* [PATCH AUTOSEL 4.19 25/45] ibmvnic: Unmap DMA address of TX descriptor buffers after use
From: Sasha Levin @ 2019-08-29 18:15 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Devesh K . Singh, Sasha Levin, netdev, Abdul Haleem,
Thomas Falcon, linuxppc-dev, David S . Miller
In-Reply-To: <20190829181547.8280-1-sashal@kernel.org>
From: Thomas Falcon <tlfalcon@linux.ibm.com>
[ Upstream commit 80f0fe0934cd3daa13a5e4d48a103f469115b160 ]
There's no need to wait until a completion is received to unmap
TX descriptor buffers that have been passed to the hypervisor.
Instead unmap it when the hypervisor call has completed. This patch
avoids the possibility that a buffer will not be unmapped because
a TX completion is lost or mishandled.
Reported-by: Abdul Haleem <abdhalee@linux.vnet.ibm.com>
Tested-by: Devesh K. Singh <devesh_singh@in.ibm.com>
Signed-off-by: Thomas Falcon <tlfalcon@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/ibm/ibmvnic.c | 11 ++---------
1 file changed, 2 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 0ae43d27cdcff..255de7d68cd33 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1586,6 +1586,8 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
lpar_rc = send_subcrq_indirect(adapter, handle_array[queue_num],
(u64)tx_buff->indir_dma,
(u64)num_entries);
+ dma_unmap_single(dev, tx_buff->indir_dma,
+ sizeof(tx_buff->indir_arr), DMA_TO_DEVICE);
} else {
tx_buff->num_entries = num_entries;
lpar_rc = send_subcrq(adapter, handle_array[queue_num],
@@ -2747,7 +2749,6 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter,
union sub_crq *next;
int index;
int i, j;
- u8 *first;
restart_loop:
while (pending_scrq(adapter, scrq)) {
@@ -2777,14 +2778,6 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter,
txbuff->data_dma[j] = 0;
}
- /* if sub_crq was sent indirectly */
- first = &txbuff->indir_arr[0].generic.first;
- if (*first == IBMVNIC_CRQ_CMD) {
- dma_unmap_single(dev, txbuff->indir_dma,
- sizeof(txbuff->indir_arr),
- DMA_TO_DEVICE);
- *first = 0;
- }
if (txbuff->last_frag) {
dev_kfree_skb_any(txbuff->skb);
--
2.20.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.19 09/45] ibmveth: Convert multicast list size for little-endian system
From: Sasha Levin @ 2019-08-29 18:15 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Jakub Kicinski, netdev, Thomas Falcon, Hangbin Liu,
linuxppc-dev
In-Reply-To: <20190829181547.8280-1-sashal@kernel.org>
From: Thomas Falcon <tlfalcon@linux.ibm.com>
[ Upstream commit 66cf4710b23ab2adda11155684a2c8826f4fe732 ]
The ibm,mac-address-filters property defines the maximum number of
addresses the hypervisor's multicast filter list can support. It is
encoded as a big-endian integer in the OF device tree, but the virtual
ethernet driver does not convert it for use by little-endian systems.
As a result, the driver is not behaving as it should on affected systems
when a large number of multicast addresses are assigned to the device.
Reported-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Thomas Falcon <tlfalcon@linux.ibm.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/ibm/ibmveth.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index f70cb4d3c6846..40ad1e5032553 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1618,7 +1618,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
struct net_device *netdev;
struct ibmveth_adapter *adapter;
unsigned char *mac_addr_p;
- unsigned int *mcastFilterSize_p;
+ __be32 *mcastFilterSize_p;
long ret;
unsigned long ret_attr;
@@ -1640,8 +1640,9 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
return -EINVAL;
}
- mcastFilterSize_p = (unsigned int *)vio_get_attribute(dev,
- VETH_MCAST_FILTER_SIZE, NULL);
+ mcastFilterSize_p = (__be32 *)vio_get_attribute(dev,
+ VETH_MCAST_FILTER_SIZE,
+ NULL);
if (!mcastFilterSize_p) {
dev_err(&dev->dev, "Can't find VETH_MCAST_FILTER_SIZE "
"attribute\n");
@@ -1658,7 +1659,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
adapter->vdev = dev;
adapter->netdev = netdev;
- adapter->mcastFilterSize = *mcastFilterSize_p;
+ adapter->mcastFilterSize = be32_to_cpu(*mcastFilterSize_p);
adapter->pool_config = 0;
netif_napi_add(netdev, &adapter->napi, ibmveth_poll, 16);
--
2.20.1
^ permalink raw reply related
* [PATCH AUTOSEL 5.2 43/76] ibmvnic: Unmap DMA address of TX descriptor buffers after use
From: Sasha Levin @ 2019-08-29 18:12 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Devesh K . Singh, Sasha Levin, netdev, Abdul Haleem,
Thomas Falcon, linuxppc-dev, David S . Miller
In-Reply-To: <20190829181311.7562-1-sashal@kernel.org>
From: Thomas Falcon <tlfalcon@linux.ibm.com>
[ Upstream commit 80f0fe0934cd3daa13a5e4d48a103f469115b160 ]
There's no need to wait until a completion is received to unmap
TX descriptor buffers that have been passed to the hypervisor.
Instead unmap it when the hypervisor call has completed. This patch
avoids the possibility that a buffer will not be unmapped because
a TX completion is lost or mishandled.
Reported-by: Abdul Haleem <abdhalee@linux.vnet.ibm.com>
Tested-by: Devesh K. Singh <devesh_singh@in.ibm.com>
Signed-off-by: Thomas Falcon <tlfalcon@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/ibm/ibmvnic.c | 11 ++---------
1 file changed, 2 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 3da6800732656..cebd20f3128d4 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1568,6 +1568,8 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
lpar_rc = send_subcrq_indirect(adapter, handle_array[queue_num],
(u64)tx_buff->indir_dma,
(u64)num_entries);
+ dma_unmap_single(dev, tx_buff->indir_dma,
+ sizeof(tx_buff->indir_arr), DMA_TO_DEVICE);
} else {
tx_buff->num_entries = num_entries;
lpar_rc = send_subcrq(adapter, handle_array[queue_num],
@@ -2788,7 +2790,6 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter,
union sub_crq *next;
int index;
int i, j;
- u8 *first;
restart_loop:
while (pending_scrq(adapter, scrq)) {
@@ -2818,14 +2819,6 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter,
txbuff->data_dma[j] = 0;
}
- /* if sub_crq was sent indirectly */
- first = &txbuff->indir_arr[0].generic.first;
- if (*first == IBMVNIC_CRQ_CMD) {
- dma_unmap_single(dev, txbuff->indir_dma,
- sizeof(txbuff->indir_arr),
- DMA_TO_DEVICE);
- *first = 0;
- }
if (txbuff->last_frag) {
dev_kfree_skb_any(txbuff->skb);
--
2.20.1
^ permalink raw reply related
* [PATCH AUTOSEL 5.2 22/76] ibmveth: Convert multicast list size for little-endian system
From: Sasha Levin @ 2019-08-29 18:12 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Jakub Kicinski, netdev, Thomas Falcon, Hangbin Liu,
linuxppc-dev
In-Reply-To: <20190829181311.7562-1-sashal@kernel.org>
From: Thomas Falcon <tlfalcon@linux.ibm.com>
[ Upstream commit 66cf4710b23ab2adda11155684a2c8826f4fe732 ]
The ibm,mac-address-filters property defines the maximum number of
addresses the hypervisor's multicast filter list can support. It is
encoded as a big-endian integer in the OF device tree, but the virtual
ethernet driver does not convert it for use by little-endian systems.
As a result, the driver is not behaving as it should on affected systems
when a large number of multicast addresses are assigned to the device.
Reported-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Thomas Falcon <tlfalcon@linux.ibm.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/ibm/ibmveth.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index d654c234aaf75..c5be4ebd84373 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1605,7 +1605,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
struct net_device *netdev;
struct ibmveth_adapter *adapter;
unsigned char *mac_addr_p;
- unsigned int *mcastFilterSize_p;
+ __be32 *mcastFilterSize_p;
long ret;
unsigned long ret_attr;
@@ -1627,8 +1627,9 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
return -EINVAL;
}
- mcastFilterSize_p = (unsigned int *)vio_get_attribute(dev,
- VETH_MCAST_FILTER_SIZE, NULL);
+ mcastFilterSize_p = (__be32 *)vio_get_attribute(dev,
+ VETH_MCAST_FILTER_SIZE,
+ NULL);
if (!mcastFilterSize_p) {
dev_err(&dev->dev, "Can't find VETH_MCAST_FILTER_SIZE "
"attribute\n");
@@ -1645,7 +1646,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
adapter->vdev = dev;
adapter->netdev = netdev;
- adapter->mcastFilterSize = *mcastFilterSize_p;
+ adapter->mcastFilterSize = be32_to_cpu(*mcastFilterSize_p);
adapter->pool_config = 0;
netif_napi_add(netdev, &adapter->napi, ibmveth_poll, 16);
--
2.20.1
^ permalink raw reply related
* Re: [PATCH v4 3/4] powerpc/64: make buildable without CONFIG_COMPAT
From: Christophe Leroy @ 2019-08-29 17:40 UTC (permalink / raw)
To: Michal Suchanek, linuxppc-dev
Cc: David Hildenbrand, Heiko Carstens, David Howells, Paul Mackerras,
Breno Leitao, Michael Neuling, Nicolai Stange, Geert Uytterhoeven,
Allison Randal, Firoz Khan, Joel Stanley, Arnd Bergmann,
Nicholas Piggin, Thomas Gleixner, Christian Brauner,
Greg Kroah-Hartman, linux-kernel, Eric W. Biederman,
Andrew Donnellan, Hari Bathini
In-Reply-To: <a829dfabed8285161fcdff166d58c7e8f0f6d402.1567072270.git.msuchanek@suse.de>
Le 29/08/2019 à 12:23, Michal Suchanek a écrit :
> There are numerous references to 32bit functions in generic and 64bit
> code so ifdef them out.
