[PATCH 4.14 0/8] CVE-2020-4788: Speculation on incompletely validated data on IBM Power9

[PATCH 4.14 0/8] CVE-2020-4788: Speculation on incompletely validated data on IBM Power9

[Daniel Axtens]

IBM Power9 processors can speculatively operate on data in the L1
cache before it has been completely validated, via a way-prediction
mechanism. It is not possible for an attacker to determine the
contents of impermissible memory using this method, since these
systems implement a combination of hardware and software security
measures to prevent scenarios where protected data could be leaked.

However these measures don't address the scenario where an attacker
induces the operating system to speculatively execute instructions
using data that the attacker controls. This can be used for example to
speculatively bypass "kernel user access prevention" techniques, as
discovered by Anthony Steinhauser of Google's Safeside Project. This
is not an attack by itself, but there is a possibility it could be
used in conjunction with side-channels or other weaknesses in the
privileged code to construct an attack.

This issue can be mitigated by flushing the L1 cache between privilege
boundaries of concern. This series flushes the cache on kernel entry and
after kernel user accesses.

Thanks to Nick Piggin, Russell Currey, Christopher M. Riedl, Michael
Ellerman and Spoorthy S for their work in developing, optimising,
testing and backporting these fixes, and to the many others who helped
behind the scenes.

Andrew Donnellan (1):
  powerpc: Fix __clear_user() with KUAP enabled

Christophe Leroy (2):
  powerpc: Add a framework for user access tracking
  powerpc: Implement user_access_begin and friends

Daniel Axtens (2):
  powerpc/64s: Define MASKABLE_RELON_EXCEPTION_PSERIES_OOL
  powerpc/64s: move some exception handlers out of line

Nicholas Piggin (3):
  powerpc/64s: flush L1D on kernel entry
  powerpc/uaccess: Evaluate macro arguments once, before user access is
    allowed
  powerpc/64s: flush L1D after user accesses

 .../admin-guide/kernel-parameters.txt         |   7 +
 .../powerpc/include/asm/book3s/64/kup-radix.h |  22 +++
 arch/powerpc/include/asm/exception-64s.h      |  13 +-
 arch/powerpc/include/asm/feature-fixups.h     |  19 +++
 arch/powerpc/include/asm/futex.h              |   4 +
 arch/powerpc/include/asm/kup.h                |  40 +++++
 arch/powerpc/include/asm/security_features.h  |   7 +
 arch/powerpc/include/asm/setup.h              |   4 +
 arch/powerpc/include/asm/uaccess.h            | 148 ++++++++++++++----
 arch/powerpc/kernel/exceptions-64s.S          |  96 +++++++-----
 arch/powerpc/kernel/setup_64.c                | 122 ++++++++++++++-
 arch/powerpc/kernel/vmlinux.lds.S             |  14 ++
 arch/powerpc/lib/checksum_wrappers.c          |   4 +
 arch/powerpc/lib/feature-fixups.c             | 104 ++++++++++++
 arch/powerpc/lib/string.S                     |   4 +-
 arch/powerpc/lib/string_64.S                  |   6 +-
 arch/powerpc/platforms/powernv/setup.c        |  17 ++
 arch/powerpc/platforms/pseries/setup.c        |   8 +
 18 files changed, 558 insertions(+), 81 deletions(-)
 create mode 100644 arch/powerpc/include/asm/book3s/64/kup-radix.h
 create mode 100644 arch/powerpc/include/asm/kup.h

-- 
2.25.1

[PATCH 4.14 1/8] powerpc/64s: Define MASKABLE_RELON_EXCEPTION_PSERIES_OOL

[Daniel Axtens]

Commit da2bc4644c75 ("powerpc/64s: Add new exception vector macros")
adds:

+#define __TRAMP_REAL_VIRT_OOL_MASKABLE(name, realvec)          \
+       TRAMP_REAL_BEGIN(tramp_virt_##name);                            \
+       MASKABLE_RELON_EXCEPTION_PSERIES_OOL(realvec, name##_common);   \

However there's no reference there or anywhere else to
MASKABLE_RELON_EXCEPTION_PSERIES_OOL and an attempt to use it
unsurprisingly doesn't work.

Add a definition provided by mpe.

Fixes: da2bc4644c75 ("powerpc/64s: Add new exception vector macros")
Signed-off-by: Daniel Axtens <dja@axtens.net>
---
 arch/powerpc/include/asm/exception-64s.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index c3bdd2d8ec90..a99a455bc267 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -645,6 +645,10 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec);		\
 	EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_HV)
 
+#define MASKABLE_RELON_EXCEPTION_PSERIES_OOL(vec, label)               \
+       EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_PR, vec);          \
+       EXCEPTION_PROLOG_PSERIES_1(label, EXC_STD)
+
 /*
  * Our exception common code can be passed various "additions"
  * to specify the behaviour of interrupts, whether to kick the
-- 
2.25.1

[PATCH 4.14 2/8] powerpc/64s: move some exception handlers out of line

[Daniel Axtens]

(backport only)

We're about to grow the exception handlers, which will make a bunch of them
no longer fit within the space available. We move them out of line.

This is a fiddly and error-prone business, so in the interests of reviewability
I haven't merged this in with the addition of the entry flush.

Signed-off-by: Daniel Axtens <dja@axtens.net>
---
 arch/powerpc/kernel/exceptions-64s.S | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index cdc53fd90597..f619e0deb23b 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -516,13 +516,16 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80)
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXSLB)
+	b tramp_data_access_slb
+EXC_REAL_END(data_access_slb, 0x380, 0x80)
+
+TRAMP_REAL_BEGIN(tramp_data_access_slb)
 	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x380)
 	mr	r12,r3	/* save r3 */
 	mfspr	r3,SPRN_DAR
 	mfspr	r11,SPRN_SRR1
 	crset	4*cr6+eq
 	BRANCH_TO_COMMON(r10, slb_miss_common)
-EXC_REAL_END(data_access_slb, 0x380, 0x80)
 
 EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x80)
 	SET_SCRATCH0(r13)
@@ -560,13 +563,16 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 EXC_REAL_BEGIN(instruction_access_slb, 0x480, 0x80)
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXSLB)
+	b tramp_instruction_access_slb
+EXC_REAL_END(instruction_access_slb, 0x480, 0x80)
+
+TRAMP_REAL_BEGIN(tramp_instruction_access_slb)
 	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480)
 	mr	r12,r3	/* save r3 */
 	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
 	mfspr	r11,SPRN_SRR1
 	crclr	4*cr6+eq
 	BRANCH_TO_COMMON(r10, slb_miss_common)
-EXC_REAL_END(instruction_access_slb, 0x480, 0x80)
 
 EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x80)
 	SET_SCRATCH0(r13)
-- 
2.25.1

[PATCH 4.14 3/8] powerpc/64s: flush L1D on kernel entry

[Daniel Axtens]

From: Nicholas Piggin <npiggin@gmail.com>

commit f79643787e0a0762d2409b7b8334e83f22d85695 upstream.

IBM Power9 processors can speculatively operate on data in the L1 cache before
it has been completely validated, via a way-prediction mechanism. It is not possible
for an attacker to determine the contents of impermissible memory using this method,
since these systems implement a combination of hardware and software security measures
to prevent scenarios where protected data could be leaked.

However these measures don't address the scenario where an attacker induces
the operating system to speculatively execute instructions using data that the
attacker controls. This can be used for example to speculatively bypass "kernel
user access prevention" techniques, as discovered by Anthony Steinhauser of
Google's Safeside Project. This is not an attack by itself, but there is a possibility
it could be used in conjunction with side-channels or other weaknesses in the
privileged code to construct an attack.

This issue can be mitigated by flushing the L1 cache between privilege boundaries
of concern. This patch flushes the L1 cache on kernel entry.

This is part of the fix for CVE-2020-4788.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Daniel Axtens <dja@axtens.net>
---
 .../admin-guide/kernel-parameters.txt         |  3 +
 arch/powerpc/include/asm/exception-64s.h      |  9 ++-
 arch/powerpc/include/asm/feature-fixups.h     | 10 ++++
 arch/powerpc/include/asm/security_features.h  |  4 ++
 arch/powerpc/include/asm/setup.h              |  3 +
 arch/powerpc/kernel/exceptions-64s.S          | 47 +++++++++++++--
 arch/powerpc/kernel/setup_64.c                | 60 ++++++++++++++++++-
 arch/powerpc/kernel/vmlinux.lds.S             |  7 +++
 arch/powerpc/lib/feature-fixups.c             | 54 +++++++++++++++++
 arch/powerpc/platforms/powernv/setup.c        | 11 ++++
 arch/powerpc/platforms/pseries/setup.c        |  4 ++
 11 files changed, 205 insertions(+), 7 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 0a59fcf934f4..28d8f46a3596 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2446,6 +2446,7 @@
 					       mds=off [X86]
 					       tsx_async_abort=off [X86]
 					       kvm.nx_huge_pages=off [X86]
+					       no_entry_flush [PPC]
 
 				Exceptions:
 					       This does not have any effect on
@@ -2749,6 +2750,8 @@
 
 	noefi		Disable EFI runtime services support.
 
