ (pte).pte_high })
-#define __swp_entry_to_pte(x) ((pte_t){ { .pte_high = (x).val } })
+
+/*
+ * Normally, __swp_entry() converts from arch-independent swp_entry_t to
+ * arch-dependent swp_entry_t, and __swp_entry_to_pte() just stores the result
+ * to pte. But here we have 32bit swp_entry_t and 64bit pte, and need to use the
+ * whole 64 bits. Thus, we shift the "real" arch-dependent conversion to
+ * __swp_entry_to_pte() through the following helper macro based on 64bit
+ * __swp_entry().
+ */
+#define __swp_pteval_entry(type, offset) ((pteval_t) { \
+ (~(pteval_t)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \
+ | ((pteval_t)(type) << (64 - SWP_TYPE_BITS)) })
+
+#define __swp_entry_to_pte(x) ((pte_t){ .pte = \
+ __swp_pteval_entry(__swp_type(x), __swp_offset(x)) })
+/*
+ * Analogically, __pte_to_swp_entry() doesn't just extract the arch-dependent
+ * swp_entry_t, but also has to convert it from 64bit to the 32bit
+ * intermediate representation, using the following macros based on 64bit
+ * __swp_type() and __swp_offset().
+ */
+#define __pteval_swp_type(x) ((unsigned long)((x).pte >> (64 - SWP_TYPE_BITS)))
+#define __pteval_swp_offset(x) ((unsigned long)(~((x).pte) << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT))
+
+#define __pte_to_swp_entry(pte) (__swp_entry(__pteval_swp_type(pte), \
+ __pteval_swp_offset(pte)))
+
+#include <asm/pgtable-invert.h>
#endif /* _ASM_X86_PGTABLE_3LEVEL_H */
diff --git a/arch/x86/include/asm/pgtable-invert.h b/arch/x86/include/asm/pgtable-invert.h
new file mode 100644
index 000000000000..44b1203ece12
--- /dev/null
+++ b/arch/x86/include/asm/pgtable-invert.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_PGTABLE_INVERT_H
+#define _ASM_PGTABLE_INVERT_H 1
+
+#ifndef __ASSEMBLY__
+
+static inline bool __pte_needs_invert(u64 val)
+{
+ return !(val & _PAGE_PRESENT);
+}
+
+/* Get a mask to xor with the page table entry to get the correct pfn. */
+static inline u64 protnone_mask(u64 val)
+{
+ return __pte_needs_invert(val) ? ~0ull : 0;
+}
+
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask)
+{
+ /*
+ * When a PTE transitions from NONE to !NONE or vice-versa
+ * invert the PFN part to stop speculation.
+ * pte_pfn undoes this when needed.
+ */
+ if (__pte_needs_invert(oldval) != __pte_needs_invert(val))
+ val = (val & ~mask) | (~val & mask);
+ return val;
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 84c62d950023..4de6c282c02a 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -148,19 +148,29 @@ static inline int pte_special(pte_t pte)
return pte_flags(pte) & _PAGE_SPECIAL;
}
+/* Entries that were set to PROT_NONE are inverted */
+
+static inline u64 protnone_mask(u64 val);
+
static inline unsigned long pte_pfn(pte_t pte)
{
- return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
+ phys_addr_t pfn = pte_val(pte);
+ pfn ^= protnone_mask(pfn);
+ return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT;
}
static inline unsigned long pmd_pfn(pmd_t pmd)
{
- return (pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
+ phys_addr_t pfn = pmd_val(pmd);
+ pfn ^= protnone_mask(pfn);
+ return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
}
static inline unsigned long pud_pfn(pud_t pud)
{
- return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT;
+ phys_addr_t pfn = pud_val(pud);
+ pfn ^= protnone_mask(pfn);
+ return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT;
}
#define pte_page(pte) pfn_to_page(pte_pfn(pte))
@@ -305,11 +315,6 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd)
return pmd_set_flags(pmd, _PAGE_RW);
}
-static inline pmd_t pmd_mknotpresent(pmd_t pmd)
-{
- return pmd_clear_flags(pmd, _PAGE_PRESENT | _PAGE_PROTNONE);
-}
-
#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
static inline int pte_soft_dirty(pte_t pte)
{
@@ -359,19 +364,58 @@ static inline pgprotval_t massage_pgprot(pgprot_t pgprot)
static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
{
- return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) |
- massage_pgprot(pgprot));
+ phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
+ pfn ^= protnone_mask(pgprot_val(pgprot));
+ pfn &= PTE_PFN_MASK;
+ return __pte(pfn | massage_pgprot(pgprot));
}
static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
{
- return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) |
- massage_pgprot(pgprot));
+ phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
+ pfn ^= protnone_mask(pgprot_val(pgprot));
+ pfn &= PHYSICAL_PMD_PAGE_MASK;
+ return __pmd(pfn | massage_pgprot(pgprot));
+}
+
+static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot)
+{
+ phys_addr_t pfn = page_nr << PAGE_SHIFT;
+ pfn ^= protnone_mask(pgprot_val(pgprot));
+ pfn &= PHYSICAL_PUD_PAGE_MASK;
+ return __pud(pfn | massage_pgprot(pgprot));
+}
+
+static inline pmd_t pmd_mknotpresent(pmd_t pmd)
+{
+ return pfn_pmd(pmd_pfn(pmd),
+ __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE)));
}
+static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
+{
+ pudval_t v = native_pud_val(pud);
+
+ return __pud(v | set);
+}
+
+static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear)
+{
+ pudval_t v = native_pud_val(pud);
+
+ return __pud(v & ~clear);
+}
+
+static inline pud_t pud_mkhuge(pud_t pud)
+{
+ return pud_set_flags(pud, _PAGE_PSE);
+}
+
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask);
+
static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
- pteval_t val = pte_val(pte);
+ pteval_t val = pte_val(pte), oldval = val;
/*
* Chop off the NX bit (if present), and add the NX portion of
@@ -379,17 +423,17 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
*/
val &= _PAGE_CHG_MASK;
val |= massage_pgprot(newprot) & ~_PAGE_CHG_MASK;
-
+ val = flip_protnone_guard(oldval, val, PTE_PFN_MASK);
return __pte(val);
}
static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
{
- pmdval_t val = pmd_val(pmd);
+ pmdval_t val = pmd_val(pmd), oldval = val;
val &= _HPAGE_CHG_MASK;
val |= massage_pgprot(newprot) & ~_HPAGE_CHG_MASK;
-
+ val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK);
return __pmd(val);
}
@@ -926,6 +970,14 @@ static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
}
#endif
+#define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1
+extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot);
+
+static inline bool arch_has_pfn_modify_check(void)
+{
+ return boot_cpu_has_bug(X86_BUG_L1TF);
+}
+
#include <asm-generic/pgtable.h>
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index c810226e741a..221a32ed1372 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -163,18 +163,52 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
#define pte_offset_map(dir, address) pte_offset_kernel((dir), (address))
#define pte_unmap(pte) ((void)(pte))/* NOP */
-/* Encode and de-code a swap entry */
-#define SWP_TYPE_BITS 5
-#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1)
+/*
+ * Encode and de-code a swap entry
+ *
+ * | ... | 11| 10| 9|8|7|6|5| 4| 3|2| 1|0| <- bit number
+ * | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names
+ * | TYPE (59-63) | ~OFFSET (9-58) |0|0|X|X| X| X|X|SD|0| <- swp entry
+ *
+ * G (8) is aliased and used as a PROT_NONE indicator for
+ * !present ptes. We need to start storing swap entries above
+ * there. We also need to avoid using A and D because of an
+ * erratum where they can be incorrectly set by hardware on
+ * non-present PTEs.