>
> Signed-off-by: Michal Suchanek <msuchanek@suse.de>
> ---
> v2:
> - fix 32bit ifdef condition in signal.c
> - simplify the compat ifdef condition in vdso.c - 64bit is redundant
> - simplify the compat ifdef condition in callchain.c - 64bit is redundant
> v3:
> - use IS_ENABLED and maybe_unused where possible
> - do not ifdef declarations
> - clean up Makefile
> v4:
> - further makefile cleanup
> - simplify is_32bit_task conditions
> - avoid ifdef in condition by using return
> ---
> arch/powerpc/include/asm/thread_info.h | 4 ++--
> arch/powerpc/kernel/Makefile | 7 +++----
> arch/powerpc/kernel/entry_64.S | 2 ++
> arch/powerpc/kernel/signal.c | 3 +--
> arch/powerpc/kernel/syscall_64.c | 6 ++----
> arch/powerpc/kernel/vdso.c | 5 ++---
> arch/powerpc/perf/callchain.c | 14 ++++++++++----
> 7 files changed, 22 insertions(+), 19 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
> index 8e1d0195ac36..c128d8a48ea3 100644
> --- a/arch/powerpc/include/asm/thread_info.h
> +++ b/arch/powerpc/include/asm/thread_info.h
> @@ -144,10 +144,10 @@ static inline bool test_thread_local_flags(unsigned int flags)
> return (ti->local_flags & flags) != 0;
> }
>
> -#ifdef CONFIG_PPC64
> +#ifdef CONFIG_COMPAT
> #define is_32bit_task() (test_thread_flag(TIF_32BIT))
> #else
> -#define is_32bit_task() (1)
> +#define is_32bit_task() (IS_ENABLED(CONFIG_PPC32))
> #endif
>
> #if defined(CONFIG_PPC64)
> diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
> index 1d646a94d96c..9d8772e863b9 100644
> --- a/arch/powerpc/kernel/Makefile
> +++ b/arch/powerpc/kernel/Makefile
> @@ -44,16 +44,15 @@ CFLAGS_btext.o += -DDISABLE_BRANCH_PROFILING
> endif
>
> obj-y := cputable.o ptrace.o syscalls.o \
> - irq.o align.o signal_32.o pmc.o vdso.o \
> + irq.o align.o signal_$(BITS).o pmc.o vdso.o \
> process.o systbl.o idle.o \
> signal.o sysfs.o cacheinfo.o time.o \
> prom.o traps.o setup-common.o \
> udbg.o misc.o io.o misc_$(BITS).o \
> of_platform.o prom_parse.o
> -obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \
> - signal_64.o ptrace32.o \
> - paca.o nvram_64.o firmware.o \
> +obj-$(CONFIG_PPC64) += setup_64.o paca.o nvram_64.o firmware.o \
> syscall_64.o
> +obj-$(CONFIG_COMPAT) += sys_ppc32.o ptrace32.o signal_32.o
> obj-$(CONFIG_VDSO32) += vdso32/
> obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o
> obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
> diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
> index 2ec825a85f5b..a2dbf216f607 100644
> --- a/arch/powerpc/kernel/entry_64.S
> +++ b/arch/powerpc/kernel/entry_64.S
> @@ -51,8 +51,10 @@
> SYS_CALL_TABLE:
> .tc sys_call_table[TC],sys_call_table
>
> +#ifdef CONFIG_COMPAT
> COMPAT_SYS_CALL_TABLE:
> .tc compat_sys_call_table[TC],compat_sys_call_table
> +#endif
>
> /* This value is used to mark exception frames on the stack. */
> exception_marker:
> diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
> index 60436432399f..61678cb0e6a1 100644
> --- a/arch/powerpc/kernel/signal.c
> +++ b/arch/powerpc/kernel/signal.c
> @@ -247,7 +247,6 @@ static void do_signal(struct task_struct *tsk)
> sigset_t *oldset = sigmask_to_save();
> struct ksignal ksig = { .sig = 0 };
> int ret;
> - int is32 = is_32bit_task();
>
> BUG_ON(tsk != current);
>
> @@ -277,7 +276,7 @@ static void do_signal(struct task_struct *tsk)
>
> rseq_signal_deliver(&ksig, tsk->thread.regs);
>
> - if (is32) {
> + if (is_32bit_task()) {
> if (ksig.ka.sa.sa_flags & SA_SIGINFO)
> ret = handle_rt_signal32(&ksig, oldset, tsk);
> else
> diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
> index 98ed970796d5..0d5cbbe54cf1 100644
> --- a/arch/powerpc/kernel/syscall_64.c
> +++ b/arch/powerpc/kernel/syscall_64.c
> @@ -38,7 +38,6 @@ typedef long (*syscall_fn)(long, long, long, long, long, long);
>
> long system_call_exception(long r3, long r4, long r5, long r6, long r7, long r8, unsigned long r0, struct pt_regs *regs)
> {
> - unsigned long ti_flags;
> syscall_fn f;
>
> BUG_ON(!(regs->msr & MSR_PR));
> @@ -83,8 +82,7 @@ long system_call_exception(long r3, long r4, long r5, long r6, long r7, long r8,
> */
> regs->softe = IRQS_ENABLED;
>
> - ti_flags = current_thread_info()->flags;
> - if (unlikely(ti_flags & _TIF_SYSCALL_DOTRACE)) {
> + if (unlikely(current_thread_info()->flags & _TIF_SYSCALL_DOTRACE)) {
> /*
> * We use the return value of do_syscall_trace_enter() as the
> * syscall number. If the syscall was rejected for any reason
> @@ -100,7 +98,7 @@ long system_call_exception(long r3, long r4, long r5, long r6, long r7, long r8,
> /* May be faster to do array_index_nospec? */
> barrier_nospec();
>
> - if (unlikely(ti_flags & _TIF_32BIT)) {
> + if (unlikely(is_32bit_task())) {
> f = (void *)compat_sys_call_table[r0];
>
> r3 &= 0x00000000ffffffffULL;
> diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
> index d60598113a9f..6d4a077f74d6 100644
> --- a/arch/powerpc/kernel/vdso.c
> +++ b/arch/powerpc/kernel/vdso.c
> @@ -667,9 +667,7 @@ static void __init vdso_setup_syscall_map(void)
> {
> unsigned int i;
> extern unsigned long *sys_call_table;
> -#ifdef CONFIG_PPC64
> extern unsigned long *compat_sys_call_table;
> -#endif
> extern unsigned long sys_ni_syscall;
>
>
> @@ -678,7 +676,8 @@ static void __init vdso_setup_syscall_map(void)
> if (sys_call_table[i] != sys_ni_syscall)
> vdso_data->syscall_map_64[i >> 5] |=
> 0x80000000UL >> (i & 0x1f);
> - if (compat_sys_call_table[i] != sys_ni_syscall)
> + if (IS_ENABLED(CONFIG_COMPAT) &&
> + compat_sys_call_table[i] != sys_ni_syscall)
> vdso_data->syscall_map_32[i >> 5] |=
> 0x80000000UL >> (i & 0x1f);
> #else /* CONFIG_PPC64 */
> diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
> index c84bbd4298a0..aef8c750d242 100644
> --- a/arch/powerpc/perf/callchain.c
> +++ b/arch/powerpc/perf/callchain.c
> @@ -15,7 +15,7 @@
> #include <asm/sigcontext.h>
> #include <asm/ucontext.h>
> #include <asm/vdso.h>
> -#ifdef CONFIG_PPC64
> +#ifdef CONFIG_COMPAT
Is this ifdef needed at all ? Is it a problem to include it all the time ?
> #include "../kernel/ppc32.h"
> #endif
> #include <asm/pte-walk.h>
> @@ -165,6 +165,7 @@ static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret)
> return read_user_stack_slow(ptr, ret, 8);
> }
>
> +__maybe_unused
I don't like that too much. I see this function is almost identical
between PPC64 and PPC32. It should be possible to have only one, using
IS_ENABLED(CONFIG_PPC64) inside it to call read_user_stack_slow().
An define a dummy read_user_stack_slow() for PPC32 as already done for
perf_callchain_user_64().
> static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
> {
> if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned int) ||
> @@ -341,6 +342,7 @@ static inline int valid_user_sp(unsigned long sp, int is_64)
>
> #endif /* CONFIG_PPC64 */
>
> +#if defined(CONFIG_PPC32) || defined(CONFIG_COMPAT)
> /*
> * Layout for non-RT signal frames
> */
> @@ -482,12 +484,16 @@ static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
> sp = next_sp;
> }
> }
> +#endif /* 32bit */
>
> void
> perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
> {
> - if (current_is_64bit())
> - perf_callchain_user_64(entry, regs);
> - else
> +#if defined(CONFIG_PPC32) || defined(CONFIG_COMPAT)
> + if (!current_is_64bit()) {
> perf_callchain_user_32(entry, regs);
> + return;
> + }
> +#endif
> + perf_callchain_user_64(entry, regs);
> }
>
Instead of that it could just be:
if (current_is_64bit())
perf_callchain_user_64(entry, regs);
else
perf_callchain_user_32(entry, regs);
By adding a dummy perf_callchain_user_32() when needed as already done
for perf_callchain_user_64()
And by making sure current_is_64bit() returns IS_ENABLED(CONFIG_PPC64)
when CONFIG_COMPAT is not set, on the same principle as you did for
is_32bit_task()
And maybe you could think about spliting callchain.c out in a
callchain_32.c and a callchain_64.c that gets selected by the Makefiles
based on the same principle as you did for ptrace_32.c etc...