+	no_entry_flush  [PPC] Don't flush the L1-D cache when entering the kernel.
+
 	noexec		[IA-64]
 
 	noexec		[X86]
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index a99a455bc267..882545978651 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -84,11 +84,18 @@
 	nop;								\
 	nop
 
+#define ENTRY_FLUSH_SLOT						\
+	ENTRY_FLUSH_FIXUP_SECTION;					\
+	nop;								\
+	nop;								\
+	nop;
+
 /*
  * r10 must be free to use, r13 must be paca
  */
 #define INTERRUPT_TO_KERNEL						\
-	STF_ENTRY_BARRIER_SLOT
+	STF_ENTRY_BARRIER_SLOT;						\
+	ENTRY_FLUSH_SLOT
 
 /*
  * Macros for annotating the expected destination of (h)rfid
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index b1d478acbaec..e282e8146c9d 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -203,6 +203,14 @@ label##3:					       	\
 	FTR_ENTRY_OFFSET 955b-956b;			\
 	.popsection;
 
+#define ENTRY_FLUSH_FIXUP_SECTION			\
+957:							\
+	.pushsection __entry_flush_fixup,"a";		\
+	.align 2;					\
+958:							\
+	FTR_ENTRY_OFFSET 957b-958b;			\
+	.popsection;
+
 #define RFI_FLUSH_FIXUP_SECTION				\
 951:							\
 	.pushsection __rfi_flush_fixup,"a";		\
@@ -235,8 +243,10 @@ label##3:					       	\
 #include <linux/types.h>
 
 extern long stf_barrier_fallback;
+extern long entry_flush_fallback;
 extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup;
 extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup;
+extern long __start___entry_flush_fixup, __stop___entry_flush_fixup;
 extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
 extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup;
 extern long __start__btb_flush_fixup, __stop__btb_flush_fixup;
diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h
index ccf44c135389..082b56bf678d 100644
--- a/arch/powerpc/include/asm/security_features.h
+++ b/arch/powerpc/include/asm/security_features.h
@@ -84,12 +84,16 @@ static inline bool security_ftr_enabled(unsigned long feature)
 // Software required to flush link stack on context switch
 #define SEC_FTR_FLUSH_LINK_STACK	0x0000000000001000ull
 
+// The L1-D cache should be flushed when entering the kernel
+#define SEC_FTR_L1D_FLUSH_ENTRY		0x0000000000004000ull
+
 
 // Features enabled by default
 #define SEC_FTR_DEFAULT \
 	(SEC_FTR_L1D_FLUSH_HV | \
 	 SEC_FTR_L1D_FLUSH_PR | \
 	 SEC_FTR_BNDS_CHK_SPEC_BAR | \
+	 SEC_FTR_L1D_FLUSH_ENTRY | \
 	 SEC_FTR_FAVOUR_SECURITY)
 
 #endif /* _ASM_POWERPC_SECURITY_FEATURES_H */
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index 5ceab440ecb9..02dfa8b1147e 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -51,12 +51,15 @@ enum l1d_flush_type {
 };
 
 void setup_rfi_flush(enum l1d_flush_type, bool enable);
+void setup_entry_flush(bool enable);
+void setup_uaccess_flush(bool enable);
 void do_rfi_flush_fixups(enum l1d_flush_type types);
 #ifdef CONFIG_PPC_BARRIER_NOSPEC
 void setup_barrier_nospec(void);
 #else
 static inline void setup_barrier_nospec(void) { };
 #endif
+void do_entry_flush_fixups(enum l1d_flush_type types);
 void do_barrier_nospec_fixups(bool enable);
 extern bool barrier_nospec_enabled;
 
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index f619e0deb23b..2712331190af 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -484,7 +484,7 @@ EXC_COMMON_BEGIN(unrecover_mce)
 	b	1b
 
 
-EXC_REAL(data_access, 0x300, 0x80)
+EXC_REAL_OOL(data_access, 0x300, 0x80)
 EXC_VIRT(data_access, 0x4300, 0x80, 0x300)
 TRAMP_KVM_SKIP(PACA_EXGEN, 0x300)
 
@@ -540,7 +540,7 @@ EXC_VIRT_END(data_access_slb, 0x4380, 0x80)
 TRAMP_KVM_SKIP(PACA_EXSLB, 0x380)
 
 
-EXC_REAL(instruction_access, 0x400, 0x80)
+EXC_REAL_OOL(instruction_access, 0x400, 0x80)
 EXC_VIRT(instruction_access, 0x4400, 0x80, 0x400)
 TRAMP_KVM(PACA_EXGEN, 0x400)
 
@@ -836,13 +836,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
 
 
 EXC_REAL_OOL_MASKABLE(decrementer, 0x900, 0x80)
-EXC_VIRT_MASKABLE(decrementer, 0x4900, 0x80, 0x900)
+EXC_VIRT_OOL_MASKABLE(decrementer, 0x4900, 0x80, 0x900)
 TRAMP_KVM(PACA_EXGEN, 0x900)
 EXC_COMMON_ASYNC(decrementer_common, 0x900, timer_interrupt)
 
 
-EXC_REAL_HV(hdecrementer, 0x980, 0x80)
-EXC_VIRT_HV(hdecrementer, 0x4980, 0x80, 0x980)
+EXC_REAL_OOL_HV(hdecrementer, 0x980, 0x80)
+EXC_VIRT_OOL_HV(hdecrementer, 0x4980, 0x80, 0x980)
 TRAMP_KVM_HV(PACA_EXGEN, 0x980)
 EXC_COMMON(hdecrementer_common, 0x980, hdec_interrupt)
 
@@ -1459,6 +1459,43 @@ TRAMP_REAL_BEGIN(stf_barrier_fallback)
 	.endr
 	blr
 
+TRAMP_REAL_BEGIN(entry_flush_fallback)
+	std	r9,PACA_EXRFI+EX_R9(r13)
+	std	r10,PACA_EXRFI+EX_R10(r13)
+	std	r11,PACA_EXRFI+EX_R11(r13)
+	mfctr	r9
+	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+	ld	r11,PACA_L1D_FLUSH_SIZE(r13)
+	srdi	r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
+	mtctr	r11
+	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+	/* order ld/st prior to dcbt stop all streams with flushing */
+	sync
+
+	/*
+	 * The load addresses are at staggered offsets within cachelines,
+	 * which suits some pipelines better (on others it should not
+	 * hurt).
+	 */
+1:
+	ld	r11,(0x80 + 8)*0(r10)
+	ld	r11,(0x80 + 8)*1(r10)
+	ld	r11,(0x80 + 8)*2(r10)
+	ld	r11,(0x80 + 8)*3(r10)
+	ld	r11,(0x80 + 8)*4(r10)
+	ld	r11,(0x80 + 8)*5(r10)
+	ld	r11,(0x80 + 8)*6(r10)
+	ld	r11,(0x80 + 8)*7(r10)
+	addi	r10,r10,0x80*8
+	bdnz	1b
+
+	mtctr	r9
+	ld	r9,PACA_EXRFI+EX_R9(r13)
+	ld	r10,PACA_EXRFI+EX_R10(r13)
+	ld	r11,PACA_EXRFI+EX_R11(r13)
+	blr
+
 TRAMP_REAL_BEGIN(rfi_flush_fallback)
 	SET_SCRATCH0(r13);
 	GET_PACA(r13);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index a1e336901cc8..62a3c2e5d918 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -792,7 +792,9 @@ early_initcall(disable_hardlockup_detector);
 static enum l1d_flush_type enabled_flush_types;
 static void *l1d_flush_fallback_area;
 static bool no_rfi_flush;
+static bool no_entry_flush;
 bool rfi_flush;
+bool entry_flush;
 
 static int __init handle_no_rfi_flush(char *p)
 {
@@ -802,6 +804,14 @@ static int __init handle_no_rfi_flush(char *p)
 }
 early_param("no_rfi_flush", handle_no_rfi_flush);
 
+static int __init handle_no_entry_flush(char *p)
+{
+	pr_info("entry-flush: disabled on command line.");
+	no_entry_flush = true;
+	return 0;
+}
+early_param("no_entry_flush", handle_no_entry_flush);
+
 /*
  * The RFI flush is not KPTI, but because users will see doco that says to use
  * nopti we hijack that option here to also disable the RFI flush.
@@ -833,6 +843,18 @@ void rfi_flush_enable(bool enable)
 	rfi_flush = enable;
 }
 