+ *
+ * SD (1) in swp entry is used to store soft dirty bit, which helps us
+ * remember soft dirty over page migration
+ *
+ * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
+ * but also L and G.
+ *
+ * The offset is inverted by a binary not operation to make the high
+ * physical bits set.
+ */
+#define SWP_TYPE_BITS 5
+
+#define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1)
+
+/* We always extract/encode the offset by shifting it all the way up, and then down again */
+#define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT+SWP_TYPE_BITS)
#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
-#define __swp_type(x) (((x).val >> (_PAGE_BIT_PRESENT + 1)) \
- & ((1U << SWP_TYPE_BITS) - 1))
-#define __swp_offset(x) ((x).val >> SWP_OFFSET_SHIFT)
-#define __swp_entry(type, offset) ((swp_entry_t) { \
- ((type) << (_PAGE_BIT_PRESENT + 1)) \
- | ((offset) << SWP_OFFSET_SHIFT) })
+/* Extract the high bits for type */
+#define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS))
+
+/* Shift up (to get rid of type), then down to get value */
+#define __swp_offset(x) (~(x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT)
+
+/*
+ * Shift the offset up "too far" by TYPE bits, then down again
+ * The offset is inverted by a binary not operation to make the high
+ * physical bits set.
+ */
+#define __swp_entry(type, offset) ((swp_entry_t) { \
+ (~(unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \
+ | ((unsigned long)(type) << (64-SWP_TYPE_BITS)) })
+
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) })
#define __swp_entry_to_pte(x) ((pte_t) { .pte = (x).val })
@@ -201,6 +235,8 @@ extern void cleanup_highmap(void);
extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
+#include <asm/pgtable-invert.h>
+
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_X86_PGTABLE_64_H */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 8dba273da25a..7572ce32055e 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -70,15 +70,15 @@
/*
* Tracking soft dirty bit when a page goes to a swap is tricky.
* We need a bit which can be stored in pte _and_ not conflict
- * with swap entry format. On x86 bits 6 and 7 are *not* involved
- * into swap entry computation, but bit 6 is used for nonlinear
- * file mapping, so we borrow bit 7 for soft dirty tracking.
+ * with swap entry format. On x86 bits 1-4 are *not* involved
+ * into swap entry computation, but bit 7 is used for thp migration,
+ * so we borrow bit 1 for soft dirty tracking.
*
* Please note that this bit must be treated as swap dirty page
- * mark if and only if the PTE has present bit clear!
+ * mark if and only if the PTE/PMD has present bit clear!
*/
#ifdef CONFIG_MEM_SOFT_DIRTY
-#define _PAGE_SWP_SOFT_DIRTY _PAGE_PSE
+#define _PAGE_SWP_SOFT_DIRTY _PAGE_RW
#else
#define _PAGE_SWP_SOFT_DIRTY (_AT(pteval_t, 0))
#endif
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 8e415cf65457..a3a53955f01c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -172,6 +172,11 @@ extern const struct seq_operations cpuinfo_op;
extern void cpu_detect(struct cpuinfo_x86 *c);
+static inline unsigned long l1tf_pfn_limit(void)
+{
+ return BIT(boot_cpu_data.x86_phys_bits - 1 - PAGE_SHIFT) - 1;
+}
+
extern void early_cpu_init(void);
extern void identify_boot_cpu(void);
extern void identify_secondary_cpu(struct cpuinfo_x86 *);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 12a8867071f3..34e4aaaf03d2 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -26,9 +26,11 @@
#include <asm/pgtable.h>
#include <asm/cacheflush.h>
#include <asm/intel-family.h>
+#include <asm/e820.h>
static void __init spectre_v2_select_mitigation(void);
static void __init ssb_select_mitigation(void);
+static void __init l1tf_select_mitigation(void);
/*
* Our boot-time value of the SPEC_CTRL MSR. We read it once so that any
@@ -80,6 +82,8 @@ void __init check_bugs(void)
*/
ssb_select_mitigation();
+ l1tf_select_mitigation();
+
#ifdef CONFIG_X86_32
/*
* Check whether we are able to run this kernel safely on SMP.
@@ -309,23 +313,6 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
return cmd;
}
-/* Check for Skylake-like CPUs (for RSB handling) */
-static bool __init is_skylake_era(void)
-{
- if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
- boot_cpu_data.x86 == 6) {
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_SKYLAKE_MOBILE:
- case INTEL_FAM6_SKYLAKE_DESKTOP:
- case INTEL_FAM6_SKYLAKE_X:
- case INTEL_FAM6_KABYLAKE_MOBILE:
- case INTEL_FAM6_KABYLAKE_DESKTOP:
- return true;
- }
- }
- return false;
-}
-
static void __init spectre_v2_select_mitigation(void)
{
enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -386,22 +373,15 @@ retpoline_auto:
pr_info("%s\n", spectre_v2_strings[mode]);
/*
- * If neither SMEP nor PTI are available, there is a risk of
- * hitting userspace addresses in the RSB after a context switch
- * from a shallow call stack to a deeper one. To prevent this fill
- * the entire RSB, even when using IBRS.