Christophe
^ permalink raw reply
* Re: [PATCH] sefltest/ima: support appended signatures (modsig)
From: Jordan Hand @ 2019-08-29 16:38 UTC (permalink / raw)
To: Mimi Zohar, linux-integrity
Cc: Dave Young, linuxppc-dev, linux-kernel, Petr Vorel,
linux-kselftest, Jessica Yu, shuah, Thiago Jung Bauermann
In-Reply-To: <1566995946-6582-1-git-send-email-zohar@linux.ibm.com>
On 8/28/19 5:39 AM, Mimi Zohar wrote:
> Detect and allow appended signatures.
Ran the tests successfully on x86_64 QEMU
Reviewed-by: Jordan Hand <jorhand@linux.microsoft.com>
Tested-by: Jordan Hand <jorhand@linux.microsoft.com>
^ permalink raw reply
* [PATCH v2 1/2] powerpc: Add PowerPC Capabilities ELF note
From: Maxiwell S. Garcia @ 2019-08-29 15:50 UTC (permalink / raw)
To: linuxppc-dev
Cc: linux-arch, andmike, linuxram, linux-kernel, kvm-ppc, cclaudio,
Maxiwell S . Garcia, bauerman
In-Reply-To: <20190829155021.2915-1-maxiwell@linux.ibm.com>
From: Claudio Carvalho <cclaudio@linux.ibm.com>
Add the PowerPC name and the PPC_ELFNOTE_CAPABILITIES type in the
kernel binary ELF note. This type is a bitmap that can be used to
advertise kernel capabilities to userland.
This patch also defines PPCCAP_ULTRAVISOR_BIT as being the bit zero.
Suggested-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Claudio Carvalho <cclaudio@linux.ibm.com>
[ maxiwell: Define the 'PowerPC' type in the elfnote.h ]
Signed-off-by: Maxiwell S. Garcia <maxiwell@linux.ibm.com>
---
arch/powerpc/include/asm/elfnote.h | 24 ++++++++++++++++++
arch/powerpc/kernel/Makefile | 2 +-
arch/powerpc/kernel/note.S | 40 ++++++++++++++++++++++++++++++
3 files changed, 65 insertions(+), 1 deletion(-)
create mode 100644 arch/powerpc/include/asm/elfnote.h
create mode 100644 arch/powerpc/kernel/note.S
diff --git a/arch/powerpc/include/asm/elfnote.h b/arch/powerpc/include/asm/elfnote.h
new file mode 100644
index 000000000000..a201b6e9ae44
--- /dev/null
+++ b/arch/powerpc/include/asm/elfnote.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * PowerPC ELF notes.
+ *
+ * Copyright 2019, IBM Corporation
+ */
+
+#ifndef __ASM_POWERPC_ELFNOTE_H__
+#define __ASM_POWERPC_ELFNOTE_H__
+
+/*
+ * These note types should live in a SHT_NOTE segment and have
+ * "PowerPC" in the name field.
+ */
+
+/*
+ * The capabilities supported/required by this kernel (bitmap).
+ *
+ * This type uses a bitmap as "desc" field. Each bit is described
+ * in arch/powerpc/kernel/note.S
+ */
+#define PPC_ELFNOTE_CAPABILITIES 1
+
+#endif /* __ASM_POWERPC_ELFNOTE_H__ */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 56dfa7a2a6f2..0fcd3045284f 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -52,7 +52,7 @@ obj-y := cputable.o ptrace.o syscalls.o \
of_platform.o prom_parse.o
obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \
signal_64.o ptrace32.o \
- paca.o nvram_64.o firmware.o
+ paca.o nvram_64.o firmware.o note.o
obj-$(CONFIG_VDSO32) += vdso32/
obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
diff --git a/arch/powerpc/kernel/note.S b/arch/powerpc/kernel/note.S
new file mode 100644
index 000000000000..bcdad15395dd
--- /dev/null
+++ b/arch/powerpc/kernel/note.S
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * PowerPC ELF notes.
+ *
+ * Copyright 2019, IBM Corporation
+ */
+
+#include <linux/elfnote.h>
+#include <asm/elfnote.h>
+
+/*
+ * Ultravisor-capable bit (PowerNV only).
+ *
+ * Bit 0 indicates that the powerpc kernel binary knows how to run in an
+ * ultravisor-enabled system.
+ *
+ * In an ultravisor-enabled system, some machine resources are now controlled
+ * by the ultravisor. If the kernel is not ultravisor-capable, but it ends up
+ * being run on a machine with ultravisor, the kernel will probably crash
+ * trying to access ultravisor resources. For instance, it may crash in early
+ * boot trying to set the partition table entry 0.
+ *
+ * In an ultravisor-enabled system, a bootloader could warn the user or prevent
+ * the kernel from being run if the PowerPC ultravisor capability doesn't exist
+ * or the Ultravisor-capable bit is not set.
+ */
+#ifdef CONFIG_PPC_POWERNV
+#define PPCCAP_ULTRAVISOR_BIT (1 << 0)
+#else
+#define PPCCAP_ULTRAVISOR_BIT 0
+#endif
+
+/*
+ * Add the PowerPC Capabilities in the binary ELF note. It is a bitmap that
+ * can be used to advertise kernel capabilities to userland.
+ */
+#define PPC_CAPABILITIES_BITMAP (PPCCAP_ULTRAVISOR_BIT)
+
+ELFNOTE(PowerPC, PPC_ELFNOTE_CAPABILITIES,
+ .long PPC_CAPABILITIES_BITMAP)
--
2.20.1
^ permalink raw reply related
* [PATCH v2 2/2] docs: powerpc: Add ELF note documentation
From: Maxiwell S. Garcia @ 2019-08-29 15:50 UTC (permalink / raw)
To: linuxppc-dev
Cc: linux-arch, andmike, linuxram, linux-kernel, kvm-ppc, cclaudio,
Maxiwell S. Garcia, bauerman
In-Reply-To: <20190829155021.2915-1-maxiwell@linux.ibm.com>
The ELF note documentation describes the types and descriptors to be
used with the PowerPC namespace.
Signed-off-by: Maxiwell S. Garcia <maxiwell@linux.ibm.com>
Signed-off-by: Claudio Carvalho <cclaudio@linux.ibm.com>
---
Documentation/powerpc/elfnote.rst | 42 +++++++++++++++++++++++++++++++
1 file changed, 42 insertions(+)
create mode 100644 Documentation/powerpc/elfnote.rst
diff --git a/Documentation/powerpc/elfnote.rst b/Documentation/powerpc/elfnote.rst
new file mode 100644
index 000000000000..2a5c4beeb809
--- /dev/null
+++ b/Documentation/powerpc/elfnote.rst
@@ -0,0 +1,42 @@
+==========================
+ELF Note PowerPC Namespace
+==========================
+
+The PowerPC namespace in an ELF Note of the kernel binary is used to store
+capabilities and information which can be used by a bootloader or userland.
+
+Types and Descriptors
+---------------------
+
+The types to be used with the "PowerPC" namesapce are defined in the
+include/uapi/asm/elfnote.h
+
+ 1) PPC_ELFNOTE_CAPABILITIES
+
+Define the capabilities supported/required by the kernel. This type uses a
+bitmap as "descriptor" field. Each bit is described below:
+
+- Ultravisor-capable bit (PowerNV only).
+
+ #define PPCCAP_ULTRAVISOR_BIT (1 << 0)
+
+ Indicate that the powerpc kernel binary knows how to run in an
+ ultravisor-enabled system.
+
+ In an ultravisor-enabled system, some machine resources are now controlled
+ by the ultravisor. If the kernel is not ultravisor-capable, but it ends up
+ being run on a machine with ultravisor, the kernel will probably crash
+ trying to access ultravisor resources. For instance, it may crash in early
+ boot trying to set the partition table entry 0.
+
+ In an ultravisor-enabled system, a bootloader could warn the user or prevent
+ the kernel from being run if the PowerPC ultravisor capability doesn't exist
+ or the Ultravisor-capable bit is not set.
+
+References
+----------
+
+arch/powerpc/include/asm/elfnote.h
+arch/powerpc/kernel/note.S
+
+
--
2.20.1
^ permalink raw reply related
* [PATCH v2 0/2] powerpc: Add PowerPC Capabilities ELF note
From: Maxiwell S. Garcia @ 2019-08-29 15:50 UTC (permalink / raw)
To: linuxppc-dev
Cc: linux-arch, andmike, linuxram, linux-kernel, kvm-ppc, cclaudio,
Maxiwell S. Garcia, bauerman
The first patch adds the PowerPC name and the PPC_ELFNOTE_CAPABILITIES
type in the kernel binary ELF note. This type is a bitmap that can be
used to advertise kernel capabilities to userland.
The second patch adds a new documentation file to detail the
ELF Note PowerPC namespace and the PPC_ELFNOTE_CAPABILITIES type.