+void entry_flush_enable(bool enable)
+{
+	if (enable) {
+		do_entry_flush_fixups(enabled_flush_types);
+		on_each_cpu(do_nothing, NULL, 1);
+	} else {
+		do_entry_flush_fixups(L1D_FLUSH_NONE);
+	}
+
+	entry_flush = enable;
+}
+
 static void __ref init_fallback_flush(void)
 {
 	u64 l1d_size, limit;
@@ -874,10 +896,19 @@ void setup_rfi_flush(enum l1d_flush_type types, bool enable)
 
 	enabled_flush_types = types;
 
-	if (!no_rfi_flush && !cpu_mitigations_off())
+	if (!cpu_mitigations_off() && !no_rfi_flush)
 		rfi_flush_enable(enable);
 }
 
+void setup_entry_flush(bool enable)
+{
+	if (cpu_mitigations_off())
+		return;
+
+	if (!no_entry_flush)
+		entry_flush_enable(enable);
+}
+
 #ifdef CONFIG_DEBUG_FS
 static int rfi_flush_set(void *data, u64 val)
 {
@@ -905,9 +936,36 @@ static int rfi_flush_get(void *data, u64 *val)
 
 DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n");
 
+static int entry_flush_set(void *data, u64 val)
+{
+	bool enable;
+
+	if (val == 1)
+		enable = true;
+	else if (val == 0)
+		enable = false;
+	else
+		return -EINVAL;
+
+	/* Only do anything if we're changing state */
+	if (enable != entry_flush)
+		entry_flush_enable(enable);
+
+	return 0;
+}
+
+static int entry_flush_get(void *data, u64 *val)
+{
+	*val = entry_flush ? 1 : 0;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_entry_flush, entry_flush_get, entry_flush_set, "%llu\n");
+
 static __init int rfi_flush_debugfs_init(void)
 {
 	debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush);
+	debugfs_create_file("entry_flush", 0600, powerpc_debugfs_root, NULL, &fops_entry_flush);
 	return 0;
 }
 device_initcall(rfi_flush_debugfs_init);
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index e4da937d6cf9..6c3cd47bdb81 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -140,6 +140,13 @@ SECTIONS
 		__stop___stf_entry_barrier_fixup = .;
 	}
 
+	. = ALIGN(8);
+	__entry_flush_fixup : AT(ADDR(__entry_flush_fixup) - LOAD_OFFSET) {
+		__start___entry_flush_fixup = .;
+		*(__entry_flush_fixup)
+		__stop___entry_flush_fixup = .;
+	}
+
 	. = ALIGN(8);
 	__stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) {
 		__start___stf_exit_barrier_fixup = .;
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index de7861e09b41..d21c05bc94a0 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -232,6 +232,60 @@ void do_stf_barrier_fixups(enum stf_barrier_type types)
 	do_stf_exit_barrier_fixups(types);
 }
 
+void do_entry_flush_fixups(enum l1d_flush_type types)
+{
+	unsigned int instrs[3], *dest;
+	long *start, *end;
+	int i;
+
+	start = PTRRELOC(&__start___entry_flush_fixup);
+	end = PTRRELOC(&__stop___entry_flush_fixup);
+
+	instrs[0] = 0x60000000; /* nop */
+	instrs[1] = 0x60000000; /* nop */
+	instrs[2] = 0x60000000; /* nop */
+
+	i = 0;
+	if (types == L1D_FLUSH_FALLBACK) {
+		instrs[i++] = 0x7d4802a6; /* mflr r10		*/
+		instrs[i++] = 0x60000000; /* branch patched below */
+		instrs[i++] = 0x7d4803a6; /* mtlr r10		*/
+	}
+
+	if (types & L1D_FLUSH_ORI) {
+		instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+		instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+	}
+
+	if (types & L1D_FLUSH_MTTRIG)
+		instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+		patch_instruction(dest, instrs[0]);
+
+		if (types == L1D_FLUSH_FALLBACK)
+			patch_branch((dest + 1), (unsigned long)&entry_flush_fallback,
+				     BRANCH_SET_LINK);
+		else
+			patch_instruction((dest + 1), instrs[1]);
+
+		patch_instruction((dest + 2), instrs[2]);
+	}
+
+	printk(KERN_DEBUG "entry-flush: patched %d locations (%s flush)\n", i,
+		(types == L1D_FLUSH_NONE)       ? "no" :
+		(types == L1D_FLUSH_FALLBACK)   ? "fallback displacement" :
+		(types &  L1D_FLUSH_ORI)        ? (types & L1D_FLUSH_MTTRIG)
+							? "ori+mttrig type"
+							: "ori type" :
+		(types &  L1D_FLUSH_MTTRIG)     ? "mttrig type"
+						: "unknown");
+}
+
 void do_rfi_flush_fixups(enum l1d_flush_type types)
 {
 	unsigned int instrs[3], *dest;
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 888aa9584e94..28cb14a26503 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -124,12 +124,23 @@ static void pnv_setup_rfi_flush(void)
 			type = L1D_FLUSH_ORI;
 	}
 
+	/*
+	 * If we are non-Power9 bare metal, we don't need to flush on kernel
+	 * entry: it fixes a P9 specific vulnerability.
+	 */
+	if (!pvr_version_is(PVR_POWER9))
+		security_ftr_clear(SEC_FTR_L1D_FLUSH_ENTRY);
+
 	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && \
 		 (security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR)   || \
 		  security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV));
 
 	setup_rfi_flush(type, enable);
 	setup_count_cache_flush();
+
+	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+		 security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY);
+	setup_entry_flush(enable);
 }
 
 static void __init pnv_setup_arch(void)
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 7a9945b35053..5e58b0cf92df 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -544,6 +544,10 @@ void pseries_setup_rfi_flush(void)
 
 	setup_rfi_flush(types, enable);
 	setup_count_cache_flush();
+
+	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+		 security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY);
+	setup_entry_flush(enable);
 }
 
 static void __init pSeries_setup_arch(void)
-- 
2.25.1

[PATCH 4.14 4/8] powerpc: Add a framework for user access tracking

[Daniel Axtens]

From: Christophe Leroy <christophe.leroy@c-s.fr>

Backported from commit de78a9c42a79 ("powerpc: Add a framework
for Kernel Userspace Access Protection"). Here we don't try to
add the KUAP framework, we just want the helper functions
because we want to put uaccess flush helpers in them.

In terms of fixes, we don't need commit 1d8f739b07bd ("powerpc/kuap:
Fix set direction in allow/prevent_user_access()") as we don't have
real KUAP. Likewise as all our allows are noops and all our prevents
are just flushes, we don't need commit 9dc086f1e9ef ("powerpc/futex:
Fix incorrect user access blocking") The other 2 fixes we do need.

The original description is:

This patch implements a framework for Kernel Userspace Access
Protection.

Then subarches will have the possibility to provide their own
implementation by providing setup_kuap() and
allow/prevent_user_access().

Some platforms will need to know the area accessed and whether it is
accessed from read, write or both. Therefore source, destination and
size and handed over to the two functions.

mpe: Rename to allow/prevent rather than unlock/lock, and add
read/write wrappers. Drop the 32-bit code for now until we have an
implementation for it. Add kuap to pt_regs for 64-bit as well as
32-bit. Don't split strings, use pr_crit_ratelimited().

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Russell Currey <ruscur@russell.cc>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Daniel Axtens <dja@axtens.net>
---
 arch/powerpc/include/asm/futex.h     |  4 +++
 arch/powerpc/include/asm/kup.h       | 36 ++++++++++++++++++++++++++
 arch/powerpc/include/asm/uaccess.h   | 38 ++++++++++++++++++++++------
 arch/powerpc/lib/checksum_wrappers.c |  4 +++
 4 files changed, 74 insertions(+), 8 deletions(-)
 create mode 100644 arch/powerpc/include/asm/kup.h

diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h
index 3c7d85945229..cbcb97c43d82 100644
--- a/arch/powerpc/include/asm/futex.h
+++ b/arch/powerpc/include/asm/futex.h
@@ -35,6 +35,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
 {
 	int oldval = 0, ret;
 
+	allow_write_to_user(uaddr, sizeof(*uaddr));
 	pagefault_disable();
 
 	switch (op) {
@@ -61,6 +62,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
 
 	*oval = oldval;
 
+	prevent_write_to_user(uaddr, sizeof(*uaddr));
 	return ret;
 }
 
@@ -74,6 +76,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
+	allow_write_to_user(uaddr, sizeof(*uaddr));
         __asm__ __volatile__ (
         PPC_ATOMIC_ENTRY_BARRIER
 "1:     lwarx   %1,0,%3         # futex_atomic_cmpxchg_inatomic\n\
@@ -94,6 +97,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
         : "cc", "memory");
 