+ * If spectre v2 protection has been enabled, unconditionally fill
+ * RSB during a context switch; this protects against two independent
+ * issues:
*
- * Skylake era CPUs have a separate issue with *underflow* of the
- * RSB, when they will predict 'ret' targets from the generic BTB.
- * The proper mitigation for this is IBRS. If IBRS is not supported
- * or deactivated in favour of retpolines the RSB fill on context
- * switch is required.
+ * - RSB underflow (and switch to BTB) on Skylake+
+ * - SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs
*/
- if ((!boot_cpu_has(X86_FEATURE_KAISER) &&
- !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
- setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
- pr_info("Spectre v2 mitigation: Filling RSB on context switch\n");
- }
+ setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
+ pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
/* Initialize Indirect Branch Prediction Barrier if supported */
if (boot_cpu_has(X86_FEATURE_IBPB)) {
@@ -652,6 +632,35 @@ void x86_spec_ctrl_setup_ap(void)
x86_amd_ssb_disable();
}
+#undef pr_fmt
+#define pr_fmt(fmt) "L1TF: " fmt
+static void __init l1tf_select_mitigation(void)
+{
+ u64 half_pa;
+
+ if (!boot_cpu_has_bug(X86_BUG_L1TF))
+ return;
+
+#if CONFIG_PGTABLE_LEVELS == 2
+ pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n");
+ return;
+#endif
+
+ /*
+ * This is extremely unlikely to happen because almost all
+ * systems have far more MAX_PA/2 than RAM can be fit into
+ * DIMM slots.
+ */
+ half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT;
+ if (e820_any_mapped(half_pa, ULLONG_MAX - half_pa, E820_RAM)) {
+ pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n");
+ return;
+ }
+
+ setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV);
+}
+#undef pr_fmt
+
#ifdef CONFIG_SYSFS
static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
@@ -679,6 +688,11 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
case X86_BUG_SPEC_STORE_BYPASS:
return sprintf(buf, "%s\n", ssb_strings[ssb_mode]);
+ case X86_BUG_L1TF:
+ if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV))
+ return sprintf(buf, "Mitigation: Page Table Inversion\n");
+ break;
+
default:
break;
}
@@ -705,4 +719,9 @@ ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *
{
return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS);
}
+
+ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_common(dev, attr, buf, X86_BUG_L1TF);
+}
#endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 3d21b28f9826..4d3fa79c0f09 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -880,6 +880,21 @@ static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
{}
};
+static const __initconst struct x86_cpu_id cpu_no_l1tf[] = {
+ /* in addition to cpu_no_speculation */
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MOOREFIELD },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_DENVERTON },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GEMINI_LAKE },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM },
+ {}
+};
+
static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
{
u64 ia32_cap = 0;
@@ -905,6 +920,11 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
return;
setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
+
+ if (x86_match_cpu(cpu_no_l1tf))
+ return;
+
+ setup_force_cpu_bug(X86_BUG_L1TF);
}
/*
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 1f5c47a49e35..c6f466d6cc57 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -393,7 +393,6 @@ int __copy_instruction(u8 *dest, u8 *src)
newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest;
if ((s64) (s32) newdisp != newdisp) {
pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp);
- pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", src, dest, insn.displacement.value);
return 0;
}
disp = (u8 *) dest + insn_offset_displacement(&insn);
@@ -609,8 +608,7 @@ static int reenter_kprobe(struct kprobe *p, struct pt_regs *regs,
* Raise a BUG or we'll continue in an endless reentering loop
* and eventually a stack overflow.
*/
- printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n",
- p->addr);
+ pr_err("Unrecoverable kprobe detected.\n");
dump_kprobe(p);
BUG();
default:
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index f534a0e3af53..632195b41688 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -97,10 +97,12 @@ unsigned paravirt_patch_call(void *insnbuf,
struct branch *b = insnbuf;
unsigned long delta = (unsigned long)target - (addr+5);
- if (tgt_clobbers & ~site_clobbers)
- return len; /* target would clobber too much for this site */
- if (len < 5)
+ if (len < 5) {
+#ifdef CONFIG_RETPOLINE
+ WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr);
+#endif
return len; /* call too long for patch site */
+ }
b->opcode = 0xe8; /* call */
b->delta = delta;
@@ -115,8 +117,12 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
struct branch *b = insnbuf;
unsigned long delta = (unsigned long)target - (addr+5);
- if (len < 5)
+ if (len < 5) {
+#ifdef CONFIG_RETPOLINE
+ WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr);
+#endif
return len; /* call too long for patch site */
+ }
b->opcode = 0xe9; /* jmp */
b->delta = delta;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index bbaae4cf9e8e..31c4bc0d3372 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -851,6 +851,12 @@ void __init setup_arch(char **cmdline_p)
memblock_reserve(__pa_symbol(_text),
(unsigned long)__bss_stop - (unsigned long)_text);
+ /*
+ * Make sure page 0 is always reserved because on systems with
+ * L1TF its contents can be leaked to user processes.
+ */
+ memblock_reserve(0, PAGE_SIZE);
+
early_reserve_initrd();
/*
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 151fd33e9043..4954a6cef50a 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -4,6 +4,8 @@
#include <linux/swap.h>
#include <linux/memblock.h>
#include <linux/bootmem.h> /* for max_low_pfn */
+#include <linux/swapfile.h>
+#include <linux/swapops.h>
#include <asm/cacheflush.h>
#include <asm/e820.h>
@@ -767,3 +769,26 @@ void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache)
__cachemode2pte_tbl[cache] = __cm_idx2pte(entry);
__pte2cachemode_tbl[entry] = cache;
}
+
+#ifdef CONFIG_SWAP
+unsigned long max_swapfile_size(void)
+{
+ unsigned long pages;
+
+ pages = generic_max_swapfile_size();
+
+ if (boot_cpu_has_bug(X86_BUG_L1TF)) {
+ /* Limit the swap file size to MAX_PA/2 for L1TF workaround */
+ unsigned long l1tf_limit = l1tf_pfn_limit() + 1;
+ /*
+ * We encode swap offsets also with 3 bits below those for pfn
+ * which makes the usable limit higher.