V2:
* Create the header arch/powerpc/include/asm/elfnote.h with the
new type PPC_ELFNOTE_CAPABILITIES
* Add documentation file in powerpc dir
Claudio Carvalho (1):
powerpc: Add PowerPC Capabilities ELF note
Maxiwell S. Garcia (1):
docs: powerpc: Add ELF note documentation
Documentation/powerpc/elfnote.rst | 42 ++++++++++++++++++++++++++++++
arch/powerpc/include/asm/elfnote.h | 24 +++++++++++++++++
arch/powerpc/kernel/Makefile | 2 +-
arch/powerpc/kernel/note.S | 40 ++++++++++++++++++++++++++++
4 files changed, 107 insertions(+), 1 deletion(-)
create mode 100644 Documentation/powerpc/elfnote.rst
create mode 100644 arch/powerpc/include/asm/elfnote.h
create mode 100644 arch/powerpc/kernel/note.S
--
2.20.1
^ permalink raw reply
* Re: [PATCH v2 0/4] powerpc/64: syscalls in C
From: Nicholas Piggin @ 2019-08-29 15:49 UTC (permalink / raw)
To: Segher Boessenkool; +Cc: linuxppc-dev
In-Reply-To: <20190829115122.GJ31406@gate.crashing.org>
Segher Boessenkool's on August 29, 2019 9:51 pm:
> On Thu, Aug 29, 2019 at 07:38:01PM +1000, Nicholas Piggin wrote:
>> So... this actually seems to work. Haven't booted it, but the compiler
>> seems to do what we want.
>
> From the GCC manual:
>
> After defining a global register variable, for the current compilation
> unit:
>
> * If the register is a call-saved register, call ABI is affected: the
> register will not be restored in function epilogue sequences after
> the variable has been assigned. Therefore, functions cannot safely
> return to callers that assume standard ABI.
>
> and
>
> * Accesses to the variable may be optimized as usual and the register
> remains available for allocation and use in any computations,
> provided that observable values of the variable are not affected.
>
> This doesn't do what you think, or what you want, or what you think you
> want ;-)
After reading gcc docs from gcc 4 to 9, I think it does.
We want this to apply to all functions in the compilaition unit. It's
fine to use the regs temporarily, and so it's fine for called functions
in other units to call them (because they will be restored), and we
don't want them restored for our caller.
> (And if you make all those regs -ffixed-* you are in for a world of hurt).
From the look of it, -ffixed would be a little bit stronger in that it
will never allow the register to be used, wheras the global register
variable allows it to be allocated and used elsewhere so long as its
observable value is not affected. The latter is actually preferred
because it's fine for the compiler to use the regs if it wants to. It
does not even have to use r15 register when I reference r15 variable,
only whatever value it had.
Thanks,
Nick
^ permalink raw reply
* Re: remove default fallbacks in dma_map_ops v3
From: Christoph Hellwig @ 2019-08-29 15:38 UTC (permalink / raw)
To: iommu, Marek Szyprowski
Cc: linux-xtensa, Michal Simek, Vladimir Murzin, linux-parisc,
linux-sh, Takashi Iwai, Robin Murphy, Helge Deller, x86,
linux-kernel, linux-m68k, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20190808160005.10325-1-hch@lst.de>
I've applied this to the dma-mapping for-next tree now.
If there are any issues with the parisc patch I'll happily take
incremental patches.
^ permalink raw reply
* Re: cleanup the dma_pgprot handling v2
From: Christoph Hellwig @ 2019-08-29 15:28 UTC (permalink / raw)
To: iommu
Cc: Shawn Anastasio, Will Deacon, linuxppc-dev, linux-kernel,
linux-m68k, Geert Uytterhoeven, Paul Burton, Catalin Marinas,
James Hogan, Russell King, linux-mips, Guan Xuetao,
linux-arm-kernel, Robin Murphy
In-Reply-To: <20190826132553.4116-1-hch@lst.de>
I've pulled this into the dma-mapping for-next tree now.
^ permalink raw reply
* [PATCH 01/37] perf arch powerpc: Sync powerpc syscall.tbl
From: Arnaldo Carvalho de Melo @ 2019-08-29 14:38 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Ravi Bangoria, Arnaldo Carvalho de Melo, Clark Williams,
linux-kernel, Nicholas Piggin, linux-perf-users, Jiri Olsa,
Namhyung Kim, Naveen N. Rao, linuxppc-dev
In-Reply-To: <20190829143917.29745-1-acme@kernel.org>
From: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Copy over powerpc syscall.tbl to grab changes from the below commits:
commit cee3536d24a1 ("powerpc: Wire up clone3 syscall")
commit 1a271a68e030 ("arch: mark syscall number 435 reserved for clone3")
commit 7615d9e1780e ("arch: wire-up pidfd_open()")
commit d8076bdb56af ("uapi: Wire up the mount API syscalls on non-x86 arches [ver #2]")
commit 39036cd27273 ("arch: add pidfd and io_uring syscalls everywhere")
commit 48166e6ea47d ("y2038: add 64-bit time_t syscalls to all 32-bit architectures")
commit d33c577cccd0 ("y2038: rename old time and utime syscalls")
commit 00bf25d693e7 ("y2038: use time32 syscall names on 32-bit")
commit 8dabe7245bbc ("y2038: syscalls: rename y2038 compat syscalls")
commit 0d6040d46817 ("arch: add split IPC system calls where needed")
Reported-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: linuxppc-dev@lists.ozlabs.org
Link: http://lkml.kernel.org/r/20190827071458.19897-1-naveen.n.rao@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
.../arch/powerpc/entry/syscalls/syscall.tbl | 146 ++++++++++++++----
1 file changed, 119 insertions(+), 27 deletions(-)
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index db3bbb8744af..43f736ed47f2 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -20,7 +20,9 @@
10 common unlink sys_unlink
11 nospu execve sys_execve compat_sys_execve
12 common chdir sys_chdir
-13 common time sys_time compat_sys_time
+13 32 time sys_time32
+13 64 time sys_time
+13 spu time sys_time
14 common mknod sys_mknod
15 common chmod sys_chmod
16 common lchown sys_lchown
@@ -36,14 +38,17 @@
22 spu umount sys_ni_syscall
23 common setuid sys_setuid
24 common getuid sys_getuid
-25 common stime sys_stime compat_sys_stime
+25 32 stime sys_stime32
+25 64 stime sys_stime
+25 spu stime sys_stime
26 nospu ptrace sys_ptrace compat_sys_ptrace
27 common alarm sys_alarm
28 32 oldfstat sys_fstat sys_ni_syscall
28 64 oldfstat sys_ni_syscall
28 spu oldfstat sys_ni_syscall
29 nospu pause sys_pause
-30 nospu utime sys_utime compat_sys_utime
+30 32 utime sys_utime32
+30 64 utime sys_utime
31 common stty sys_ni_syscall
32 common gtty sys_ni_syscall
33 common access sys_access
@@ -157,7 +162,9 @@
121 common setdomainname sys_setdomainname
122 common uname sys_newuname
123 common modify_ldt sys_ni_syscall
-124 common adjtimex sys_adjtimex compat_sys_adjtimex
+124 32 adjtimex sys_adjtimex_time32
+124 64 adjtimex sys_adjtimex
+124 spu adjtimex sys_adjtimex
125 common mprotect sys_mprotect
126 32 sigprocmask sys_sigprocmask compat_sys_sigprocmask
126 64 sigprocmask sys_ni_syscall
@@ -198,8 +205,12 @@
158 common sched_yield sys_sched_yield
159 common sched_get_priority_max sys_sched_get_priority_max
160 common sched_get_priority_min sys_sched_get_priority_min
-161 common sched_rr_get_interval sys_sched_rr_get_interval compat_sys_sched_rr_get_interval
-162 common nanosleep sys_nanosleep compat_sys_nanosleep
+161 32 sched_rr_get_interval sys_sched_rr_get_interval_time32
+161 64 sched_rr_get_interval sys_sched_rr_get_interval
+161 spu sched_rr_get_interval sys_sched_rr_get_interval
+162 32 nanosleep sys_nanosleep_time32
+162 64 nanosleep sys_nanosleep
+162 spu nanosleep sys_nanosleep
163 common mremap sys_mremap
164 common setresuid sys_setresuid
165 common getresuid sys_getresuid
@@ -213,7 +224,8 @@
173 nospu rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction
174 nospu rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask
175 nospu rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending
-176 nospu rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait
+176 32 rt_sigtimedwait sys_rt_sigtimedwait_time32 compat_sys_rt_sigtimedwait_time32
+176 64 rt_sigtimedwait sys_rt_sigtimedwait
177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo
178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend
179 common pread64 sys_pread64 compat_sys_pread64
@@ -260,7 +272,9 @@
218 common removexattr sys_removexattr
219 common lremovexattr sys_lremovexattr
220 common fremovexattr sys_fremovexattr
-221 common futex sys_futex compat_sys_futex
+221 32 futex sys_futex_time32
+221 64 futex sys_futex
+221 spu futex sys_futex
222 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity
223 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity
# 224 unused
@@ -268,7 +282,9 @@
226 32 sendfile64 sys_sendfile64 compat_sys_sendfile64
227 common io_setup sys_io_setup compat_sys_io_setup
228 common io_destroy sys_io_destroy
-229 common io_getevents sys_io_getevents compat_sys_io_getevents
+229 32 io_getevents sys_io_getevents_time32
+229 64 io_getevents sys_io_getevents
+229 spu io_getevents sys_io_getevents
230 common io_submit sys_io_submit compat_sys_io_submit
231 common io_cancel sys_io_cancel
232 nospu set_tid_address sys_set_tid_address
@@ -280,19 +296,33 @@
238 common epoll_wait sys_epoll_wait
239 common remap_file_pages sys_remap_file_pages