 	*uval = prev;
+	prevent_write_to_user(uaddr, sizeof(*uaddr));
         return ret;
 }
 
diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h
new file mode 100644
index 000000000000..7895d5eeaf21
--- /dev/null
+++ b/arch/powerpc/include/asm/kup.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_KUP_H_
+#define _ASM_POWERPC_KUP_H_
+
+#ifndef __ASSEMBLY__
+
+#include <asm/pgtable.h>
+
+static inline void allow_user_access(void __user *to, const void __user *from,
+				     unsigned long size) { }
+static inline void prevent_user_access(void __user *to, const void __user *from,
+				       unsigned long size) { }
+
+static inline void allow_read_from_user(const void __user *from, unsigned long size)
+{
+	allow_user_access(NULL, from, size);
+}
+
+static inline void allow_write_to_user(void __user *to, unsigned long size)
+{
+	allow_user_access(to, NULL, size);
+}
+
+static inline void prevent_read_from_user(const void __user *from, unsigned long size)
+{
+	prevent_user_access(NULL, from, size);
+}
+
+static inline void prevent_write_to_user(void __user *to, unsigned long size)
+{
+	prevent_user_access(to, NULL, size);
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_POWERPC_KUP_H_ */
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 3865d1d23597..f07528ba5b52 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -7,6 +7,7 @@
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/extable.h>
+#include <asm/kup.h>
 
 /*
  * The fs value determines whether argument validity checking should be
@@ -132,6 +133,7 @@ extern long __put_user_bad(void);
 #define __put_user_size(x, ptr, size, retval)			\
 do {								\
 	retval = 0;						\
+	allow_write_to_user(ptr, size);				\
 	switch (size) {						\
 	  case 1: __put_user_asm(x, ptr, retval, "stb"); break;	\
 	  case 2: __put_user_asm(x, ptr, retval, "sth"); break;	\
@@ -139,6 +141,7 @@ do {								\
 	  case 8: __put_user_asm2(x, ptr, retval); break;	\
 	  default: __put_user_bad();				\
 	}							\
+	prevent_write_to_user(ptr, size);			\
 } while (0)
 
 #define __put_user_nocheck(x, ptr, size)			\
@@ -214,6 +217,7 @@ do {								\
 	__chk_user_ptr(ptr);					\
 	if (size > sizeof(x))					\
 		(x) = __get_user_bad();				\
+	allow_read_from_user(ptr, size);			\
 	switch (size) {						\
 	case 1: __get_user_asm(x, ptr, retval, "lbz"); break;	\
 	case 2: __get_user_asm(x, ptr, retval, "lhz"); break;	\
@@ -221,6 +225,7 @@ do {								\
 	case 8: __get_user_asm2(x, ptr, retval);  break;	\
 	default: (x) = __get_user_bad();			\
 	}							\
+	prevent_read_from_user(ptr, size);			\
 } while (0)
 
 /*
@@ -280,16 +285,22 @@ extern unsigned long __copy_tofrom_user(void __user *to,
 static inline unsigned long
 raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
 {
+	unsigned long ret;
+
 	barrier_nospec();
-	return __copy_tofrom_user(to, from, n);
+	allow_user_access(to, from, n);
+	ret = __copy_tofrom_user(to, from, n);
+	prevent_user_access(to, from, n);
+	return ret;
 }
 #endif /* __powerpc64__ */
 
 static inline unsigned long raw_copy_from_user(void *to,
 		const void __user *from, unsigned long n)
 {
+	unsigned long ret;
 	if (__builtin_constant_p(n) && (n <= 8)) {
-		unsigned long ret = 1;
+		ret = 1;
 
 		switch (n) {
 		case 1:
@@ -314,14 +325,18 @@ static inline unsigned long raw_copy_from_user(void *to,
 	}
 
 	barrier_nospec();
-	return __copy_tofrom_user((__force void __user *)to, from, n);
+	allow_read_from_user(from, n);
+	ret = __copy_tofrom_user((__force void __user *)to, from, n);
+	prevent_read_from_user(from, n);
+	return ret;
 }
 
 static inline unsigned long raw_copy_to_user(void __user *to,
 		const void *from, unsigned long n)
 {
+	unsigned long ret;
 	if (__builtin_constant_p(n) && (n <= 8)) {
-		unsigned long ret = 1;
+		ret = 1;
 
 		switch (n) {
 		case 1:
@@ -341,17 +356,24 @@ static inline unsigned long raw_copy_to_user(void __user *to,
 			return 0;
 	}
 
-	return __copy_tofrom_user(to, (__force const void __user *)from, n);
+	allow_write_to_user(to, n);
+	ret = __copy_tofrom_user(to, (__force const void __user *)from, n);
+	prevent_write_to_user(to, n);
+	return ret;
 }
 
 extern unsigned long __clear_user(void __user *addr, unsigned long size);
 
 static inline unsigned long clear_user(void __user *addr, unsigned long size)
 {
+	unsigned long ret = size;
 	might_fault();
-	if (likely(access_ok(VERIFY_WRITE, addr, size)))
-		return __clear_user(addr, size);
-	return size;
+	if (likely(access_ok(VERIFY_WRITE, addr, size))) {
+		allow_write_to_user(addr, size);
+		ret = __clear_user(addr, size);
+		prevent_write_to_user(addr, size);
+	}
+	return ret;
 }
 
 extern long strncpy_from_user(char *dst, const char __user *src, long count);
diff --git a/arch/powerpc/lib/checksum_wrappers.c b/arch/powerpc/lib/checksum_wrappers.c
index a0cb63fb76a1..8d83c39be7e4 100644
--- a/arch/powerpc/lib/checksum_wrappers.c
+++ b/arch/powerpc/lib/checksum_wrappers.c
@@ -29,6 +29,7 @@ __wsum csum_and_copy_from_user(const void __user *src, void *dst,
 	unsigned int csum;
 
 	might_sleep();
+	allow_read_from_user(src, len);
 
 	*err_ptr = 0;
 
@@ -60,6 +61,7 @@ __wsum csum_and_copy_from_user(const void __user *src, void *dst,
 	}
 
 out:
+	prevent_read_from_user(src, len);
 	return (__force __wsum)csum;
 }
 EXPORT_SYMBOL(csum_and_copy_from_user);
@@ -70,6 +72,7 @@ __wsum csum_and_copy_to_user(const void *src, void __user *dst, int len,
 	unsigned int csum;
 
 	might_sleep();
+	allow_write_to_user(dst, len);
 
 	*err_ptr = 0;
 
@@ -97,6 +100,7 @@ __wsum csum_and_copy_to_user(const void *src, void __user *dst, int len,
 	}
 
 out:
+	prevent_write_to_user(dst, len);
 	return (__force __wsum)csum;
 }
 EXPORT_SYMBOL(csum_and_copy_to_user);
-- 
2.25.1

[PATCH 4.14 5/8] powerpc: Implement user_access_begin and friends

[Daniel Axtens]

From: Christophe Leroy <christophe.leroy@c-s.fr>

commit 5cd623333e7cf4e3a334c70529268b65f2a6c2c7 upstream.

Today, when a function like strncpy_from_user() is called,
the userspace access protection is de-activated and re-activated
for every word read.

By implementing user_access_begin and friends, the protection
is de-activated at the beginning of the copy and re-activated at the
end.

Implement user_access_begin(), user_access_end() and
unsafe_get_user(), unsafe_put_user() and unsafe_copy_to_user()

For the time being, we keep user_access_save() and
user_access_restore() as nops.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/36d4fbf9e56a75994aca4ee2214c77b26a5a8d35.1579866752.git.christophe.leroy@c-s.fr
Signed-off-by: Daniel Axtens <dja@axtens.net>
---
 arch/powerpc/include/asm/uaccess.h | 76 ++++++++++++++++++++++--------
 1 file changed, 57 insertions(+), 19 deletions(-)

diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index f07528ba5b52..f5a56f103197 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -83,9 +83,14 @@
 	__put_user_check((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
 
 #define __get_user(x, ptr) \
-	__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
+	__get_user_nocheck((x), (ptr), sizeof(*(ptr)), true)
 #define __put_user(x, ptr) \
-	__put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
+	__put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), true)
+
+#define __get_user_allowed(x, ptr) \
+	__get_user_nocheck((x), (ptr), sizeof(*(ptr)), false)
+#define __put_user_allowed(x, ptr) \
+	__put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), false)
 
 #define __get_user_inatomic(x, ptr) \
 	__get_user_nosleep((x), (ptr), sizeof(*(ptr)))
@@ -130,10 +135,9 @@ extern long __put_user_bad(void);
 		: "r" (x), "b" (addr), "i" (-EFAULT), "0" (err))
 #endif /* __powerpc64__ */
 
