summaryrefslogtreecommitdiff
path: root/arch/powerpc/kernel
diff options
context:
space:
mode:
authorNicholas Piggin <npiggin@gmail.com>2020-11-20 10:52:39 +1100
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2020-11-22 10:00:23 +0100
commitdb01cad9efe3c3838a6b3a3f68affd295c4b92d6 (patch)
tree5d4e40b100a1b2c6e7a09887798070b75a2c80f8 /arch/powerpc/kernel
parent39885f4d7c24a61e46c2bf531deef7ac849fcd00 (diff)
powerpc/64s: flush L1D on kernel entry
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> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'arch/powerpc/kernel')
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S47
-rw-r--r--arch/powerpc/kernel/setup_64.c60
-rw-r--r--arch/powerpc/kernel/vmlinux.lds.S7
3 files changed, 108 insertions, 6 deletions
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
@@ -141,6 +141,13 @@ SECTIONS
}
. = 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 = .;
*(__stf_exit_barrier_fixup)