+ */
+#if CONFIG_PGTABLE_LEVELS > 2
+ l1tf_limit <<= PAGE_SHIFT - SWP_OFFSET_FIRST_BIT;
+#endif
+ pages = min_t(unsigned long, l1tf_limit, pages);
+ }
+ return pages;
+}
+#endif
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 76604c8a2a48..7bf14e74fc8f 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -125,24 +125,29 @@ static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long addr)
static void clear_pmd_presence(pmd_t *pmd, bool clear, pmdval_t *old)
{
+ pmd_t new_pmd;
pmdval_t v = pmd_val(*pmd);
if (clear) {
- *old = v & _PAGE_PRESENT;
- v &= ~_PAGE_PRESENT;
- } else /* presume this has been called with clear==true previously */
- v |= *old;
- set_pmd(pmd, __pmd(v));
+ *old = v;
+ new_pmd = pmd_mknotpresent(*pmd);
+ } else {
+ /* Presume this has been called with clear==true previously */
+ new_pmd = __pmd(*old);
+ }
+ set_pmd(pmd, new_pmd);
}
static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old)
{
pteval_t v = pte_val(*pte);
if (clear) {
- *old = v & _PAGE_PRESENT;
- v &= ~_PAGE_PRESENT;
- } else /* presume this has been called with clear==true previously */
- v |= *old;
- set_pte_atomic(pte, __pte(v));
+ *old = v;
+ /* Nothing should care about address */
+ pte_clear(&init_mm, 0, pte);
+ } else {
+ /* Presume this has been called with clear==true previously */
+ set_pte_atomic(pte, __pte(*old));
+ }
}
static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 307f60ecfc6d..9a055ea279eb 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -121,3 +121,24 @@ const char *arch_vma_name(struct vm_area_struct *vma)
return "[mpx]";
return NULL;
}
+
+/*
+ * Only allow root to set high MMIO mappings to PROT_NONE.
+ * This prevents an unpriv. user to set them to PROT_NONE and invert
+ * them, then pointing to valid memory for L1TF speculation.
+ *
+ * Note: for locked down kernels may want to disable the root override.
+ */
+bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
+{
+ if (!boot_cpu_has_bug(X86_BUG_L1TF))
+ return true;
+ if (!__pte_needs_invert(pgprot_val(prot)))
+ return true;
+ /* If it's real memory always allow */
+ if (pfn_valid(pfn))
+ return true;
+ if (pfn > l1tf_pfn_limit() && !capable(CAP_SYS_ADMIN))
+ return false;
+ return true;
+}
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 79377e2a7bcd..27610c2d1821 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -1006,8 +1006,8 @@ static int populate_pmd(struct cpa_data *cpa,
pmd = pmd_offset(pud, start);
- set_pmd(pmd, __pmd(cpa->pfn | _PAGE_PSE |
- massage_pgprot(pmd_pgprot)));
+ set_pmd(pmd, pmd_mkhuge(pfn_pmd(cpa->pfn,
+ canon_pgprot(pmd_pgprot))));
start += PMD_SIZE;
cpa->pfn += PMD_SIZE;
@@ -1079,8 +1079,8 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
* Map everything starting from the Gb boundary, possibly with 1G pages
*/
while (end - start >= PUD_SIZE) {
- set_pud(pud, __pud(cpa->pfn | _PAGE_PSE |
- massage_pgprot(pud_pgprot)));
+ set_pud(pud, pud_mkhuge(pfn_pud(cpa->pfn,
+ canon_pgprot(pud_pgprot))));
start += PUD_SIZE;
cpa->pfn += PUD_SIZE;
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index f9e0d09f7c66..8a0f77fb5181 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -154,10 +154,12 @@ static const struct lpss_device_desc lpt_sdio_dev_desc = {
static const struct lpss_device_desc byt_pwm_dev_desc = {
.flags = LPSS_SAVE_CTX,
+ .prv_offset = 0x800,
};
static const struct lpss_device_desc bsw_pwm_dev_desc = {
.flags = LPSS_SAVE_CTX | LPSS_NO_D3_DELAY,
+ .prv_offset = 0x800,
};
static const struct lpss_device_desc byt_uart_dev_desc = {
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 143edea1076f..41090ef5facb 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -524,16 +524,24 @@ ssize_t __weak cpu_show_spec_store_bypass(struct device *dev,
return sprintf(buf, "Not affected\n");
}
+ssize_t __weak cpu_show_l1tf(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sprintf(buf, "Not affected\n");
+}
+
static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL);
+static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL);
static struct attribute *cpu_root_vulnerabilities_attrs[] = {
&dev_attr_meltdown.attr,
&dev_attr_spectre_v1.attr,
&dev_attr_spectre_v2.attr,
&dev_attr_spec_store_bypass.attr,
+ &dev_attr_l1tf.attr,
NULL
};
diff --git a/drivers/char/tpm/tpm-dev.c b/drivers/char/tpm/tpm-dev.c
index 912ad30be585..4719aa781bf2 100644
--- a/drivers/char/tpm/tpm-dev.c
+++ b/drivers/char/tpm/tpm-dev.c
@@ -25,7 +25,7 @@ struct file_priv {
struct tpm_chip *chip;
/* Data passed to and from the tpm via the read/write calls */
- atomic_t data_pending;
+ size_t data_pending;
struct mutex buffer_mutex;
struct timer_list user_read_timer; /* user needs to claim result */
@@ -46,7 +46,7 @@ static void timeout_work(struct work_struct *work)
struct file_priv *priv = container_of(work, struct file_priv, work);
mutex_lock(&priv->buffer_mutex);
- atomic_set(&priv->data_pending, 0);
+ priv->data_pending = 0;
memset(priv->data_buffer, 0, sizeof(priv->data_buffer));
mutex_unlock(&priv->buffer_mutex);
}
@@ -72,7 +72,6 @@ static int tpm_open(struct inode *inode, struct file *file)
}
priv->chip = chip;
- atomic_set(&priv->data_pending, 0);
mutex_init(&priv->buffer_mutex);
setup_timer(&priv->user_read_timer, user_reader_timeout,
(unsigned long)priv);
@@ -86,28 +85,24 @@ static ssize_t tpm_read(struct file *file, char __user *buf,
size_t size, loff_t *off)
{
struct file_priv *priv = file->private_data;
- ssize_t ret_size;
+ ssize_t ret_size = 0;
int rc;
del_singleshot_timer_sync(&priv->user_read_timer);
flush_work(&priv->work);
- ret_size = atomic_read(&priv->data_pending);
- if (ret_size > 0) { /* relay data */
- ssize_t orig_ret_size = ret_size;
- if (size < ret_size)
- ret_size = size;
+ mutex_lock(&priv->buffer_mutex);
- mutex_lock(&priv->buffer_mutex);
+ if (priv->data_pending) {
+ ret_size = min_t(ssize_t, size, priv->data_pending);
rc = copy_to_user(buf, priv->data_buffer, ret_size);
- memset(priv->data_buffer, 0, orig_ret_size);
+ memset(priv->data_buffer, 0, priv->data_pending);
if (rc)
ret_size = -EFAULT;
- mutex_unlock(&priv->buffer_mutex);
+ priv->data_pending = 0;
}
- atomic_set(&priv->data_pending, 0);
-
+ mutex_unlock(&priv->buffer_mutex);
return ret_size;
}
@@ -118,18 +113,20 @@ static ssize_t tpm_write(struct file *file, const char __user *buf,
size_t in_size = size;
ssize_t out_size;
- /* cannot perform a write until the read has cleared
- either via tpm_read or a user_read_timer timeout.