-#define __put_user_size(x, ptr, size, retval)			\
+#define __put_user_size_allowed(x, ptr, size, retval)		\
 do {								\
 	retval = 0;						\
-	allow_write_to_user(ptr, size);				\
 	switch (size) {						\
 	  case 1: __put_user_asm(x, ptr, retval, "stb"); break;	\
 	  case 2: __put_user_asm(x, ptr, retval, "sth"); break;	\
@@ -141,17 +145,26 @@ do {								\
 	  case 8: __put_user_asm2(x, ptr, retval); break;	\
 	  default: __put_user_bad();				\
 	}							\
+} while (0)
+
+#define __put_user_size(x, ptr, size, retval)			\
+do {								\
+	allow_write_to_user(ptr, size);				\
+	__put_user_size_allowed(x, ptr, size, retval);		\
 	prevent_write_to_user(ptr, size);			\
 } while (0)
 
-#define __put_user_nocheck(x, ptr, size)			\
+#define __put_user_nocheck(x, ptr, size, do_allow)			\
 ({								\
 	long __pu_err;						\
 	__typeof__(*(ptr)) __user *__pu_addr = (ptr);		\
 	if (!is_kernel_addr((unsigned long)__pu_addr))		\
 		might_fault();					\
 	__chk_user_ptr(ptr);					\
-	__put_user_size((x), __pu_addr, (size), __pu_err);	\
+	if (do_allow)								\
+		__put_user_size((x), __pu_addr, (size), __pu_err);		\
+	else									\
+		__put_user_size_allowed((x), __pu_addr, (size), __pu_err);	\
 	__pu_err;						\
 })
 
@@ -211,13 +224,12 @@ extern long __get_user_bad(void);
 		: "b" (addr), "i" (-EFAULT), "0" (err))
 #endif /* __powerpc64__ */
 
-#define __get_user_size(x, ptr, size, retval)			\
+#define __get_user_size_allowed(x, ptr, size, retval)		\
 do {								\
 	retval = 0;						\
 	__chk_user_ptr(ptr);					\
 	if (size > sizeof(x))					\
 		(x) = __get_user_bad();				\
-	allow_read_from_user(ptr, size);			\
 	switch (size) {						\
 	case 1: __get_user_asm(x, ptr, retval, "lbz"); break;	\
 	case 2: __get_user_asm(x, ptr, retval, "lhz"); break;	\
@@ -225,6 +237,12 @@ do {								\
 	case 8: __get_user_asm2(x, ptr, retval);  break;	\
 	default: (x) = __get_user_bad();			\
 	}							\
+} while (0)
+
+#define __get_user_size(x, ptr, size, retval)			\
+do {								\
+	allow_read_from_user(ptr, size);			\
+	__get_user_size_allowed(x, ptr, size, retval);		\
 	prevent_read_from_user(ptr, size);			\
 } while (0)
 
@@ -235,7 +253,7 @@ do {								\
 #define __long_type(x) \
 	__typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
 
-#define __get_user_nocheck(x, ptr, size)			\
+#define __get_user_nocheck(x, ptr, size, do_allow)			\
 ({								\
 	long __gu_err;						\
 	__long_type(*(ptr)) __gu_val;				\
@@ -244,7 +262,10 @@ do {								\
 	if (!is_kernel_addr((unsigned long)__gu_addr))		\
 		might_fault();					\
 	barrier_nospec();					\
-	__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
+	if (do_allow)								\
+		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);		\
+	else									\
+		__get_user_size_allowed(__gu_val, __gu_addr, (size), __gu_err);	\
 	(x) = (__typeof__(*(ptr)))__gu_val;			\
 	__gu_err;						\
 })
@@ -331,33 +352,40 @@ static inline unsigned long raw_copy_from_user(void *to,
 	return ret;
 }
 
-static inline unsigned long raw_copy_to_user(void __user *to,
-		const void *from, unsigned long n)
+static inline unsigned long
+raw_copy_to_user_allowed(void __user *to, const void *from, unsigned long n)
 {
-	unsigned long ret;
 	if (__builtin_constant_p(n) && (n <= 8)) {
-		ret = 1;
+		unsigned long ret = 1;
 
 		switch (n) {
 		case 1:
-			__put_user_size(*(u8 *)from, (u8 __user *)to, 1, ret);
+			__put_user_size_allowed(*(u8 *)from, (u8 __user *)to, 1, ret);
 			break;
 		case 2:
-			__put_user_size(*(u16 *)from, (u16 __user *)to, 2, ret);
+			__put_user_size_allowed(*(u16 *)from, (u16 __user *)to, 2, ret);
 			break;
 		case 4:
-			__put_user_size(*(u32 *)from, (u32 __user *)to, 4, ret);
+			__put_user_size_allowed(*(u32 *)from, (u32 __user *)to, 4, ret);
 			break;
 		case 8:
-			__put_user_size(*(u64 *)from, (u64 __user *)to, 8, ret);
+			__put_user_size_allowed(*(u64 *)from, (u64 __user *)to, 8, ret);
 			break;
 		}
 		if (ret == 0)
 			return 0;
 	}
 
+	return __copy_tofrom_user(to, (__force const void __user *)from, n);
+}
+
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	unsigned long ret;
+
 	allow_write_to_user(to, n);
-	ret = __copy_tofrom_user(to, (__force const void __user *)from, n);
+	ret = raw_copy_to_user_allowed(to, from, n);
 	prevent_write_to_user(to, n);
 	return ret;
 }
@@ -379,4 +407,14 @@ static inline unsigned long clear_user(void __user *addr, unsigned long size)
 extern long strncpy_from_user(char *dst, const char __user *src, long count);
 extern __must_check long strnlen_user(const char __user *str, long n);
 
+
+#define user_access_begin(type, ptr, len) access_ok(type, ptr, len)
+#define user_access_end()		  prevent_user_access(NULL, NULL, ~0ul)
+
+#define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0)
+#define unsafe_get_user(x, p, e) unsafe_op_wrap(__get_user_allowed(x, p), e)
+#define unsafe_put_user(x, p, e) unsafe_op_wrap(__put_user_allowed(x, p), e)
+#define unsafe_copy_to_user(d, s, l, e) \
+	unsafe_op_wrap(raw_copy_to_user_allowed(d, s, l), e)
+
 #endif	/* _ARCH_POWERPC_UACCESS_H */
-- 
2.25.1

[PATCH 4.14 6/8] powerpc: Fix __clear_user() with KUAP enabled

[Daniel Axtens]

From: Andrew Donnellan <ajd@linux.ibm.com>

commit 61e3acd8c693a14fc69b824cb5b08d02cb90a6e7 upstream.

The KUAP implementation adds calls in clear_user() to enable and
disable access to userspace memory. However, it doesn't add these to
__clear_user(), which is used in the ptrace regset code.

As there's only one direct user of __clear_user() (the regset code),
and the time taken to set the AMR for KUAP purposes is going to
dominate the cost of a quick access_ok(), there's not much point
having a separate path.

Rename __clear_user() to __arch_clear_user(), and make __clear_user()
just call clear_user().

Reported-by: syzbot+f25ecf4b2982d8c7a640@syzkaller-ppc64.appspotmail.com
Reported-by: Daniel Axtens <dja@axtens.net>
Suggested-by: Michael Ellerman <mpe@ellerman.id.au>
Fixes: de78a9c42a79 ("powerpc: Add a framework for Kernel Userspace Access Protection")
Signed-off-by: Andrew Donnellan <ajd@linux.ibm.com>
[mpe: Use __arch_clear_user() for the asm version like arm64 & nds32]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191209132221.15328-1-ajd@linux.ibm.com
Signed-off-by: Daniel Axtens <dja@axtens.net>
---
 arch/powerpc/include/asm/uaccess.h | 9 +++++++--
 arch/powerpc/lib/string.S          | 4 ++--
 arch/powerpc/lib/string_64.S       | 6 +++---
 3 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index f5a56f103197..6cba56b911d9 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -390,7 +390,7 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 	return ret;
 }
 
-extern unsigned long __clear_user(void __user *addr, unsigned long size);
+unsigned long __arch_clear_user(void __user *addr, unsigned long size);
 
 static inline unsigned long clear_user(void __user *addr, unsigned long size)
 {
@@ -398,12 +398,17 @@ static inline unsigned long clear_user(void __user *addr, unsigned long size)
 	might_fault();
 	if (likely(access_ok(VERIFY_WRITE, addr, size))) {
 		allow_write_to_user(addr, size);
-		ret = __clear_user(addr, size);
+		ret = __arch_clear_user(addr, size);
 		prevent_write_to_user(addr, size);
 	}
 	return ret;
 }
 
+static inline unsigned long __clear_user(void __user *addr, unsigned long size)
+{
+	return clear_user(addr, size);
+}
+
 extern long strncpy_from_user(char *dst, const char __user *src, long count);
 extern __must_check long strnlen_user(const char __user *str, long n);
 
diff --git a/arch/powerpc/lib/string.S b/arch/powerpc/lib/string.S
index 0378def28d41..7ef5497f3f97 100644
--- a/arch/powerpc/lib/string.S
+++ b/arch/powerpc/lib/string.S
@@ -88,7 +88,7 @@ _GLOBAL(memchr)
 EXPORT_SYMBOL(memchr)
 