240 common timer_create sys_timer_create compat_sys_timer_create
-241 common timer_settime sys_timer_settime compat_sys_timer_settime
-242 common timer_gettime sys_timer_gettime compat_sys_timer_gettime
+241 32 timer_settime sys_timer_settime32
+241 64 timer_settime sys_timer_settime
+241 spu timer_settime sys_timer_settime
+242 32 timer_gettime sys_timer_gettime32
+242 64 timer_gettime sys_timer_gettime
+242 spu timer_gettime sys_timer_gettime
243 common timer_getoverrun sys_timer_getoverrun
244 common timer_delete sys_timer_delete
-245 common clock_settime sys_clock_settime compat_sys_clock_settime
-246 common clock_gettime sys_clock_gettime compat_sys_clock_gettime
-247 common clock_getres sys_clock_getres compat_sys_clock_getres
-248 common clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep
+245 32 clock_settime sys_clock_settime32
+245 64 clock_settime sys_clock_settime
+245 spu clock_settime sys_clock_settime
+246 32 clock_gettime sys_clock_gettime32
+246 64 clock_gettime sys_clock_gettime
+246 spu clock_gettime sys_clock_gettime
+247 32 clock_getres sys_clock_getres_time32
+247 64 clock_getres sys_clock_getres
+247 spu clock_getres sys_clock_getres
+248 32 clock_nanosleep sys_clock_nanosleep_time32
+248 64 clock_nanosleep sys_clock_nanosleep
+248 spu clock_nanosleep sys_clock_nanosleep
249 32 swapcontext ppc_swapcontext ppc32_swapcontext
249 64 swapcontext ppc64_swapcontext
249 spu swapcontext sys_ni_syscall
250 common tgkill sys_tgkill
-251 common utimes sys_utimes compat_sys_utimes
+251 32 utimes sys_utimes_time32
+251 64 utimes sys_utimes
+251 spu utimes sys_utimes
252 common statfs64 sys_statfs64 compat_sys_statfs64
253 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64
254 32 fadvise64_64 ppc_fadvise64_64
@@ -308,8 +338,10 @@
261 nospu set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy
262 nospu mq_open sys_mq_open compat_sys_mq_open
263 nospu mq_unlink sys_mq_unlink
-264 nospu mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend
-265 nospu mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive
+264 32 mq_timedsend sys_mq_timedsend_time32
+264 64 mq_timedsend sys_mq_timedsend
+265 32 mq_timedreceive sys_mq_timedreceive_time32
+265 64 mq_timedreceive sys_mq_timedreceive
266 nospu mq_notify sys_mq_notify compat_sys_mq_notify
267 nospu mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr
268 nospu kexec_load sys_kexec_load compat_sys_kexec_load
@@ -324,8 +356,10 @@
277 nospu inotify_rm_watch sys_inotify_rm_watch
278 nospu spu_run sys_spu_run
279 nospu spu_create sys_spu_create
-280 nospu pselect6 sys_pselect6 compat_sys_pselect6
-281 nospu ppoll sys_ppoll compat_sys_ppoll
+280 32 pselect6 sys_pselect6_time32 compat_sys_pselect6_time32
+280 64 pselect6 sys_pselect6
+281 32 ppoll sys_ppoll_time32 compat_sys_ppoll_time32
+281 64 ppoll sys_ppoll
282 common unshare sys_unshare
283 common splice sys_splice
284 common tee sys_tee
@@ -334,7 +368,9 @@
287 common mkdirat sys_mkdirat
288 common mknodat sys_mknodat
289 common fchownat sys_fchownat
-290 common futimesat sys_futimesat compat_sys_futimesat
+290 32 futimesat sys_futimesat_time32
+290 64 futimesat sys_futimesat
+290 spu utimesat sys_futimesat
291 32 fstatat64 sys_fstatat64
291 64 newfstatat sys_newfstatat
291 spu newfstatat sys_newfstatat
@@ -350,15 +386,21 @@
301 common move_pages sys_move_pages compat_sys_move_pages
302 common getcpu sys_getcpu
303 nospu epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait
-304 common utimensat sys_utimensat compat_sys_utimensat
+304 32 utimensat sys_utimensat_time32
+304 64 utimensat sys_utimensat
+304 spu utimensat sys_utimensat
305 common signalfd sys_signalfd compat_sys_signalfd
306 common timerfd_create sys_timerfd_create
307 common eventfd sys_eventfd
308 common sync_file_range2 sys_sync_file_range2 compat_sys_sync_file_range2
309 nospu fallocate sys_fallocate compat_sys_fallocate
310 nospu subpage_prot sys_subpage_prot
-311 common timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime
-312 common timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime
+311 32 timerfd_settime sys_timerfd_settime32
+311 64 timerfd_settime sys_timerfd_settime
+311 spu timerfd_settime sys_timerfd_settime
+312 32 timerfd_gettime sys_timerfd_gettime32
+312 64 timerfd_gettime sys_timerfd_gettime
+312 spu timerfd_gettime sys_timerfd_gettime
313 common signalfd4 sys_signalfd4 compat_sys_signalfd4
314 common eventfd2 sys_eventfd2
315 common epoll_create1 sys_epoll_create1
@@ -389,11 +431,15 @@
340 common getsockopt sys_getsockopt compat_sys_getsockopt
341 common sendmsg sys_sendmsg compat_sys_sendmsg
342 common recvmsg sys_recvmsg compat_sys_recvmsg
-343 common recvmmsg sys_recvmmsg compat_sys_recvmmsg
+343 32 recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32
+343 64 recvmmsg sys_recvmmsg
+343 spu recvmmsg sys_recvmmsg
344 common accept4 sys_accept4
345 common name_to_handle_at sys_name_to_handle_at
346 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at
-347 common clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime
+347 32 clock_adjtime sys_clock_adjtime32
+347 64 clock_adjtime sys_clock_adjtime
+347 spu clock_adjtime sys_clock_adjtime
348 common syncfs sys_syncfs
349 common sendmmsg sys_sendmmsg compat_sys_sendmmsg
350 common setns sys_setns
@@ -414,6 +460,7 @@
363 spu switch_endian sys_ni_syscall
364 common userfaultfd sys_userfaultfd
365 common membarrier sys_membarrier
+# 366-377 originally left for IPC, now unused
378 nospu mlock2 sys_mlock2
379 nospu copy_file_range sys_copy_file_range
380 common preadv2 sys_preadv2 compat_sys_preadv2
@@ -424,4 +471,49 @@
385 nospu pkey_free sys_pkey_free
386 nospu pkey_mprotect sys_pkey_mprotect
387 nospu rseq sys_rseq
-388 nospu io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents
+388 32 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents
+388 64 io_pgetevents sys_io_pgetevents
+# room for arch specific syscalls
+392 64 semtimedop sys_semtimedop
+393 common semget sys_semget
+394 common semctl sys_semctl compat_sys_semctl
+395 common shmget sys_shmget
+396 common shmctl sys_shmctl compat_sys_shmctl
+397 common shmat sys_shmat compat_sys_shmat
+398 common shmdt sys_shmdt
+399 common msgget sys_msgget
+400 common msgsnd sys_msgsnd compat_sys_msgsnd
+401 common msgrcv sys_msgrcv compat_sys_msgrcv
+402 common msgctl sys_msgctl compat_sys_msgctl
+403 32 clock_gettime64 sys_clock_gettime sys_clock_gettime
+404 32 clock_settime64 sys_clock_settime sys_clock_settime
+405 32 clock_adjtime64 sys_clock_adjtime sys_clock_adjtime
+406 32 clock_getres_time64 sys_clock_getres sys_clock_getres
+407 32 clock_nanosleep_time64 sys_clock_nanosleep sys_clock_nanosleep
+408 32 timer_gettime64 sys_timer_gettime sys_timer_gettime
+409 32 timer_settime64 sys_timer_settime sys_timer_settime
+410 32 timerfd_gettime64 sys_timerfd_gettime sys_timerfd_gettime
+411 32 timerfd_settime64 sys_timerfd_settime sys_timerfd_settime
+412 32 utimensat_time64 sys_utimensat sys_utimensat
+413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64
+414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64
+416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents
+417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64
+418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend
+419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive
+420 32 semtimedop_time64 sys_semtimedop sys_semtimedop
+421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64
+422 32 futex_time64 sys_futex sys_futex
+423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
+428 common open_tree sys_open_tree
+429 common move_mount sys_move_mount
+430 common fsopen sys_fsopen
+431 common fsconfig sys_fsconfig
+432 common fsmount sys_fsmount
+433 common fspick sys_fspick
+434 common pidfd_open sys_pidfd_open
+435 nospu clone3 ppc_clone3
--
2.21.0
^ permalink raw reply related
* Re: [PATCH v4 1/4] powerpc: make llseek 32bit-only.
From: Arnd Bergmann @ 2019-08-29 14:32 UTC (permalink / raw)
To: Michal Suchánek
Cc: Michael Neuling, Allison Randal, Nicolai Stange,
David Hildenbrand, Greg Kroah-Hartman, Christian Brauner,
Heiko Carstens, Linux Kernel Mailing List, Nicholas Piggin,
Geert Uytterhoeven, David Howells, Paul Mackerras, Joel Stanley,
Andrew Donnellan, Breno Leitao, Firoz Khan, Thomas Gleixner,
linuxppc-dev, Hari Bathini, Eric W. Biederman
In-Reply-To: <20190829161923.101ff3eb@kitsune.suse.cz>
On Thu, Aug 29, 2019 at 4:19 PM Michal Suchánek <msuchanek@suse.de> wrote:
> On Thu, 29 Aug 2019 14:57:39 +0200 Arnd Bergmann <arnd@arndb.de> wrote:
> > On Thu, Aug 29, 2019 at 2:37 PM Michal Suchánek <msuchanek@suse.de> wrote:
> > > On Thu, 29 Aug 2019 14:19:46 +0200 Arnd Bergmann <arnd@arndb.de> wrote:
> > > > On Thu, Aug 29, 2019 at 12:23 PM Michal Suchanek <msuchanek@suse.de> wrote:
> > > > In particular, I don't see why you single out llseek here, but leave other
> > > > syscalls that are not needed on 64-bit machines such as pread64().