- This also prevents splitted buffered writes from blocking here.
- */
- if (atomic_read(&priv->data_pending) != 0)
- return -EBUSY;
-
if (in_size > TPM_BUFSIZE)
return -E2BIG;
mutex_lock(&priv->buffer_mutex);
+ /* Cannot perform a write until the read has cleared either via
+ * tpm_read or a user_read_timer timeout. This also prevents split
+ * buffered writes from blocking here.
+ */
+ if (priv->data_pending != 0) {
+ mutex_unlock(&priv->buffer_mutex);
+ return -EBUSY;
+ }
+
if (copy_from_user
(priv->data_buffer, (void __user *) buf, in_size)) {
mutex_unlock(&priv->buffer_mutex);
@@ -153,7 +150,7 @@ static ssize_t tpm_write(struct file *file, const char __user *buf,
return out_size;
}
- atomic_set(&priv->data_pending, out_size);
+ priv->data_pending = out_size;
mutex_unlock(&priv->buffer_mutex);
/* Set a timeout by which the reader must come claim the result */
@@ -172,7 +169,7 @@ static int tpm_release(struct inode *inode, struct file *file)
del_singleshot_timer_sync(&priv->user_read_timer);
flush_work(&priv->work);
file->private_data = NULL;
- atomic_set(&priv->data_pending, 0);
+ priv->data_pending = 0;
clear_bit(0, &priv->chip->is_open);
kfree(priv);
return 0;
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 6790ebb366dd..98fd9a594841 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -122,16 +122,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
umem->address = addr;
umem->page_size = PAGE_SIZE;
umem->pid = get_task_pid(current, PIDTYPE_PID);
- /*
- * We ask for writable memory if any of the following
- * access flags are set. "Local write" and "remote write"
- * obviously require write access. "Remote atomic" can do
- * things like fetch and add, which will modify memory, and
- * "MW bind" can change permissions by binding a window.
- */
- umem->writable = !!(access &
- (IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE |
- IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND));
+ umem->writable = ib_access_writable(access);
if (access & IB_ACCESS_ON_DEMAND) {
put_pid(umem->pid);
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index ce87e9cc7eff..bf52e35dd506 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -130,6 +130,40 @@ out:
return err;
}
+static struct ib_umem *mlx4_get_umem_mr(struct ib_ucontext *context, u64 start,
+ u64 length, u64 virt_addr,
+ int access_flags)
+{
+ /*
+ * Force registering the memory as writable if the underlying pages
+ * are writable. This is so rereg can change the access permissions
+ * from readable to writable without having to run through ib_umem_get
+ * again
+ */
+ if (!ib_access_writable(access_flags)) {
+ struct vm_area_struct *vma;
+
+ down_read(¤t->mm->mmap_sem);
+ /*
+ * FIXME: Ideally this would iterate over all the vmas that
+ * cover the memory, but for now it requires a single vma to
+ * entirely cover the MR to support RO mappings.