 #ifdef CONFIG_PPC32
-_GLOBAL(__clear_user)
+_GLOBAL(__arch_clear_user)
 	addi	r6,r3,-4
 	li	r3,0
 	li	r5,0
@@ -128,5 +128,5 @@ _GLOBAL(__clear_user)
 	EX_TABLE(1b, 91b)
 	EX_TABLE(8b, 92b)
 
-EXPORT_SYMBOL(__clear_user)
+EXPORT_SYMBOL(__arch_clear_user)
 #endif
diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S
index 56aac4c22025..ea3798f4f25f 100644
--- a/arch/powerpc/lib/string_64.S
+++ b/arch/powerpc/lib/string_64.S
@@ -29,7 +29,7 @@ PPC64_CACHES:
 	.section	".text"
 
 /**
- * __clear_user: - Zero a block of memory in user space, with less checking.
+ * __arch_clear_user: - Zero a block of memory in user space, with less checking.
  * @to:   Destination address, in user space.
  * @n:    Number of bytes to zero.
  *
@@ -70,7 +70,7 @@ err3;	stb	r0,0(r3)
 	mr	r3,r4
 	blr
 
-_GLOBAL_TOC(__clear_user)
+_GLOBAL_TOC(__arch_clear_user)
 	cmpdi	r4,32
 	neg	r6,r3
 	li	r0,0
@@ -193,4 +193,4 @@ err1;	dcbz	0,r3
 	cmpdi	r4,32
 	blt	.Lshort_clear
 	b	.Lmedium_clear
-EXPORT_SYMBOL(__clear_user)
+EXPORT_SYMBOL(__arch_clear_user)
-- 
2.25.1

[PATCH 4.14 7/8] powerpc/uaccess: Evaluate macro arguments once, before user access is allowed

[Daniel Axtens]

From: Nicholas Piggin <npiggin@gmail.com>

commit d02f6b7dab8228487268298ea1f21081c0b4b3eb upstream.

get/put_user() can be called with nontrivial arguments. fs/proc/page.c
has a good example:

    if (put_user(stable_page_flags(ppage), out)) {

stable_page_flags() is quite a lot of code, including spin locks in
the page allocator.

Ensure these arguments are evaluated before user access is allowed.

This improves security by reducing code with access to userspace, but
it also fixes a PREEMPT bug with KUAP on powerpc/64s:
stable_page_flags() is currently called with AMR set to allow writes,
it ends up calling spin_unlock(), which can call preempt_schedule. But
the task switch code can not be called with AMR set (it relies on
interrupts saving the register), so this blows up.

It's fine if the code inside allow_user_access() is preemptible,
because a timer or IPI will save the AMR, but it's not okay to
explicitly cause a reschedule.

Fixes: de78a9c42a79 ("powerpc: Add a framework for Kernel Userspace Access Protection")
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200407041245.600651-1-npiggin@gmail.com
Signed-off-by: Daniel Axtens <dja@axtens.net>
---
 arch/powerpc/include/asm/uaccess.h | 49 +++++++++++++++++++++---------
 1 file changed, 35 insertions(+), 14 deletions(-)

diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 6cba56b911d9..95f060cb7a09 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -158,13 +158,17 @@ do {								\
 ({								\
 	long __pu_err;						\
 	__typeof__(*(ptr)) __user *__pu_addr = (ptr);		\
+	__typeof__(*(ptr)) __pu_val = (x);			\
+	__typeof__(size) __pu_size = (size);			\
+								\
 	if (!is_kernel_addr((unsigned long)__pu_addr))		\
 		might_fault();					\
-	__chk_user_ptr(ptr);					\
+	__chk_user_ptr(__pu_addr);				\
 	if (do_allow)								\
-		__put_user_size((x), __pu_addr, (size), __pu_err);		\
+		__put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err);	\
 	else									\
-		__put_user_size_allowed((x), __pu_addr, (size), __pu_err);	\
+		__put_user_size_allowed(__pu_val, __pu_addr, __pu_size, __pu_err); \
+								\
 	__pu_err;						\
 })
 
@@ -172,9 +176,13 @@ do {								\
 ({									\
 	long __pu_err = -EFAULT;					\
 	__typeof__(*(ptr)) __user *__pu_addr = (ptr);			\
+	__typeof__(*(ptr)) __pu_val = (x);				\
+	__typeof__(size) __pu_size = (size);				\
+									\
 	might_fault();							\
-	if (access_ok(VERIFY_WRITE, __pu_addr, size))			\
-		__put_user_size((x), __pu_addr, (size), __pu_err);	\
+	if (access_ok(VERIFY_WRITE, __pu_addr, __pu_size))			\
+		__put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err); \
+									\
 	__pu_err;							\
 })
 
@@ -182,8 +190,12 @@ do {								\
 ({								\
 	long __pu_err;						\
 	__typeof__(*(ptr)) __user *__pu_addr = (ptr);		\
-	__chk_user_ptr(ptr);					\
-	__put_user_size((x), __pu_addr, (size), __pu_err);	\
+	__typeof__(*(ptr)) __pu_val = (x);			\
+	__typeof__(size) __pu_size = (size);			\
+								\
+	__chk_user_ptr(__pu_addr);				\
+	__put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err); \
+								\
 	__pu_err;						\
 })
 
@@ -258,15 +270,18 @@ do {								\
 	long __gu_err;						\
 	__long_type(*(ptr)) __gu_val;				\
 	__typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
-	__chk_user_ptr(ptr);					\
+	__typeof__(size) __gu_size = (size);			\
+								\
+	__chk_user_ptr(__gu_addr);				\
 	if (!is_kernel_addr((unsigned long)__gu_addr))		\
 		might_fault();					\
 	barrier_nospec();					\
 	if (do_allow)								\
-		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);		\
+		__get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err);	\
 	else									\
-		__get_user_size_allowed(__gu_val, __gu_addr, (size), __gu_err);	\
+		__get_user_size_allowed(__gu_val, __gu_addr, __gu_size, __gu_err); \
 	(x) = (__typeof__(*(ptr)))__gu_val;			\
+								\
 	__gu_err;						\
 })
 
@@ -275,12 +290,15 @@ do {								\
 	long __gu_err = -EFAULT;					\
 	__long_type(*(ptr)) __gu_val = 0;				\
 	__typeof__(*(ptr)) __user *__gu_addr = (ptr);		\
+	__typeof__(size) __gu_size = (size);				\
+									\
 	might_fault();							\
-	if (access_ok(VERIFY_READ, __gu_addr, (size))) {		\
+	if (access_ok(VERIFY_READ, __gu_addr, __gu_size)) {		\
 		barrier_nospec();					\
-		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
+		__get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err); \
 	}								\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;				\
+									\
 	__gu_err;							\
 })
 
@@ -289,10 +307,13 @@ do {								\
 	long __gu_err;						\
 	__long_type(*(ptr)) __gu_val;				\
 	__typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
-	__chk_user_ptr(ptr);					\
+	__typeof__(size) __gu_size = (size);			\
+								\
+	__chk_user_ptr(__gu_addr);				\
 	barrier_nospec();					\
-	__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
+	__get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err); \
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
+								\
 	__gu_err;						\
 })
 
-- 
2.25.1

[PATCH 4.14 8/8] powerpc/64s: flush L1D after user accesses

[Daniel Axtens]

From: Nicholas Piggin <npiggin@gmail.com>

commit 9a32a7e78bd0cd9a9b6332cbdc345ee5ffd0c5de upstream.

IBM Power9 processors can speculatively operate on data in the L1 cache before
it has been completely validated, via a way-prediction mechanism. It is not possible
for an attacker to determine the contents of impermissible memory using this method,
since these systems implement a combination of hardware and software security measures
to prevent scenarios where protected data could be leaked.

However these measures don't address the scenario where an attacker induces
the operating system to speculatively execute instructions using data that the
attacker controls. This can be used for example to speculatively bypass "kernel
user access prevention" techniques, as discovered by Anthony Steinhauser of
Google's Safeside Project. This is not an attack by itself, but there is a possibility
it could be used in conjunction with side-channels or other weaknesses in the
privileged code to construct an attack.

This issue can be mitigated by flushing the L1 cache between privilege boundaries
of concern. This patch flushes the L1 cache after user accesses.