> > >
> > > Because llseek is not built in fs/ when building 64bit only causing a
> > > link error.
> > >
> > > I initially posted patch to build it always but it was pointed out it
> > > is not needed, and the interface does not make sense on 64bit, and
> > > that platforms that don't have it on 64bit now don't want that useless
> > > code.
> >
> > Ok, please put that into the changeset description then.
> >
> > I looked at uses of __NR__llseek in debian code search and
> > found this one:
> >
> > https://codesearch.debian.net/show?file=umview_0.8.2-1.2%2Fxmview%2Fum_mmap.c&line=328
> >
> > It looks like this application will try to use llseek instead of lseek
> > when built against kernel headers that define __NR_llseek.
> >
>
> The available documentation says this syscall is for 32bit only so
> using it on 64bit is undefined. The interface is not well-defined in
> that case either.
That's generally not how it works. If there is an existing application
that relies on the behavior of the system call interface, we should not
change it in a way that breaks the application, regardless of what the
documentation says. Presumably nobody cares about umview on
powerpc64, but there might be other applications doing the same
thing.
It looks like sparc64 and parisc64 do the same thing as powerpc64,
and provide llseek() calls that may or may not be used by
applications.
I think your original approach of always building sys_llseek on
powerpc64 is the safe choice here.
Arnd
^ permalink raw reply
* Re: [PATCH v4 1/4] powerpc: make llseek 32bit-only.
From: Michal Suchánek @ 2019-08-29 14:19 UTC (permalink / raw)
To: Arnd Bergmann
Cc: Michael Neuling, Allison Randal, Nicolai Stange,
David Hildenbrand, Greg Kroah-Hartman, Christian Brauner,
Heiko Carstens, Linux Kernel Mailing List, Nicholas Piggin,
Geert Uytterhoeven, David Howells, Paul Mackerras, Joel Stanley,
Andrew Donnellan, Breno Leitao, Firoz Khan, Thomas Gleixner,
linuxppc-dev, Hari Bathini, Eric W. Biederman
In-Reply-To: <CAK8P3a2DHP+8Vbc4yjq5-wT9GpSxvndCa8gnvx0WcD8YAUAsMw@mail.gmail.com>
On Thu, 29 Aug 2019 14:57:39 +0200
Arnd Bergmann <arnd@arndb.de> wrote:
> On Thu, Aug 29, 2019 at 2:37 PM Michal Suchánek <msuchanek@suse.de> wrote:
> > On Thu, 29 Aug 2019 14:19:46 +0200 Arnd Bergmann <arnd@arndb.de> wrote:
> > > On Thu, Aug 29, 2019 at 12:23 PM Michal Suchanek <msuchanek@suse.de> wrote:
> > > In particular, I don't see why you single out llseek here, but leave other
> > > syscalls that are not needed on 64-bit machines such as pread64().
> >
> > Because llseek is not built in fs/ when building 64bit only causing a
> > link error.
> >
> > I initially posted patch to build it always but it was pointed out it
> > is not needed, and the interface does not make sense on 64bit, and
> > that platforms that don't have it on 64bit now don't want that useless
> > code.
>
> Ok, please put that into the changeset description then.
>
> I looked at uses of __NR__llseek in debian code search and
> found this one:
>
> https://codesearch.debian.net/show?file=umview_0.8.2-1.2%2Fxmview%2Fum_mmap.c&line=328
>
> It looks like this application will try to use llseek instead of lseek
> when built against kernel headers that define __NR_llseek.
>
The available documentation says this syscall is for 32bit only so
using it on 64bit is undefined. The interface is not well-defined in
that case either.
Thanks
Michal
^ permalink raw reply
* RE: [PATCH] powerpc: Avoid clang warnings around setjmp and longjmp
From: David Laight @ 2019-08-29 9:59 UTC (permalink / raw)
To: 'Nathan Chancellor', Nick Desaulniers
Cc: LKML, # 3.4.x, clang-built-linux, Paul Mackerras, linuxppc-dev
In-Reply-To: <20190828184529.GC127646@archlinux-threadripper>
From: Nathan Chancellor
> Sent: 28 August 2019 19:45
...
> However, I think that -fno-builtin-* would be appropriate here because
> we are providing our own setjmp implementation, meaning clang should not
> be trying to do anything with the builtin implementation like building a
> declaration for it.
Isn't implementing setjmp impossible unless you tell the compiler that
you function is 'setjmp-like' ?
For instance I think it all goes horribly wrong if the generated code
looks like:
push local_variable
// setup arguments to setjmp
call setjmp
pop local_variable
// check return value of setjmp
With a naive compiler and simple ABI setjmp just has to save the
return address, stack pointer and caller saved registers.
With modern compilers and ABI I doubt you can implement setjmp
without some help from the compiler.
It is probably best to avoid setjmp/longjmp completely.
David
-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)
^ permalink raw reply
* Re: [PATCH RESEND v11 7/8] open: openat2(2) syscall
From: Aleksa Sarai @ 2019-08-29 13:19 UTC (permalink / raw)
To: Rasmus Villemoes
Cc: linux-ia64, linux-sh, Alexei Starovoitov, linux-kernel,
David Howells, open list:KERNEL SELFTEST FRAMEWORK, sparclinux,
Shuah Khan, linux-arch, linux-s390, Daniel Colascione,
Aleksa Sarai, linux-arm-kernel, linux-mips, linux-xtensa,
Kees Cook, Arnd Bergmann, Jann Horn, Tycho Andersen, linux-m68k,
Al Viro, Andy Lutomirski, Shuah Khan, David Drysdale,
Christian Brauner, J. Bruce Fields, linux-parisc, Linux API,
Chanho Min, linuxppc-dev, Jeff Layton, Oleg Nesterov,
Eric Biederman, linux-alpha, Linux FS Devel, Andrew Morton,
Linus Torvalds, containers
In-Reply-To: <899401fa-ff0a-2ce9-8826-09904efab2d2@rasmusvillemoes.dk>
[-- Attachment #1: Type: text/plain, Size: 3601 bytes --]
On 2019-08-29, Rasmus Villemoes <linux@rasmusvillemoes.dk> wrote:
> On 29/08/2019 14.15, Aleksa Sarai wrote:
> > On 2019-08-24, Daniel Colascione <dancol@google.com> wrote:
>
> >> Why pad the structure when new functionality (perhaps accommodated via
> >> a larger structure) could be signaled by passing a new flag? Adding
> >> reserved fields to a structure with a size embedded in the ABI makes a
> >> lot of sense --- e.g., pthread_mutex_t can't grow. But this structure
> >> can grow, so the reservation seems needless to me.
> >
> > Quite a few folks have said that ->reserved is either unnecessary or
> > too big. I will be changing this, though I am not clear what the best
> > way of extending the structure is. If anyone has a strong opinion on
> > this (or an alternative to the ones listed below), please chime in. I
> > don't have any really strong attachment to this aspect of the API.
> >
> > There appear to be a few ways we can do it (that all have precedence
> > with other syscalls):
> >
> > 1. Use O_* flags to indicate extensions.
> > 2. A separate "version" field that is incremented when we change.
> > 3. Add a size_t argument to openat2(2).
> > 4. Reserve space (as in this patchset).
> >
> > (My personal preference would be (3), followed closely by (2).)
>
> 3, definitely, and instead of having to invent a new scheme for every
> new syscall, make that the default pattern by providing a helper
Sure (though hopefully I don't need to immediately go and refactor all
the existing size_t syscalls). I will be presenting about this patchset
at the containers microconference at LPC (in a few weeks), so I'll hold
of on any API-related rewrites until after that.
> int __copy_abi_struct(void *kernel, size_t ksize, const void __user
> *user, size_t usize)
> {
> size_t copy = min(ksize, usize);
>
> if (copy_from_user(kernel, user, copy))
> return -EFAULT;
>
> if (usize > ksize) {
> /* maybe a separate "return user_is_zero(user + ksize, usize -
> ksize);" helper */
> char c;
> user += ksize;
> usize -= ksize;
> while (usize--) {
> if (get_user(c, user++))
> return -EFAULT;
> if (c)
> return -EINVAL;
This part would probably be better done with memchr_inv() and
copy_from_user() (and probably should put an upper limit on usize), but
I get what you mean.
> }
> } else if (ksize > usize) {
> memset(kernel + usize, 0, ksize - usize);
> }
> return 0;
> }
> #define copy_abi_struct(kernel, user, usize) \
> __copy_abi_struct(kernel, sizeof(*kernel), user, usize)
>
> > Both (1) and (2) have the problem that the "struct version" is inside
> > the struct so we'd need to copy_from_user() twice. This isn't the end of
> > the world, it just feels a bit less clean than is ideal. (3) fixes that
> > problem, at the cost of making the API slightly more cumbersome to use
> > directly (though again glibc could wrap that away).
>
> I don't see how 3 is cumbersome to use directly. Userspace code does
> struct openat_of_the_day args = {.field1 = x, .field3 = y} and passes
> &args, sizeof(args). What does glibc need to do beyond its usual munging
> of the userspace ABI registers to the syscall ABI registers?
I'd argue that
ret = openat2(AT_FDCWD, "foo", &how, sizeof(how)); // (3)
is slightly less pretty than
ret = openat2(AT_FDCWD, "foo", &how); // (1), (2), (4)
But it's not really that bad. Forget I said anything.