+ */
+ vma = find_vma(current->mm, start);
+ if (vma && vma->vm_end >= start + length &&
+ vma->vm_start <= start) {
+ if (vma->vm_flags & VM_WRITE)
+ access_flags |= IB_ACCESS_LOCAL_WRITE;
+ } else {
+ access_flags |= IB_ACCESS_LOCAL_WRITE;
+ }
+
+ up_read(¤t->mm->mmap_sem);
+ }
+
+ return ib_umem_get(context, start, length, access_flags, 0);
+}
+
struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
u64 virt_addr, int access_flags,
struct ib_udata *udata)
@@ -144,10 +178,8 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
if (!mr)
return ERR_PTR(-ENOMEM);
- /* Force registering the memory as writable. */
- /* Used for memory re-registeration. HCA protects the access */
- mr->umem = ib_umem_get(pd->uobject->context, start, length,
- access_flags | IB_ACCESS_LOCAL_WRITE, 0);
+ mr->umem = mlx4_get_umem_mr(pd->uobject->context, start, length,
+ virt_addr, access_flags);
if (IS_ERR(mr->umem)) {
err = PTR_ERR(mr->umem);
goto err_free;
@@ -214,6 +246,9 @@ int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags,
}
if (flags & IB_MR_REREG_ACCESS) {
+ if (ib_access_writable(mr_access_flags) && !mmr->umem->writable)
+ return -EPERM;
+
err = mlx4_mr_hw_change_access(dev->dev, *pmpt_entry,
convert_access(mr_access_flags));
@@ -227,10 +262,9 @@ int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags,
mlx4_mr_rereg_mem_cleanup(dev->dev, &mmr->mmr);
ib_umem_release(mmr->umem);
- mmr->umem = ib_umem_get(mr->uobject->context, start, length,
- mr_access_flags |
- IB_ACCESS_LOCAL_WRITE,
- 0);
+ mmr->umem =
+ mlx4_get_umem_mr(mr->uobject->context, start, length,
+ virt_addr, mr_access_flags);
if (IS_ERR(mmr->umem)) {
err = PTR_ERR(mmr->umem);
/* Prevent mlx4_ib_dereg_mr from free'ing invalid pointer */
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
index 748b63b86cbc..40242ead096f 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
@@ -643,7 +643,7 @@ static ssize_t ocrdma_dbgfs_ops_write(struct file *filp,
struct ocrdma_stats *pstats = filp->private_data;
struct ocrdma_dev *dev = pstats->dev;
- if (count > 32)
+ if (*ppos != 0 || count == 0 || count > sizeof(tmp_str))
goto err;
if (copy_from_user(tmp_str, buffer, count))
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index bec9f099573b..68d0a5c9d437 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -879,7 +879,6 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
struct sk_buff *skb,
struct sk_buff_head *list)
{
- struct skb_shared_info *shinfo = skb_shinfo(skb);
RING_IDX cons = queue->rx.rsp_cons;
struct sk_buff *nskb;
@@ -888,15 +887,16 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
RING_GET_RESPONSE(&queue->rx, ++cons);
skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0];
- if (shinfo->nr_frags == MAX_SKB_FRAGS) {
+ if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) {
unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
BUG_ON(pull_to <= skb_headlen(skb));
__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
}
- BUG_ON(shinfo->nr_frags >= MAX_SKB_FRAGS);
+ BUG_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS);
- skb_add_rx_frag(skb, shinfo->nr_frags, skb_frag_page(nfrag),
+ skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+ skb_frag_page(nfrag),
rx->offset, rx->status, PAGE_SIZE);
skb_shinfo(nskb)->nr_frags = 0;
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index de53c9694b68..5dc288fecace 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -520,18 +520,26 @@ static int sr_init_command(struct scsi_cmnd *SCpnt)
static int sr_block_open(struct block_device *bdev, fmode_t mode)
{
struct scsi_cd *cd;
+ struct scsi_device *sdev;
int ret = -ENXIO;
+ cd = scsi_cd_get(bdev->bd_disk);
+ if (!cd)
+ goto out;
+
+ sdev = cd->device;
+ scsi_autopm_get_device(sdev);
check_disk_change(bdev);
mutex_lock(&sr_mutex);
- cd = scsi_cd_get(bdev->bd_disk);
- if (cd) {
- ret = cdrom_open(&cd->cdi, bdev, mode);
- if (ret)
- scsi_cd_put(cd);
- }
+ ret = cdrom_open(&cd->cdi, bdev, mode);
mutex_unlock(&sr_mutex);
+
+ scsi_autopm_put_device(sdev);
+ if (ret)
+ scsi_cd_put(cd);
+
+out:
return ret;
}
@@ -559,6 +567,8 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
if (ret)
goto out;
+ scsi_autopm_get_device(sdev);
+
/*
* Send SCSI addressing ioctls directly to mid level, send other
* ioctls to cdrom/block level.
@@ -567,15 +577,18 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
case SCSI_IOCTL_GET_IDLUN:
case SCSI_IOCTL_GET_BUS_NUMBER:
ret = scsi_ioctl(sdev, cmd, argp);
- goto out;
+ goto put;
}
ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg);
if (ret != -ENOSYS)
- goto out;
+ goto put;
ret = scsi_ioctl(sdev, cmd, argp);
+put:
+ scsi_autopm_put_device(sdev);
+
out:
mutex_unlock(&sr_mutex);
return ret;
diff --git a/fs/dcache.c b/fs/dcache.c
index 250c1222e30c..807efaab838e 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1954,10 +1954,12 @@ struct dentry *d_make_root(struct inode *root_inode)
static const struct qstr name = QSTR_INIT("/", 1);
res = __d_alloc(root_inode->i_sb, &name);
- if (res)
+ if (res) {
+ res->d_flags |= DCACHE_RCUACCESS;
d_instantiate(res, root_inode);
- else
+ } else {
iput(root_inode);
+ }
}
return res;
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 041117fd8fd7..0963213e9cd3 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1308,7 +1308,10 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
ext4_itable_unused_count(sb, gdp)),
sbi->s_inodes_per_block);
- if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) {
+ if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group) ||
+ ((group == 0) && ((EXT4_INODES_PER_GROUP(sb) -
+ ext4_itable_unused_count(sb, gdp)) <
+ EXT4_FIRST_INO(sb)))) {
ext4_error(sb, "Something is wrong with group %u: "
"used itable blocks: %d; "
"itable unused count: %u",
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3e4d8ac1974e..8d18f6142da5 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2875,14 +2875,8 @@ static ext4_group_t ext4_has_uninit_itable(struct super_block *sb)
if (!gdp)
continue;
- if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))
- continue;
- if (group != 0)
+ if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
break;
- ext4_error(sb, "Inode table for bg 0 marked as "
- "needing zeroing");
- if (sb->s_flags & MS_RDONLY)
- return ngroups;
}
return group;
diff --git a/fs/namespace.c b/fs/namespace.c
index a879560ea144..b56b50e3da11 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -603,12 +603,21 @@ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq)
return 0;
mnt = real_mount(bastard);
mnt_add_count(mnt, 1);
+ smp_mb(); // see mntput_no_expire()
if (likely(!read_seqretry(&mount_lock, seq)))
return 0;
if (bastard->mnt_flags & MNT_SYNC_UMOUNT) {
mnt_add_count(mnt, -1);
return 1;
}
+ lock_mount_hash();
+ if (unlikely(bastard->mnt_flags & MNT_DOOMED)) {
+ mnt_add_count(mnt, -1);
+ unlock_mount_hash();
+ return 1;
+ }
+ unlock_mount_hash();
+ /* caller will mntput() */
return -1;
}
@@ -1124,12 +1133,27 @@ static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput);
static void mntput_no_expire(struct mount *mnt)
{
rcu_read_lock();
- mnt_add_count(mnt, -1);
- if (likely(mnt->mnt_ns)) { /* shouldn't be the last one */
+ if (likely(READ_ONCE(mnt->mnt_ns))) {
+ /*
+ * Since we don't do lock_mount_hash() here,
+ * ->mnt_ns can change under us. However, if it's
+ * non-NULL, then there's a reference that won't
+ * be dropped until after an RCU delay done after
+ * turning ->mnt_ns NULL. So if we observe it
+ * non-NULL under rcu_read_lock(), the reference
+ * we are dropping is not the final one.