This is part of the fix for CVE-2020-4788.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Daniel Axtens <dja@axtens.net>
---
 .../admin-guide/kernel-parameters.txt         |  4 +
 .../powerpc/include/asm/book3s/64/kup-radix.h | 22 +++++
 arch/powerpc/include/asm/feature-fixups.h     |  9 +++
 arch/powerpc/include/asm/kup.h                |  4 +
 arch/powerpc/include/asm/security_features.h  |  3 +
 arch/powerpc/include/asm/setup.h              |  1 +
 arch/powerpc/kernel/exceptions-64s.S          | 81 ++++++-------------
 arch/powerpc/kernel/setup_64.c                | 62 ++++++++++++++
 arch/powerpc/kernel/vmlinux.lds.S             |  7 ++
 arch/powerpc/lib/feature-fixups.c             | 50 ++++++++++++
 arch/powerpc/platforms/powernv/setup.c        | 10 ++-
 arch/powerpc/platforms/pseries/setup.c        |  4 +
 12 files changed, 198 insertions(+), 59 deletions(-)
 create mode 100644 arch/powerpc/include/asm/book3s/64/kup-radix.h

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 28d8f46a3596..ea422ec7c507 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2447,6 +2447,7 @@
 					       tsx_async_abort=off [X86]
 					       kvm.nx_huge_pages=off [X86]
 					       no_entry_flush [PPC]
+					       no_uaccess_flush [PPC]
 
 				Exceptions:
 					       This does not have any effect on
@@ -2801,6 +2802,9 @@
 	nospec_store_bypass_disable
 			[HW] Disable all mitigations for the Speculative Store Bypass vulnerability
 
+	no_uaccess_flush
+	                [PPC] Don't flush the L1-D cache after accessing user data.
+
 	noxsave		[BUGS=X86] Disables x86 extended register state save
 			and restore using xsave. The kernel will fallback to
 			enabling legacy floating-point and sse state.
diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h
new file mode 100644
index 000000000000..aa54ac2e5659
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H
+#define _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H
+
+DECLARE_STATIC_KEY_FALSE(uaccess_flush_key);
+
+/* Prototype for function defined in exceptions-64s.S */
+void do_uaccess_flush(void);
+
+static __always_inline void allow_user_access(void __user *to, const void __user *from,
+					      unsigned long size)
+{
+}
+
+static inline void prevent_user_access(void __user *to, const void __user *from,
+				       unsigned long size)
+{
+	if (static_branch_unlikely(&uaccess_flush_key))
+		do_uaccess_flush();
+}
+
+#endif /* _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H */
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index e282e8146c9d..745c017b8de6 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -203,6 +203,14 @@ label##3:					       	\
 	FTR_ENTRY_OFFSET 955b-956b;			\
 	.popsection;
 
+#define UACCESS_FLUSH_FIXUP_SECTION			\
+959:							\
+	.pushsection __uaccess_flush_fixup,"a";		\
+	.align 2;					\
+960:							\
+	FTR_ENTRY_OFFSET 959b-960b;			\
+	.popsection;
+
 #define ENTRY_FLUSH_FIXUP_SECTION			\
 957:							\
 	.pushsection __entry_flush_fixup,"a";		\
@@ -246,6 +254,7 @@ extern long stf_barrier_fallback;
 extern long entry_flush_fallback;
 extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup;
 extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup;
+extern long __start___uaccess_flush_fixup, __stop___uaccess_flush_fixup;
 extern long __start___entry_flush_fixup, __stop___entry_flush_fixup;
 extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
 extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup;
diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h
index 7895d5eeaf21..f0f8e36ad71f 100644
--- a/arch/powerpc/include/asm/kup.h
+++ b/arch/powerpc/include/asm/kup.h
@@ -6,10 +6,14 @@
 
 #include <asm/pgtable.h>
 
+#ifdef CONFIG_PPC_BOOK3S_64
+#include <asm/book3s/64/kup-radix.h>
+#else
 static inline void allow_user_access(void __user *to, const void __user *from,
 				     unsigned long size) { }
 static inline void prevent_user_access(void __user *to, const void __user *from,
 				       unsigned long size) { }
+#endif /* CONFIG_PPC_BOOK3S_64 */
 
 static inline void allow_read_from_user(const void __user *from, unsigned long size)
 {
diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h
index 082b56bf678d..3b45a64e491e 100644
--- a/arch/powerpc/include/asm/security_features.h
+++ b/arch/powerpc/include/asm/security_features.h
@@ -87,6 +87,8 @@ static inline bool security_ftr_enabled(unsigned long feature)
 // The L1-D cache should be flushed when entering the kernel
 #define SEC_FTR_L1D_FLUSH_ENTRY		0x0000000000004000ull
 
+// The L1-D cache should be flushed after user accesses from the kernel
+#define SEC_FTR_L1D_FLUSH_UACCESS	0x0000000000008000ull
 
 // Features enabled by default
 #define SEC_FTR_DEFAULT \
@@ -94,6 +96,7 @@ static inline bool security_ftr_enabled(unsigned long feature)
 	 SEC_FTR_L1D_FLUSH_PR | \
 	 SEC_FTR_BNDS_CHK_SPEC_BAR | \
 	 SEC_FTR_L1D_FLUSH_ENTRY | \
+	 SEC_FTR_L1D_FLUSH_UACCESS | \
 	 SEC_FTR_FAVOUR_SECURITY)
 
 #endif /* _ASM_POWERPC_SECURITY_FEATURES_H */
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index 02dfa8b1147e..6750ad3cd3b1 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -59,6 +59,7 @@ void setup_barrier_nospec(void);
 #else
 static inline void setup_barrier_nospec(void) { };
 #endif
+void do_uaccess_flush_fixups(enum l1d_flush_type types);
 void do_entry_flush_fixups(enum l1d_flush_type types);
 void do_barrier_nospec_fixups(bool enable);
 extern bool barrier_nospec_enabled;
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 2712331190af..b313628966ad 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1459,11 +1459,8 @@ TRAMP_REAL_BEGIN(stf_barrier_fallback)
 	.endr
 	blr
 
-TRAMP_REAL_BEGIN(entry_flush_fallback)
-	std	r9,PACA_EXRFI+EX_R9(r13)
-	std	r10,PACA_EXRFI+EX_R10(r13)
-	std	r11,PACA_EXRFI+EX_R11(r13)
-	mfctr	r9
+/* Clobbers r10, r11, ctr */
+.macro L1D_DISPLACEMENT_FLUSH
 	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
 	ld	r11,PACA_L1D_FLUSH_SIZE(r13)
 	srdi	r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
@@ -1489,7 +1486,14 @@ TRAMP_REAL_BEGIN(entry_flush_fallback)
 	ld	r11,(0x80 + 8)*7(r10)
 	addi	r10,r10,0x80*8
 	bdnz	1b
+.endm
 
+TRAMP_REAL_BEGIN(entry_flush_fallback)
+	std	r9,PACA_EXRFI+EX_R9(r13)
+	std	r10,PACA_EXRFI+EX_R10(r13)
+	std	r11,PACA_EXRFI+EX_R11(r13)
+	mfctr	r9
+	L1D_DISPLACEMENT_FLUSH
 	mtctr	r9
 	ld	r9,PACA_EXRFI+EX_R9(r13)
 	ld	r10,PACA_EXRFI+EX_R10(r13)
@@ -1505,32 +1509,7 @@ TRAMP_REAL_BEGIN(rfi_flush_fallback)
 	std	r10,PACA_EXRFI+EX_R10(r13)
 	std	r11,PACA_EXRFI+EX_R11(r13)
 	mfctr	r9
-	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
-	ld	r11,PACA_L1D_FLUSH_SIZE(r13)
-	srdi	r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
-	mtctr	r11
-	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
-
-	/* order ld/st prior to dcbt stop all streams with flushing */
-	sync
-
-	/*
-	 * The load adresses are at staggered offsets within cachelines,
-	 * which suits some pipelines better (on others it should not
-	 * hurt).
-	 */
-1:
-	ld	r11,(0x80 + 8)*0(r10)
-	ld	r11,(0x80 + 8)*1(r10)
-	ld	r11,(0x80 + 8)*2(r10)
-	ld	r11,(0x80 + 8)*3(r10)
-	ld	r11,(0x80 + 8)*4(r10)
-	ld	r11,(0x80 + 8)*5(r10)
-	ld	r11,(0x80 + 8)*6(r10)
-	ld	r11,(0x80 + 8)*7(r10)
-	addi	r10,r10,0x80*8
-	bdnz	1b
-
+	L1D_DISPLACEMENT_FLUSH
 	mtctr	r9
 	ld	r9,PACA_EXRFI+EX_R9(r13)
 	ld	r10,PACA_EXRFI+EX_R10(r13)
@@ -1548,32 +1527,7 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback)
 	std	r10,PACA_EXRFI+EX_R10(r13)
 	std	r11,PACA_EXRFI+EX_R11(r13)
 	mfctr	r9
-	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
-	ld	r11,PACA_L1D_FLUSH_SIZE(r13)
-	srdi	r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
-	mtctr	r11
-	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
-
-	/* order ld/st prior to dcbt stop all streams with flushing */
-	sync
-
-	/*
-	 * The load adresses are at staggered offsets within cachelines,
-	 * which suits some pipelines better (on others it should not
-	 * hurt).
-	 */
-1:
-	ld	r11,(0x80 + 8)*0(r10)
-	ld	r11,(0x80 + 8)*1(r10)
-	ld	r11,(0x80 + 8)*2(r10)
-	ld	r11,(0x80 + 8)*3(r10)
-	ld	r11,(0x80 + 8)*4(r10)
-	ld	r11,(0x80 + 8)*5(r10)
-	ld	r11,(0x80 + 8)*6(r10)
-	ld	r11,(0x80 + 8)*7(r10)
-	addi	r10,r10,0x80*8
-	bdnz	1b
-
+	L1D_DISPLACEMENT_FLUSH
 	mtctr	r9
 	ld	r9,PACA_EXRFI+EX_R9(r13)
 	ld	r10,PACA_EXRFI+EX_R10(r13)
@@ -1582,6 +1536,19 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback)
 	GET_SCRATCH0(r13);
 	hrfid
 
+USE_TEXT_SECTION()
+
+_GLOBAL(do_uaccess_flush)
+	UACCESS_FLUSH_FIXUP_SECTION
+	nop
+	nop
+	nop
+	blr
+	L1D_DISPLACEMENT_FLUSH
+	blr
+_ASM_NOKPROBE_SYMBOL(do_uaccess_flush)
+EXPORT_SYMBOL(do_uaccess_flush)
+
 /*
  * Real mode exceptions actually use this too, but alternate
  * instruction code patches (which end up in the common .text area)
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 62a3c2e5d918..a1eec409695e 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -793,8 +793,12 @@ static enum l1d_flush_type enabled_flush_types;
 static void *l1d_flush_fallback_area;
 static bool no_rfi_flush;
 static bool no_entry_flush;
+static bool no_uaccess_flush;
 bool rfi_flush;
 bool entry_flush;
+bool uaccess_flush;
+DEFINE_STATIC_KEY_FALSE(uaccess_flush_key);
+EXPORT_SYMBOL(uaccess_flush_key);
 
 static int __init handle_no_rfi_flush(char *p)
 {
@@ -812,6 +816,14 @@ static int __init handle_no_entry_flush(char *p)
 }
 early_param("no_entry_flush", handle_no_entry_flush);
 
+static int __init handle_no_uaccess_flush(char *p)
+{
+	pr_info("uaccess-flush: disabled on command line.");
+	no_uaccess_flush = true;
+	return 0;
+}
+early_param("no_uaccess_flush", handle_no_uaccess_flush);
+
 /*
  * The RFI flush is not KPTI, but because users will see doco that says to use
  * nopti we hijack that option here to also disable the RFI flush.
@@ -855,6 +867,20 @@ void entry_flush_enable(bool enable)
 	entry_flush = enable;
 }
 
+void uaccess_flush_enable(bool enable)
+{
+	if (enable) {
+		do_uaccess_flush_fixups(enabled_flush_types);
+		static_branch_enable(&uaccess_flush_key);
+		on_each_cpu(do_nothing, NULL, 1);
+	} else {
+		static_branch_disable(&uaccess_flush_key);
+		do_uaccess_flush_fixups(L1D_FLUSH_NONE);
+	}
+
+	uaccess_flush = enable;
+}
+
 static void __ref init_fallback_flush(void)
 {
 	u64 l1d_size, limit;
@@ -909,6 +935,15 @@ void setup_entry_flush(bool enable)
 		entry_flush_enable(enable);
 }
 
+void setup_uaccess_flush(bool enable)
+{
+	if (cpu_mitigations_off())
+		return;
+
+	if (!no_uaccess_flush)
+		uaccess_flush_enable(enable);
+}
+
 #ifdef CONFIG_DEBUG_FS
 static int rfi_flush_set(void *data, u64 val)
 {
@@ -962,10 +997,37 @@ static int entry_flush_get(void *data, u64 *val)
 
 DEFINE_SIMPLE_ATTRIBUTE(fops_entry_flush, entry_flush_get, entry_flush_set, "%llu\n");
 
+static int uaccess_flush_set(void *data, u64 val)
+{
+	bool enable;
+
+	if (val == 1)
+		enable = true;
+	else if (val == 0)
+		enable = false;
+	else
+		return -EINVAL;
+
+	/* Only do anything if we're changing state */
+	if (enable != uaccess_flush)
+		uaccess_flush_enable(enable);
+
+	return 0;
+}
+
+static int uaccess_flush_get(void *data, u64 *val)
+{
+	*val = uaccess_flush ? 1 : 0;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_uaccess_flush, uaccess_flush_get, uaccess_flush_set, "%llu\n");
+
 static __init int rfi_flush_debugfs_init(void)
 {
 	debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush);
 	debugfs_create_file("entry_flush", 0600, powerpc_debugfs_root, NULL, &fops_entry_flush);
+	debugfs_create_file("uaccess_flush", 0600, powerpc_debugfs_root, NULL, &fops_uaccess_flush);
 	return 0;
 }
 device_initcall(rfi_flush_debugfs_init);
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 6c3cd47bdb81..efb9a6982561 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -140,6 +140,13 @@ SECTIONS
 		__stop___stf_entry_barrier_fixup = .;
 	}
 
+	. = ALIGN(8);
+	__uaccess_flush_fixup : AT(ADDR(__uaccess_flush_fixup) - LOAD_OFFSET) {
+		__start___uaccess_flush_fixup = .;
+		*(__uaccess_flush_fixup)
+		__stop___uaccess_flush_fixup = .;
+	}
+
 	. = ALIGN(8);
 	__entry_flush_fixup : AT(ADDR(__entry_flush_fixup) - LOAD_OFFSET) {
 		__start___entry_flush_fixup = .;
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index d21c05bc94a0..6ebc3c9e7abb 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -232,6 +232,56 @@ void do_stf_barrier_fixups(enum stf_barrier_type types)
 	do_stf_exit_barrier_fixups(types);
 }
 
+void do_uaccess_flush_fixups(enum l1d_flush_type types)
+{
+	unsigned int instrs[4], *dest;
+	long *start, *end;
+	int i;
+
+	start = PTRRELOC(&__start___uaccess_flush_fixup);
+	end = PTRRELOC(&__stop___uaccess_flush_fixup);
+
+	instrs[0] = 0x60000000; /* nop */
+	instrs[1] = 0x60000000; /* nop */
+	instrs[2] = 0x60000000; /* nop */
+	instrs[3] = 0x4e800020; /* blr */
+
+	i = 0;
+	if (types == L1D_FLUSH_FALLBACK) {
+		instrs[3] = 0x60000000; /* nop */
+		/* fallthrough to fallback flush */
+	}
+
+	if (types & L1D_FLUSH_ORI) {
+		instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+		instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+	}
+
+	if (types & L1D_FLUSH_MTTRIG)
+		instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+		patch_instruction(dest, instrs[0]);
+
+		patch_instruction((dest + 1), instrs[1]);
+		patch_instruction((dest + 2), instrs[2]);
+		patch_instruction((dest + 3), instrs[3]);
+	}
+
+	printk(KERN_DEBUG "uaccess-flush: patched %d locations (%s flush)\n", i,
+		(types == L1D_FLUSH_NONE)       ? "no" :
+		(types == L1D_FLUSH_FALLBACK)   ? "fallback displacement" :
+		(types &  L1D_FLUSH_ORI)        ? (types & L1D_FLUSH_MTTRIG)
+							? "ori+mttrig type"
+							: "ori type" :
+		(types &  L1D_FLUSH_MTTRIG)     ? "mttrig type"
+						: "unknown");
+}
+
 void do_entry_flush_fixups(enum l1d_flush_type types)
 {
 	unsigned int instrs[3], *dest;
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 28cb14a26503..0693fd16e2c9 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -126,10 +126,12 @@ static void pnv_setup_rfi_flush(void)
 
 	/*
 	 * If we are non-Power9 bare metal, we don't need to flush on kernel
-	 * entry: it fixes a P9 specific vulnerability.
+	 * entry or after user access: they fix a P9 specific vulnerability.
 	 */
-	if (!pvr_version_is(PVR_POWER9))
+	if (!pvr_version_is(PVR_POWER9)) {
 		security_ftr_clear(SEC_FTR_L1D_FLUSH_ENTRY);
+		security_ftr_clear(SEC_FTR_L1D_FLUSH_UACCESS);
+	}
 
 	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && \
 		 (security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR)   || \
@@ -141,6 +143,10 @@ static void pnv_setup_rfi_flush(void)
 	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
 		 security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY);
 	setup_entry_flush(enable);
+
+	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+		 security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS);
+	setup_uaccess_flush(enable);
 }
 
 static void __init pnv_setup_arch(void)
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 5e58b0cf92df..ab85fac02c04 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -548,6 +548,10 @@ void pseries_setup_rfi_flush(void)
 	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
 		 security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY);
 	setup_entry_flush(enable);
+
+	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+		 security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS);
+	setup_uaccess_flush(enable);
 }
 
 static void __init pSeries_setup_arch(void)
-- 
2.25.1