--
Aleksa Sarai
Senior Software Engineer (Containers)
SUSE Linux GmbH
<https://www.cyphar.com/>
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]
^ permalink raw reply
* Re: [PATCH RESEND v11 7/8] open: openat2(2) syscall
From: Rasmus Villemoes @ 2019-08-29 13:05 UTC (permalink / raw)
To: Aleksa Sarai, Daniel Colascione
Cc: linux-ia64, linux-sh, Alexei Starovoitov, linux-kernel,
David Howells, open list:KERNEL SELFTEST FRAMEWORK, sparclinux,
Shuah Khan, linux-arch, linux-s390, Tycho Andersen, Aleksa Sarai,
linux-arm-kernel, linux-mips, linux-xtensa, Kees Cook,
Arnd Bergmann, Jann Horn, linuxppc-dev, linux-m68k, Al Viro,
Andy Lutomirski, Shuah Khan, David Drysdale, Christian Brauner,
J. Bruce Fields, linux-parisc, Linux API, Chanho Min, Jeff Layton,
Oleg Nesterov, Eric Biederman, linux-alpha, Linux FS Devel,
Andrew Morton, Linus Torvalds, containers
In-Reply-To: <20190829121527.u2uvdyeatme5cgkb@yavin>
On 29/08/2019 14.15, Aleksa Sarai wrote:
> On 2019-08-24, Daniel Colascione <dancol@google.com> wrote:
>> Why pad the structure when new functionality (perhaps accommodated via
>> a larger structure) could be signaled by passing a new flag? Adding
>> reserved fields to a structure with a size embedded in the ABI makes a
>> lot of sense --- e.g., pthread_mutex_t can't grow. But this structure
>> can grow, so the reservation seems needless to me.
>
> Quite a few folks have said that ->reserved is either unnecessary or
> too big. I will be changing this, though I am not clear what the best
> way of extending the structure is. If anyone has a strong opinion on
> this (or an alternative to the ones listed below), please chime in. I
> don't have any really strong attachment to this aspect of the API.
>
> There appear to be a few ways we can do it (that all have precedence
> with other syscalls):
>
> 1. Use O_* flags to indicate extensions.
> 2. A separate "version" field that is incremented when we change.
> 3. Add a size_t argument to openat2(2).
> 4. Reserve space (as in this patchset).
>
> (My personal preference would be (3), followed closely by (2).)
3, definitely, and instead of having to invent a new scheme for every
new syscall, make that the default pattern by providing a helper
int __copy_abi_struct(void *kernel, size_t ksize, const void __user
*user, size_t usize)
{
size_t copy = min(ksize, usize);
if (copy_from_user(kernel, user, copy))
return -EFAULT;
if (usize > ksize) {
/* maybe a separate "return user_is_zero(user + ksize, usize -
ksize);" helper */
char c;
user += ksize;
usize -= ksize;
while (usize--) {
if (get_user(c, user++))
return -EFAULT;
if (c)
return -EINVAL;
}
} else if (ksize > usize) {
memset(kernel + usize, 0, ksize - usize);
}
return 0;
}
#define copy_abi_struct(kernel, user, usize) \
__copy_abi_struct(kernel, sizeof(*kernel), user, usize)
> Both (1) and (2) have the problem that the "struct version" is inside
> the struct so we'd need to copy_from_user() twice. This isn't the end of
> the world, it just feels a bit less clean than is ideal. (3) fixes that
> problem, at the cost of making the API slightly more cumbersome to use
> directly (though again glibc could wrap that away).
I don't see how 3 is cumbersome to use directly. Userspace code does
struct openat_of_the_day args = {.field1 = x, .field3 = y} and passes
&args, sizeof(args). What does glibc need to do beyond its usual munging
of the userspace ABI registers to the syscall ABI registers?
Rasmus
^ permalink raw reply
* Re: [PATCH] powerpc/mm: tell if a bad page fault on data is read or write.
From: Christophe Leroy @ 2019-08-29 12:59 UTC (permalink / raw)
To: Michael Ellerman, Benjamin Herrenschmidt, Paul Mackerras
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <87o908tbgx.fsf@mpe.ellerman.id.au>
Le 29/08/2019 à 14:14, Michael Ellerman a écrit :
> Christophe Leroy <christophe.leroy@c-s.fr> writes:
>> DSISR has a bit to tell if the fault is due to a read or a write.
>
> Except some CPUs don't have a DSISR?
>
> Which is why we have page_fault_is_write() that's used in
> __do_page_fault().
>
> Or is that old cruft?
>
> I see eg. in head_40x.S we pass r5=0 for error code, and we don't set
> regs->dsisr anywhere AFAICS. So it might just contain some junk.
But then we have a problem with show_regs() as well, havent't we ?
if (trap == 0x200 || trap == 0x300 || trap == 0x600)
#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr);
#else
pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
#endif
I need to look closer.
Christophe
>
> cheers
>
>> diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
>> index 8432c281de92..b5047f9b5dec 100644
>> --- a/arch/powerpc/mm/fault.c
>> +++ b/arch/powerpc/mm/fault.c
>> @@ -645,6 +645,7 @@ NOKPROBE_SYMBOL(do_page_fault);
>> void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
>> {
>> const struct exception_table_entry *entry;
>> + int is_write = page_fault_is_write(regs->dsisr);
>>
>> /* Are we prepared to handle this fault? */
>> if ((entry = search_exception_tables(regs->nip)) != NULL) {
>> @@ -658,9 +659,10 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
>> case 0x300:
>> case 0x380:
>> case 0xe00:
>> - pr_alert("BUG: %s at 0x%08lx\n",
>> + pr_alert("BUG: %s on %s at 0x%08lx\n",
>> regs->dar < PAGE_SIZE ? "Kernel NULL pointer dereference" :
>> - "Unable to handle kernel data access", regs->dar);
>> + "Unable to handle kernel data access",
>> + is_write ? "write" : "read", regs->dar);
>
>> break;
>> case 0x400:
>> case 0x480:
>> --
>> 2.13.3
^ permalink raw reply
* Re: [PATCH v4 1/4] powerpc: make llseek 32bit-only.
From: Arnd Bergmann @ 2019-08-29 12:57 UTC (permalink / raw)
To: Michal Suchánek
Cc: Michael Neuling, Andrew Donnellan, Nicolai Stange,
David Hildenbrand, Greg Kroah-Hartman, Heiko Carstens,
Linux Kernel Mailing List, Nicholas Piggin, David Howells,
Hari Bathini, Paul Mackerras, Joel Stanley, Christian Brauner,
Firoz Khan, Breno Leitao, Geert Uytterhoeven, Thomas Gleixner,
linuxppc-dev, Allison Randal, Eric W. Biederman
In-Reply-To: <20190829143716.6e41b10e@naga>
On Thu, Aug 29, 2019 at 2:37 PM Michal Suchánek <msuchanek@suse.de> wrote:
> On Thu, 29 Aug 2019 14:19:46 +0200 Arnd Bergmann <arnd@arndb.de> wrote:
> > On Thu, Aug 29, 2019 at 12:23 PM Michal Suchanek <msuchanek@suse.de> wrote:
> > In particular, I don't see why you single out llseek here, but leave other
> > syscalls that are not needed on 64-bit machines such as pread64().
>
> Because llseek is not built in fs/ when building 64bit only causing a
> link error.
>
> I initially posted patch to build it always but it was pointed out it
> is not needed, and the interface does not make sense on 64bit, and
> that platforms that don't have it on 64bit now don't want that useless
> code.
Ok, please put that into the changeset description then.
I looked at uses of __NR__llseek in debian code search and
found this one:
https://codesearch.debian.net/show?file=umview_0.8.2-1.2%2Fxmview%2Fum_mmap.c&line=328
It looks like this application will try to use llseek instead of lseek
when built against kernel headers that define __NR_llseek.
Changing the powerpc kernel not to provide that to user
space may break it unless the program gets recompiled against
the latest headers.
Arnd
^ permalink raw reply
* Re: [PATCH v5 1/2] powerpc/xmon: Allow listing and clearing breakpoints in read-only mode
From: Christopher M Riedl @ 2019-08-29 12:38 UTC (permalink / raw)
To: Daniel Axtens, linuxppc-dev, kernel-hardening; +Cc: ajd
In-Reply-To: <87ef14v5j0.fsf@dja-thinkpad.axtens.net>
> On August 29, 2019 at 1:40 AM Daniel Axtens <dja@axtens.net> wrote:
>
>
> Hi Chris,
>
> > Read-only mode should not prevent listing and clearing any active
> > breakpoints.
>
> I tested this and it works for me:
>
> Tested-by: Daniel Axtens <dja@axtens.net>
>
> > + if (xmon_is_ro || !scanhex(&a)) {
>
> It took me a while to figure out what this line does: as I understand
> it, the 'b' command can also be used to install a breakpoint (as well as
> bi/bd). If we are in ro mode or if the input after 'b' doesn't scan as a
> hex string, print the list of breakpoints instead. Anyway, I'm now
> happy with it, so:
>
I can add a comment to that effect in the next version. That entire section
of code could probably be cleaned up a bit - but that's for another patch.
Thanks for testing!
>
> Reviewed-by: Daniel Axtens <dja@axtens.net>
>
> Regards,
> Daniel
>
> > /* print all breakpoints */
> > printf(" type address\n");
> > if (dabr.enabled) {
> > --
> > 2.23.0
^ permalink raw reply
* Re: [PATCH v4 1/4] powerpc: make llseek 32bit-only.