+ */
+ mnt_add_count(mnt, -1);
rcu_read_unlock();
return;
}
lock_mount_hash();
+ /*
+ * make sure that if __legitimize_mnt() has not seen us grab
+ * mount_lock, we'll see their refcount increment here.
+ */
+ smp_mb();
+ mnt_add_count(mnt, -1);
if (mnt_get_count(mnt)) {
rcu_read_unlock();
unlock_mount_hash();
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 25b793325b09..dabecb661264 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -799,6 +799,18 @@ static inline int pmd_free_pte_page(pmd_t *pmd)
}
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
+#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED
+static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
+{
+ return true;
+}
+
+static inline bool arch_has_pfn_modify_check(void)
+{
+ return false;
+}
+#endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */
+
#endif /* !__ASSEMBLY__ */
#ifndef io_remap_pfn_range
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 2f9d12022100..063c73ed6d78 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -48,6 +48,8 @@ extern ssize_t cpu_show_spectre_v2(struct device *dev,
struct device_attribute *attr, char *buf);
extern ssize_t cpu_show_spec_store_bypass(struct device *dev,
struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_l1tf(struct device *dev,
+ struct device_attribute *attr, char *buf);
extern __printf(4, 5)
struct device *cpu_device_create(struct device *parent, void *drvdata,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a100946607a5..1f4366567e7d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2083,6 +2083,8 @@ int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn);
+int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
+ unsigned long pfn, pgprot_t pgprot);
int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn);
int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h
index 388293a91e8c..e4594de79bc4 100644
--- a/include/linux/swapfile.h
+++ b/include/linux/swapfile.h
@@ -9,5 +9,7 @@ extern spinlock_t swap_lock;
extern struct plist_head swap_active_head;
extern struct swap_info_struct *swap_info[];
extern int try_to_unuse(unsigned int, bool, unsigned long);
+extern unsigned long generic_max_swapfile_size(void);
+extern unsigned long max_swapfile_size(void);
#endif /* _LINUX_SWAPFILE_H */
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index ff307b548ed3..646891f3bc1e 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -55,11 +55,7 @@ extern long do_no_restart_syscall(struct restart_block *parm);
#ifdef __KERNEL__
-#ifdef CONFIG_DEBUG_STACK_USAGE
-# define THREADINFO_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
-#else
-# define THREADINFO_GFP (GFP_KERNEL | __GFP_NOTRACK)
-#endif
+#define THREADINFO_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
/*
* flag set/clear/test wrappers
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 120da1d7f57e..10fefb0dc640 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -3007,6 +3007,20 @@ static inline int ib_check_mr_access(int flags)
return 0;
}
+static inline bool ib_access_writable(int access_flags)
+{
+ /*
+ * We have writable memory backing the MR if any of the following
+ * access flags are set. "Local write" and "remote write" obviously
+ * require write access. "Remote atomic" can do things like fetch and
+ * add, which will modify memory, and "MW bind" can change permissions
+ * by binding a window.
+ */
+ return access_flags &
+ (IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE |
+ IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND);
+}
+
/**
* ib_check_mr_status: lightweight check of MR status.
* This routine may provide status checks on a selected
diff --git a/mm/memory.c b/mm/memory.c
index 177cb7d111a9..d5bb1465d30c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1604,9 +1604,30 @@ out:
*/
int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn)
+{
+ return vm_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_insert_pfn);
+
+/**
+ * vm_insert_pfn_prot - insert single pfn into user vma with specified pgprot
+ * @vma: user vma to map to
+ * @addr: target user address of this page
+ * @pfn: source kernel pfn
+ * @pgprot: pgprot flags for the inserted page
+ *
+ * This is exactly like vm_insert_pfn, except that it allows drivers to
+ * to override pgprot on a per-page basis.
+ *
+ * This only makes sense for IO mappings, and it makes no sense for
+ * cow mappings. In general, using multiple vmas is preferable;
+ * vm_insert_pfn_prot should only be used if using multiple VMAs is
+ * impractical.
+ */
+int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
+ unsigned long pfn, pgprot_t pgprot)
{
int ret;
- pgprot_t pgprot = vma->vm_page_prot;
/*
* Technically, architectures with pte_special can avoid all these
* restrictions (same for remap_pfn_range). However we would like
@@ -1624,19 +1645,29 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
if (track_pfn_insert(vma, &pgprot, pfn))
return -EINVAL;
+ if (!pfn_modify_allowed(pfn, pgprot))
+ return -EACCES;
+
ret = insert_pfn(vma, addr, pfn, pgprot);
return ret;
}
-EXPORT_SYMBOL(vm_insert_pfn);
+EXPORT_SYMBOL(vm_insert_pfn_prot);
int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn)
{
+ pgprot_t pgprot = vma->vm_page_prot;
+
BUG_ON(!(vma->vm_flags & VM_MIXEDMAP));
if (addr < vma->vm_start || addr >= vma->vm_end)
return -EFAULT;
+ if (track_pfn_insert(vma, &pgprot, pfn))
+ return -EINVAL;
+
+ if (!pfn_modify_allowed(pfn, pgprot))
+ return -EACCES;
/*
* If we don't have pte special, then we have to use the pfn_valid()
@@ -1649,9 +1680,9 @@ int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
struct page *page;
page = pfn_to_page(pfn);
- return insert_page(vma, addr, page, vma->vm_page_prot);
+ return insert_page(vma, addr, page, pgprot);
}
- return insert_pfn(vma, addr, pfn, vma->vm_page_prot);
+ return insert_pfn(vma, addr, pfn, pgprot);
}
EXPORT_SYMBOL(vm_insert_mixed);
@@ -1666,6 +1697,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
{
pte_t *pte;
spinlock_t *ptl;
+ int err = 0;
pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
if (!pte)
@@ -1673,12 +1705,16 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
arch_enter_lazy_mmu_mode();
do {
BUG_ON(!pte_none(*pte));
+ if (!pfn_modify_allowed(pfn, prot)) {
+ err = -EACCES;
+ break;
+ }
set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot)));
pfn++;
} while (pte++, addr += PAGE_SIZE, addr != end);
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(pte - 1, ptl);
- return 0;
+ return err;
}
static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
@@ -1687,6 +1723,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
{
pmd_t *pmd;
unsigned long next;
+ int err;
pfn -= addr >> PAGE_SHIFT;
pmd = pmd_alloc(mm, pud, addr);
@@ -1695,9 +1732,10 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
VM_BUG_ON(pmd_trans_huge(*pmd));
do {
next = pmd_addr_end(addr, end);
- if (remap_pte_range(mm, pmd, addr, next,
- pfn + (addr >> PAGE_SHIFT), prot))
- return -ENOMEM;
+ err = remap_pte_range(mm, pmd, addr, next,
+ pfn + (addr >> PAGE_SHIFT), prot);
+ if (err)
+ return err;
} while (pmd++, addr = next, addr != end);
return 0;
}
@@ -1708,6 +1746,7 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
{
pud_t *pud;
unsigned long next;
+ int err;
pfn -= addr >> PAGE_SHIFT;
pud = pud_alloc(mm, pgd, addr);
@@ -1715,9 +1754,10 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
- if (remap_pmd_range(mm, pud, addr, next,
- pfn + (addr >> PAGE_SHIFT), prot))
- return -ENOMEM;
+ err = remap_pmd_range(mm, pud, addr, next,
+ pfn + (addr >> PAGE_SHIFT), prot);
+ if (err)
+ return err;
} while (pud++, addr = next, addr != end);
return 0;
}
diff --git a/mm/mprotect.c b/mm/mprotect.c
index c0b4b2a49462..a277f3412a5d 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -255,6 +255,42 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
return pages;
}
+static int prot_none_pte_entry(pte_t *pte, unsigned long addr,
+ unsigned long next, struct mm_walk *walk)
+{
+ return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ?
+ 0 : -EACCES;
+}
+
+static int prot_none_hugetlb_entry(pte_t *pte, unsigned long hmask,
+ unsigned long addr, unsigned long next,
+ struct mm_walk *walk)
+{
+ return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ?
+ 0 : -EACCES;
+}
+
+static int prot_none_test(unsigned long addr, unsigned long next,
+ struct mm_walk *walk)
+{
+ return 0;
+}
+
+static int prot_none_walk(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end, unsigned long newflags)
+{
+ pgprot_t new_pgprot = vm_get_page_prot(newflags);
+ struct mm_walk prot_none_walk = {
+ .pte_entry = prot_none_pte_entry,
+ .hugetlb_entry = prot_none_hugetlb_entry,
+ .test_walk = prot_none_test,
+ .mm = current->mm,
+ .private = &new_pgprot,
+ };
+
+ return walk_page_range(start, end, &prot_none_walk);
+}
+
int
mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
unsigned long start, unsigned long end, unsigned long newflags)
@@ -272,6 +308,19 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
return 0;
}
+ /*
+ * Do PROT_NONE PFN permission checks here when we can still
+ * bail out without undoing a lot of state. This is a rather
+ * uncommon case, so doesn't need to be very optimized.
+ */
+ if (arch_has_pfn_modify_check() &&
+ (vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) &&
+ (newflags & (VM_READ|VM_WRITE|VM_EXEC)) == 0) {
+ error = prot_none_walk(vma, start, end, newflags);
+ if (error)
+ return error;
+ }
+
/*
* If we make a private mapping writable we increase our commit;
* but (without finer accounting) cannot reduce our commit if we
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 674bf177ce44..8e25ff2b693a 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2206,6 +2206,35 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
return 0;
}
+
+/*
+ * Find out how many pages are allowed for a single swap device. There
+ * are two limiting factors:
+ * 1) the number of bits for the swap offset in the swp_entry_t type, and
+ * 2) the number of bits in the swap pte, as defined by the different
+ * architectures.
+ *
+ * In order to find the largest possible bit mask, a swap entry with
+ * swap type 0 and swap offset ~0UL is created, encoded to a swap pte,
+ * decoded to a swp_entry_t again, and finally the swap offset is
+ * extracted.
+ *
+ * This will mask all the bits from the initial ~0UL mask that can't
+ * be encoded in either the swp_entry_t or the architecture definition
+ * of a swap pte.
+ */
+unsigned long generic_max_swapfile_size(void)
+{
+ return swp_offset(pte_to_swp_entry(
+ swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
+}
+
+/* Can be overridden by an architecture for additional checks. */
+__weak unsigned long max_swapfile_size(void)
+{
+ return generic_max_swapfile_size();
+}
+
static unsigned long read_swap_header(struct swap_info_struct *p,
union swap_header *swap_header,
struct inode *inode)
@@ -2241,22 +2270,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p,
p->cluster_next = 1;
p->cluster_nr = 0;
- /*
- * Find out how many pages are allowed for a single swap
- * device. There are two limiting factors: 1) the number
- * of bits for the swap offset in the swp_entry_t type, and
- * 2) the number of bits in the swap pte as defined by the
- * different architectures. In order to find the
- * largest possible bit mask, a swap entry with swap type 0
- * and swap offset ~0UL is created, encoded to a swap pte,
- * decoded to a swp_entry_t again, and finally the swap
- * offset is extracted. This will mask all the bits from
- * the initial ~0UL mask that can't be encoded in either
- * the swp_entry_t or the architecture definition of a
- * swap pte.
- */
- maxpages = swp_offset(pte_to_swp_entry(
- swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
+ maxpages = max_swapfile_size();
last_page = swap_header->info.last_page;
if (!last_page) {
pr_warn("Empty swap-file\n");
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 93581bba8643..09d6c4a6b53d 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -354,6 +354,7 @@ config INET_ESP
select CRYPTO_CBC
select CRYPTO_SHA1
select CRYPTO_DES
+ select CRYPTO_ECHAINIV
---help---
Support for IPsec ESP.
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 851d5c9e3ecc..0f50248bad17 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -69,6 +69,7 @@ config INET6_ESP
select CRYPTO_CBC
select CRYPTO_SHA1
select CRYPTO_DES
+ select CRYPTO_ECHAINIV
---help---
Support for IPsec ESP.