From: Michal Suchánek @ 2019-08-29 12:37 UTC (permalink / raw)
To: Arnd Bergmann
Cc: Michael Neuling, Andrew Donnellan, Nicolai Stange,
David Hildenbrand, Greg Kroah-Hartman, Heiko Carstens,
Linux Kernel Mailing List, Nicholas Piggin, David Howells,
Hari Bathini, Paul Mackerras, Joel Stanley, Christian Brauner,
Firoz Khan, Breno Leitao, Geert Uytterhoeven, Thomas Gleixner,
linuxppc-dev, Allison Randal, Eric W. Biederman
In-Reply-To: <CAK8P3a1wR-jzFSzdPqgfCG4vyAi_xBPVGhc6Nn4KaXpk3cUiJw@mail.gmail.com>
On Thu, 29 Aug 2019 14:19:46 +0200
Arnd Bergmann <arnd@arndb.de> wrote:
> On Thu, Aug 29, 2019 at 12:23 PM Michal Suchanek <msuchanek@suse.de> wrote:
> >
> > Fixes: aff850393200 ("powerpc: add system call table generation support")
>
> This patch needs a proper explanation. The Fixes tag doesn't seem right
> here, since ppc64 has had llseek since the start in 2002 commit 3939e37587e7
> ("Add ppc64 support. This includes both pSeries (RS/6000) and iSeries
> (AS/400).").
>
> > diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
> > index 010b9f445586..53e427606f6c 100644
> > --- a/arch/powerpc/kernel/syscalls/syscall.tbl
> > +++ b/arch/powerpc/kernel/syscalls/syscall.tbl
> > @@ -188,7 +188,7 @@
> > 137 common afs_syscall sys_ni_syscall
> > 138 common setfsuid sys_setfsuid
> > 139 common setfsgid sys_setfsgid
> > -140 common _llseek sys_llseek
> > +140 32 _llseek sys_llseek
> > 141 common getdents sys_getdents compat_sys_getdents
> > 142 common _newselect sys_select compat_sys_select
> > 143 common flock sys_flock
>
> In particular, I don't see why you single out llseek here, but leave other
> syscalls that are not needed on 64-bit machines such as pread64().
Because llseek is not built in fs/ when building 64bit only causing a
link error.
I initially posted patch to build it always but it was pointed out it
is not needed, and the interface does not make sense on 64bit, and
that platforms that don't have it on 64bit now don't want that useless
code.
Thanks
Michal
^ permalink raw reply
* Re: [PATCH v5 2/2] powerpc/xmon: Restrict when kernel is locked down
From: Christopher M Riedl @ 2019-08-29 12:36 UTC (permalink / raw)
To: Daniel Axtens, linuxppc-dev, kernel-hardening; +Cc: ajd
In-Reply-To: <87d0gov2l5.fsf@dja-thinkpad.axtens.net>
> On August 29, 2019 at 2:43 AM Daniel Axtens <dja@axtens.net> wrote:
>
>
> Hi,
>
> > Xmon should be either fully or partially disabled depending on the
> > kernel lockdown state.
>
> I've been kicking the tyres of this, and it seems to work well:
>
> Tested-by: Daniel Axtens <dja@axtens.net>
>
Thank you for taking the time to test this!
>
> I have one small nit: if I enter confidentiality mode and then try to
> enter xmon, I get 32 messages about clearing the breakpoints each time I
> try to enter xmon:
>
Ugh, that's annoying. I tested this on a vm w/ 2 vcpus but should have
considered the case of more vcpus :(
>
> root@dja-guest:~# echo confidentiality > /sys/kernel/security/lockdown
> root@dja-guest:~# echo x >/proc/sysrq-trigger
> [ 489.585400] sysrq: Entering xmon
> xmon: Disabled due to kernel lockdown
> xmon: All breakpoints cleared
> xmon: All breakpoints cleared
> xmon: All breakpoints cleared
> xmon: All breakpoints cleared
> xmon: All breakpoints cleared
> ...
>
> Investigating, I see that this is because my vm has 32 vcpus, and I'm
> getting one per CPU.
>
> Looking at the call sites, there's only one other caller, so I think you
> might be better served with this:
>
> diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
> index 94a5fada3034..fcaf1d568162 100644
> --- a/arch/powerpc/xmon/xmon.c
> +++ b/arch/powerpc/xmon/xmon.c
> @@ -3833,10 +3833,6 @@ static void clear_all_bpt(void)
> iabr = NULL;
> dabr.enabled = 0;
> }
> -
> - get_output_lock();
> - printf("xmon: All breakpoints cleared\n");
> - release_output_lock();
> }
>
> #ifdef CONFIG_DEBUG_FS
> @@ -3846,8 +3842,13 @@ static int xmon_dbgfs_set(void *data, u64 val)
> xmon_init(xmon_on);
>
> /* make sure all breakpoints removed when disabling */
> - if (!xmon_on)
> + if (!xmon_on) {
> clear_all_bpt();
> + get_output_lock();
> + printf("xmon: All breakpoints cleared\n");
> + release_output_lock();
> + }
> +
> return 0;
> }
>
Good point, I will add this to the next version, thanks!
>
> Apart from that:
> Reviewed-by: Daniel Axtens <dja@axtens.net>
>
> Regards,
> Daniel
>
^ permalink raw reply
* [PATCH 1/3] scsi: cxlflash: Fix fallthrough warnings.
From: Michal Suchanek @ 2019-08-29 12:32 UTC (permalink / raw)
To: linuxppc-dev
Cc: Uma Krishnan, linux-scsi, Martin K. Petersen,
James E.J. Bottomley, linux-kernel, Manoj N. Kumar,
Paul Mackerras, Michal Suchanek, Matthew R. Ochs
In-Reply-To: <cover.1567081143.git.msuchanek@suse.de>
Add fallthrough comments where missing.
Signed-off-by: Michal Suchanek <msuchanek@suse.de>
---
drivers/scsi/cxlflash/main.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c
index b1f4724efde2..f402fa9a7bec 100644
--- a/drivers/scsi/cxlflash/main.c
+++ b/drivers/scsi/cxlflash/main.c
@@ -753,10 +753,13 @@ static void term_intr(struct cxlflash_cfg *cfg, enum undo_level level,
/* SISL_MSI_ASYNC_ERROR is setup only for the primary HWQ */
if (index == PRIMARY_HWQ)
cfg->ops->unmap_afu_irq(hwq->ctx_cookie, 3, hwq);
+ /* fall through */
case UNMAP_TWO:
cfg->ops->unmap_afu_irq(hwq->ctx_cookie, 2, hwq);
+ /* fall through */
case UNMAP_ONE:
cfg->ops->unmap_afu_irq(hwq->ctx_cookie, 1, hwq);
+ /* fall through */
case FREE_IRQ:
cfg->ops->free_afu_irqs(hwq->ctx_cookie);
/* fall through */
@@ -973,14 +976,18 @@ static void cxlflash_remove(struct pci_dev *pdev)
switch (cfg->init_state) {
case INIT_STATE_CDEV:
cxlflash_release_chrdev(cfg);
+ /* fall through */
case INIT_STATE_SCSI:
cxlflash_term_local_luns(cfg);
scsi_remove_host(cfg->host);
+ /* fall through */
case INIT_STATE_AFU:
term_afu(cfg);
+ /* fall through */
case INIT_STATE_PCI:
cfg->ops->destroy_afu(cfg->afu_cookie);
pci_disable_device(pdev);
+ /* fall through */
case INIT_STATE_NONE:
free_mem(cfg);
scsi_host_put(cfg->host);
@@ -3017,6 +3024,7 @@ static ssize_t num_hwqs_store(struct device *dev,
wait_event(cfg->reset_waitq, cfg->state != STATE_RESET);
if (cfg->state == STATE_NORMAL)
goto retry;
+ /* fall through */
default:
/* Ideally should not happen */
dev_err(dev, "%s: Device is not ready, state=%d\n",
--
2.12.3
^ permalink raw reply related
* [PATCH 2/3] scsi: ibmvfc: Fix fallthrough warnings.
From: Michal Suchanek @ 2019-08-29 12:32 UTC (permalink / raw)
To: linuxppc-dev
Cc: Tyrel Datwyler, linux-scsi, Martin K. Petersen,
James E.J. Bottomley, linux-kernel, Paul Mackerras,
Michal Suchanek
In-Reply-To: <cover.1567081143.git.msuchanek@suse.de>
Add fallthrough comments where they are missing.
Signed-off-by: Michal Suchanek <msuchanek@suse.de>
---
drivers/scsi/ibmvscsi/ibmvfc.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 8cdbac076a1b..2a06a5b4d3a5 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -1830,6 +1830,7 @@ static int ibmvfc_bsg_request(struct bsg_job *job)
port_id = (bsg_request->rqst_data.h_els.port_id[0] << 16) |
(bsg_request->rqst_data.h_els.port_id[1] << 8) |
bsg_request->rqst_data.h_els.port_id[2];
+ /* fallthrough */
case FC_BSG_RPT_ELS:
fc_flags = IBMVFC_FC_ELS;
break;
@@ -1838,6 +1839,7 @@ static int ibmvfc_bsg_request(struct bsg_job *job)
port_id = (bsg_request->rqst_data.h_ct.port_id[0] << 16) |
(bsg_request->rqst_data.h_ct.port_id[1] << 8) |
bsg_request->rqst_data.h_ct.port_id[2];
+ /* fallthrough */
case FC_BSG_RPT_CT:
fc_flags = IBMVFC_FC_CT_IU;
break;
@@ -4020,6 +4022,7 @@ static void ibmvfc_npiv_login_done(struct ibmvfc_event *evt)
return;
case IBMVFC_MAD_CRQ_ERROR:
ibmvfc_retry_host_init(vhost);
+ /* fallthrough */
case IBMVFC_MAD_DRIVER_FAILED:
ibmvfc_free_event(evt);
return;
--
2.12.3
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox