[RFC PATCH 12/18] powerpc/chrp: Move PHB discovery
Signed-off-by: Oliver O'Halloran
---
compile tested with chrp32_defconfig
---
arch/powerpc/platforms/chrp/pci.c | 8
arch/powerpc/platforms/chrp/setup.c | 12 +---
2 files changed, 9 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/platforms/chrp/pci.c
b/arch/powerpc/platforms/chrp/pci.c
index b2c2bf35b76c..8c421dc78b28 100644
--- a/arch/powerpc/platforms/chrp/pci.c
+++ b/arch/powerpc/platforms/chrp/pci.c
@@ -314,6 +314,14 @@ chrp_find_bridges(void)
}
}
of_node_put(root);
+
+ /*
+* "Temporary" fixes for PCI devices.
+* -- Geert
+*/
+ hydra_init(); /* Mac I/O */
+
+ pci_create_OF_bus_map();
}
/* SL82C105 IDE Control/Status Register */
diff --git a/arch/powerpc/platforms/chrp/setup.c
b/arch/powerpc/platforms/chrp/setup.c
index c45435aa5e36..3cfc382841e5 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -334,22 +334,11 @@ static void __init chrp_setup_arch(void)
/* On pegasos, enable the L2 cache if not already done by OF */
pegasos_set_l2cr();
- /* Lookup PCI host bridges */
- chrp_find_bridges();
-
- /*
-* Temporary fixes for PCI devices.
-* -- Geert
-*/
- hydra_init(); /* Mac I/O */
-
/*
* Fix the Super I/O configuration
*/
sio_init();
- pci_create_OF_bus_map();
-
/*
* Print the banner, then scroll down so boot progress
* can be printed. -- Cort
@@ -582,6 +571,7 @@ define_machine(chrp) {
.name = "CHRP",
.probe = chrp_probe,
.setup_arch = chrp_setup_arch,
+ .discover_phbs = chrp_find_bridges,
.init = chrp_init2,
.show_cpuinfo = chrp_show_cpuinfo,
.init_IRQ = chrp_init_IRQ,
--
2.26.2
[RFC PATCH 14/18] powerpc/embedded6xx/linkstation: Move PHB discovery
Signed-off-by: Oliver O'Halloran
---
compile tested with linkstation_defconfig
---
arch/powerpc/platforms/embedded6xx/linkstation.c | 10 +++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/platforms/embedded6xx/linkstation.c
b/arch/powerpc/platforms/embedded6xx/linkstation.c
index f514d5d28cd4..eb8342e7f84e 100644
--- a/arch/powerpc/platforms/embedded6xx/linkstation.c
+++ b/arch/powerpc/platforms/embedded6xx/linkstation.c
@@ -63,15 +63,18 @@ static int __init linkstation_add_bridge(struct device_node
*dev)
}
static void __init linkstation_setup_arch(void)
+{
+ printk(KERN_INFO "BUFFALO Network Attached Storage Series\n");
+ printk(KERN_INFO "(C) 2002-2005 BUFFALO INC.\n");
+}
+
+static void __init linkstation_setup_pci(void)
{
struct device_node *np;
/* Lookup PCI host bridges */
for_each_compatible_node(np, "pci", "mpc10x-pci")
linkstation_add_bridge(np);
-
- printk(KERN_INFO "BUFFALO Network Attached Storage Series\n");
- printk(KERN_INFO "(C) 2002-2005 BUFFALO INC.\n");
}
/*
@@ -153,6 +156,7 @@ define_machine(linkstation){
.name = "Buffalo Linkstation",
.probe = linkstation_probe,
.setup_arch = linkstation_setup_arch,
+ .discover_phbs = linkstation_setup_pci,
.init_IRQ = linkstation_init_IRQ,
.show_cpuinfo = linkstation_show_cpuinfo,
.get_irq= mpic_get_irq,
--
2.26.2
[RFC PATCH 13/18] powerpc/embedded6xx/holly: Move PHB discovery
Signed-off-by: Oliver O'Halloran
---
compile tested with holly_defconfig
---
arch/powerpc/platforms/embedded6xx/holly.c | 10 +++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/platforms/embedded6xx/holly.c
b/arch/powerpc/platforms/embedded6xx/holly.c
index d8f2e2c737bb..53065d564161 100644
--- a/arch/powerpc/platforms/embedded6xx/holly.c
+++ b/arch/powerpc/platforms/embedded6xx/holly.c
@@ -108,15 +108,13 @@ static void holly_remap_bridge(void)
tsi108_write_reg(TSI108_PCI_P2O_BAR2, 0x0);
}
-static void __init holly_setup_arch(void)
+static void __init holly_init_pci(void)
{
struct device_node *np;
if (ppc_md.progress)
ppc_md.progress("holly_setup_arch():set_bridge", 0);
- tsi108_csr_vir_base = get_vir_csrbase();
-
/* setup PCI host bridge */
holly_remap_bridge();
@@ -127,6 +125,11 @@ static void __init holly_setup_arch(void)
ppc_md.pci_exclude_device = holly_exclude_device;
if (ppc_md.progress)
ppc_md.progress("tsi108: resources set", 0x100);
+}
+
+static void __init holly_setup_arch(void)
+{
+ tsi108_csr_vir_base = get_vir_csrbase();
printk(KERN_INFO "PPC750GX/CL Platform\n");
}
@@ -259,6 +262,7 @@ define_machine(holly){
.name = "PPC750 GX/CL TSI",
.probe = holly_probe,
.setup_arch = holly_setup_arch,
+ .discover_phbs = holly_init_pci,
.init_IRQ = holly_init_IRQ,
.show_cpuinfo = holly_show_cpuinfo,
.get_irq= mpic_get_irq,
--
2.26.2
[RFC PATCH 15/18] powerpc/embedded6xx/mpc7448: Move PHB discovery
Signed-off-by: Oliver O'Halloran
---
compile tested with mpc7448_hpc2_defconfig
---
arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c | 14 +-
1 file changed, 9 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
index 15437abe1f6d..20b727584e40 100644
--- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
+++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
@@ -58,16 +58,14 @@ int mpc7448_hpc2_exclude_device(struct pci_controller *hose,
return PCIBIOS_SUCCESSFUL;
}
-static void __init mpc7448_hpc2_setup_arch(void)
+static void __init mpc7448_hpc2_setup_pci(void)
{
+#ifdef CONFIG_PCI
struct device_node *np;
if (ppc_md.progress)
- ppc_md.progress("mpc7448_hpc2_setup_arch():set_bridge", 0);
-
- tsi108_csr_vir_base = get_vir_csrbase();
+ ppc_md.progress("mpc7448_hpc2_setup_pci():set_bridge", 0);
/* setup PCI host bridge */
-#ifdef CONFIG_PCI
for_each_compatible_node(np, "pci", "tsi108-pci")
tsi108_setup_pci(np, MPC7448HPC2_PCI_CFG_PHYS, 0);
@@ -75,6 +73,11 @@ static void __init mpc7448_hpc2_setup_arch(void)
if (ppc_md.progress)
ppc_md.progress("tsi108: resources set", 0x100);
#endif
+}
+
+static void __init mpc7448_hpc2_setup_arch(void)
+{
+ tsi108_csr_vir_base = get_vir_csrbase();
printk(KERN_INFO "MPC7448HPC2 (TAIGA) Platform\n");
printk(KERN_INFO
@@ -180,6 +183,7 @@ define_machine(mpc7448_hpc2){
.name = "MPC7448 HPC2",
.probe = mpc7448_hpc2_probe,
.setup_arch = mpc7448_hpc2_setup_arch,
+ .discover_phbs = mpc7448_hpc2_setup_pci,
.init_IRQ = mpc7448_hpc2_init_IRQ,
.show_cpuinfo = mpc7448_hpc2_show_cpuinfo,
.get_irq= mpic_get_irq,
--
2.26.2
[RFC PATCH 16/18] powerpc/embedded6xx/mve5100: Move PHB discovery
Signed-off-by: Oliver O'Halloran
---
compile tested with mvme5100_defconfig
---
arch/powerpc/platforms/embedded6xx/mvme5100.c | 13 -
arch/powerpc/platforms/embedded6xx/storcenter.c | 8 ++--
2 files changed, 14 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/platforms/embedded6xx/mvme5100.c
b/arch/powerpc/platforms/embedded6xx/mvme5100.c
index 1cd488daa0bf..c06a0490d157 100644
--- a/arch/powerpc/platforms/embedded6xx/mvme5100.c
+++ b/arch/powerpc/platforms/embedded6xx/mvme5100.c
@@ -154,17 +154,19 @@ static const struct of_device_id mvme5100_of_bus_ids[]
__initconst = {
*/
static void __init mvme5100_setup_arch(void)
{
- struct device_node *np;
-
if (ppc_md.progress)
ppc_md.progress("mvme5100_setup_arch()", 0);
- for_each_compatible_node(np, "pci", "hawk-pci")
- mvme5100_add_bridge(np);
-
restart = ioremap(BOARD_MODRST_REG, 4);
}
+static void __init mvme5100_setup_pci(void)
+{
+ struct device_node *np;
+
+ for_each_compatible_node(np, "pci", "hawk-pci")
+ mvme5100_add_bridge(np);
+}
static void mvme5100_show_cpuinfo(struct seq_file *m)
{
@@ -205,6 +207,7 @@ define_machine(mvme5100) {
.name = "MVME5100",
.probe = mvme5100_probe,
.setup_arch = mvme5100_setup_arch,
+ .discover_phbs = mvme5100_setup_pci,
.init_IRQ = mvme5100_pic_init,
.show_cpuinfo = mvme5100_show_cpuinfo,
.get_irq= mpic_get_irq,
diff --git a/arch/powerpc/platforms/embedded6xx/storcenter.c
b/arch/powerpc/platforms/embedded6xx/storcenter.c
index ed1914dd34bb..e8c5de54b0e1 100644
--- a/arch/powerpc/platforms/embedded6xx/storcenter.c
+++ b/arch/powerpc/platforms/embedded6xx/storcenter.c
@@ -65,14 +65,17 @@ static int __init storcenter_add_bridge(struct device_node
*dev)
}
static void __init storcenter_setup_arch(void)
+{
+ printk(KERN_INFO "IOMEGA StorCenter\n");
+}
+
+static void __init storcenter_setup_pci(void)
{
struct device_node *np;
/* Lookup PCI host bridges */
for_each_compatible_node(np, "pci", "mpc10x-pci")
storcenter_add_bridge(np);
-
- printk(KERN_INFO "IOMEGA StorCenter\n");
}
/*
@@ -116,6 +119,7 @@ define_machine(storcenter){
.name = "IOMEGA StorCenter",
.probe = storcenter_probe,
.setup_arch = storcenter_setup_arch,
+ .discover_phbs = storcenter_setup_pci,
.init_IRQ = storcenter_init_IRQ,
.get_irq= mpic_get_irq,
.restart= storcenter_restart,
--
2.26.2
[RFC PATCH 17/18] powerpc/pasemi: Move PHB discovery
Signed-off-by: Oliver O'Halloran
---
compile tested with pasemi_defconfig
---
arch/powerpc/platforms/pasemi/setup.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/arch/powerpc/platforms/pasemi/setup.c
b/arch/powerpc/platforms/pasemi/setup.c
index b612474f8f8e..376797eb7894 100644
--- a/arch/powerpc/platforms/pasemi/setup.c
+++ b/arch/powerpc/platforms/pasemi/setup.c
@@ -144,8 +144,6 @@ static void __init pas_setup_arch(void)
/* Setup SMP callback */
smp_ops = &pas_smp_ops;
#endif
- /* Lookup PCI hosts */
- pas_pci_init();
/* Remap SDC register for doing reset */
/* XXXOJN This should maybe come out of the device tree */
@@ -446,6 +444,7 @@ define_machine(pasemi) {
.name = "PA Semi PWRficient",
.probe = pas_probe,
.setup_arch = pas_setup_arch,
+ .discover_phbs = pas_pci_init,
.init_IRQ = pas_init_IRQ,
.get_irq= mpic_get_irq,
.restart= pas_restart,
--
2.26.2
[RFC PATCH 18/18] powerpc/powermac: Move PHB discovery
Signed-off-by: Oliver O'Halloran
---
compile tested with pmac32_defconfig and g5_defconfig
---
arch/powerpc/platforms/powermac/setup.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/arch/powerpc/platforms/powermac/setup.c
b/arch/powerpc/platforms/powermac/setup.c
index f002b0fa69b8..0f8669139a21 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -298,9 +298,6 @@ static void __init pmac_setup_arch(void)
of_node_put(ic);
}
- /* Lookup PCI hosts */
- pmac_pci_init();
-
#ifdef CONFIG_PPC32
ohare_init();
l2cr_init();
@@ -600,6 +597,7 @@ define_machine(powermac) {
.name = "PowerMac",
.probe = pmac_probe,
.setup_arch = pmac_setup_arch,
+ .discover_phbs = pmac_pci_init,
.show_cpuinfo = pmac_show_cpuinfo,
.init_IRQ = pmac_pic_init,
.get_irq= NULL, /* changed later */
--
2.26.2
Re: [PATCH] rpadlpar_io:Add MODULE_DESCRIPTION entries to kernel modules
On Thu, Sep 24, 2020 at 3:15 PM Mamatha Inamdar
wrote:
>
> This patch adds a brief MODULE_DESCRIPTION to rpadlpar_io kernel modules
> (descriptions taken from Kconfig file)
>
> Signed-off-by: Mamatha Inamdar
> ---
> drivers/pci/hotplug/rpadlpar_core.c |1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/drivers/pci/hotplug/rpadlpar_core.c
> b/drivers/pci/hotplug/rpadlpar_core.c
> index f979b70..bac65ed 100644
> --- a/drivers/pci/hotplug/rpadlpar_core.c
> +++ b/drivers/pci/hotplug/rpadlpar_core.c
> @@ -478,3 +478,4 @@ static void __exit rpadlpar_io_exit(void)
> module_init(rpadlpar_io_init);
> module_exit(rpadlpar_io_exit);
> MODULE_LICENSE("GPL");
> +MODULE_DESCRIPTION("RPA Dynamic Logical Partitioning driver for I/O slots");
RPA as a spec was superseded by PAPR in the early 2000s. Can we rename
this already?
The only potential problem I can see is scripts doing: modprobe
rpadlpar_io or similar
However, we should be able to fix that with a module alias.
Oliver
Re: [patch RFC 00/15] mm/highmem: Provide a preemptible variant of kmap_atomic & friends
On Wed, Sep 23 2020 at 17:12, Steven Rostedt wrote: > On Wed, 23 Sep 2020 22:55:54 +0200 > Then scratch the idea of having anonymous local_lock() and just bring > local_lock in directly? Then have a kmap local lock, which would only > block those that need to do a kmap. That's still going to end up in lock ordering nightmares and you lose the ability to use kmap_local from arbitrary contexts which was again one of the goals of this exercise. Aside of that you're imposing reentrancy protections on something which does not need it in the first place. > Now as for migration disabled nesting, at least now we would have > groupings of this, and perhaps the theorists can handle that. I mean, > how is this much different that having a bunch of tasks blocked on a > mutex with the owner is pinned on a CPU? > > migrate_disable() is a BKL of pinning affinity. No. That's just wrong. preempt disable is a concurrency control, i.e. protecting against reentrancy on a given CPU. But it's a cpu global protection which means that it's not protecting a specific code path. Contrary to preempt disable, migrate disable is not protecting against reentrancy on a given CPU. It's a temporary restriction to the scheduler on placement. The fact that disabling preemption implicitely disables migration does not make them semantically equivalent. > If we only have local_lock() available (even on !RT), then it makes > the blocking in groups. At least this way you could grep for all the > different local_locks in the system and plug that into the algorithm > for WCS, just like one would with a bunch of mutexes. You cannot do that on RT at all where migrate disable is substituting preempt disable in spin and rw locks. The result would be the same as with a !RT kernel just with horribly bad performance. That means the stacking problem has to be solved anyway. So why on earth do you want to create yet another special duct tape case for kamp_local() which proliferates inconsistency instead of aiming for consistency accross all preemption models? Thanks, tglx
Re: [PATCH kernel] powerpc/dma: Fix dma_map_ops::get_required_mask
On 24/09/2020 00:10, Christoph Hellwig wrote: > On Tue, Sep 22, 2020 at 12:26:18PM +1000, Alexey Kardashevskiy wrote: >>> Well, the original intent of dma_get_required_mask is to return the >>> mask that the driver then uses to figure out what to set, so what aacraid >>> does fits that use case. >> >> What was the original intent exactly? The driver asks for the minimum or >> maximum DMA mask the platform supports? >> >> As for now, we (ppc64/powernv) can do: >> 1. bypass (==64bit) >> 2. a DMA window which used to be limited by 2GB but not anymore. >> >> I can understand if the driver asked for required mask in expectation to >> receive "less or equal than 32bit" and "more than 32 bit" and choose. >> And this probably was the intent as at the time when the bug was >> introduced, the window was always smaller than 4GB. >> >> But today the window is bigger than than (44 bits now, or a similar >> value, depends on max page order) so the returned mask is >32. Which >> still enables that DAC in aacraid but I suspect this is accidental. > > I think for powernv returning 64-bit always would make a lot of sense. > AFAIK all of powernv is PCIe and not legacy PCI, so returning anything > less isn't going to help to optimize anything. May be... The current behavior is not wrong (after the fix) but not optimal either. Even with legacy PCI it should just result in failing attempt to set 64bit mask which drivers should still handle, i.e. choose a shorter mask. Why not ditch the whole dma_get_required_mask() and just fail on setting a bigger mask? Are these failures not handled in some drivers? Or there are cases when a shorter mask is better? Thanks, >>> Of course that idea is pretty bogus for >>> PCIe devices. >> >> Why? From the PHB side, there are windows. From the device side, there >> are many crippled devices, like, no GPU I saw in last years supported >> more than 48bit. > > Yes, but dma_get_required_mask is misnamed - the mask is not required, > it is the optimal mask. Even if the window is smaller we handle it > some way, usually by using swiotlb, or by iommu tricks in your case. > >>> I suspect the right fix is to just not query dma_get_required_mask for >>> PCIe devices in aacraid (and other drivers that do something similar). >> >> May be, if you write nice and big comment next to >> dma_get_required_mask() explaining exactly what it does, then I will >> realize I am getting this all wrong and we will move to fixing the >> drivers :) > > Yes, it needs a comment or two, and probaby be renamed to > dma_get_optimal_dma_mask, and a cleanup of most users. I've added it > to my ever growing TODO list, but I would not be unhappy if someone > else gives it a spin. > -- Alexey
[Bug 195755] rcu_sched detected stalls on CPUs/tasks: (detected by 0, t=6302 jiffies, g=11405, c=11404, q=1880), ppc64, G5
https://bugzilla.kernel.org/show_bug.cgi?id=195755 Nigel Reed (ni...@nigelreed.net) changed: What|Removed |Added CC||ni...@nigelreed.net --- Comment #29 from Nigel Reed (ni...@nigelreed.net) --- I know this is old but I have been having some issues for a while, I was finally able to get something useful: [165716.089703] rcu: INFO: rcu_sched detected stalls on CPUs/tasks: [165716.095949] rcu:1-...!: (0 ticks this GP) idle=354/0/0x0 softirq=2154363/2154363 fqs=0 [165716.104512] rcu:3-...!: (0 ticks this GP) idle=29c/0/0x0 softirq=883832/883832 fqs=0 [165716.112873] rcu:4-...!: (8 GPs behind) idle=ad8/0/0x0 softirq=2165586/2165586 fqs=0 [165716.121179] rcu:9-...!: (9 GPs behind) idle=acc/0/0x0 softirq=1340600/1340600 fqs=0 [165716.129467] rcu:11-...!: (2 GPs behind) idle=a18/0/0x0 softirq=4538536/4538537 fqs=0 [165716.137828] rcu:12-...!: (0 ticks this GP) idle=870/0/0x0 softirq=2158040/2158040 fqs=0 [165775.697763] rcu: rcu_sched kthread starved for 29898 jiffies! g36134941 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402 ->cpu=3 [165775.709013] rcu: RCU grace-period kthread stack dump: [165837.494623] watchdog: BUG: soft lockup - CPU#6 stuck for 23s! [(resolved):52315] [165865.494840] watchdog: BUG: soft lockup - CPU#6 stuck for 23s! [(resolved):52315] This happened just after freshclam ran but I don't know if it's related. This is with a Ryzen 7 1800X CPU. 5.4.0-48-generic #52-Ubuntu I thought I had sysrq configured but it seems not so I can't really provide any more information, other than this is driving me crazy. -- You are receiving this mail because: You are watching the assignee of the bug.
Re: [patch RFC 00/15] mm/highmem: Provide a preemptible variant of kmap_atomic & friends
On Wed, Sep 23, 2020 at 11:52:51AM -0400, Steven Rostedt wrote: > On Wed, 23 Sep 2020 10:40:32 +0200 > pet...@infradead.org wrote: > > > However, with migrate_disable() we can have each task preempted in a > > migrate_disable() region, worse we can stack them all on the _same_ CPU > > (super ridiculous odds, sure). And then we end up only able to run one > > task, with the rest of the CPUs picking their nose. > > What if we just made migrate_disable() a local_lock() available for !RT? Can't, neiter migrate_disable() nor migrate_enable() are allowed to block -- which is what makes their implementation so 'interesting'. > This should lower the SHC in theory, if you can't have stacked migrate > disables on the same CPU. See this email in that other thread (you're on Cc too IIRC): https://lkml.kernel.org/r/20200923170809.gy1362...@hirez.programming.kicks-ass.net I think that is we 'frob' the balance PULL, we'll end up with something similar. Whichever way around we turn this thing, the migrate_disable() runtime (we'll have to add a tracer for that), will be an interference term on the lower priority task, exactly like preempt_disable() would be. We'll just not exclude a higher priority task from running. AFAICT; the best case is a single migrate_disable() nesting, where a higher priority task preempts in a migrate_disable() section -- this is per design. When this preempted task becomes elegible to run under the ideal model (IOW it becomes one of the M highest priority tasks), it might still have to wait for the preemptee's migrate_disable() section to complete. Thereby suffering interference in the exact duration of migrate_disable() section. Per this argument, the change from preempt_disable() to migrate_disable() gets us: - higher priority tasks gain reduced wake-up latency - lower priority tasks are unchanged and are subject to the exact same interference term as if the higher priority task were using preempt_disable(). Since we've already established this term is unbounded, any task but the highest priority task is basically buggered. TL;DR, if we get balancing fixed and achieve (near) the optimal case above, migrate_disable() is an over-all win. But it's provably non-deterministic as long as the migrate_disable() sections are non-deterministic. The reason this all mostly works in practise is (I think) because: - People care most about the higher prio RT tasks and craft them to mostly avoid the migrate_disable() infected code. - The preemption scenario is most pronounced at higher utilization scenarios, and I suspect this is fairly rare to begin with. - And while many of these migrate_disable() regions are unbound in theory, in practise they're often fairly reasonable. So my current todo list is: - Change RT PULL - Change DL PULL - Add migrate_disable() tracer; exactly like preempt/irqoff, except measuring task-runtime instead of cpu-time. - Add a mode that measures actual interference. - Add a traceevent to detect preemption in migrate_disable(). And then I suppose I should twist Daniel's arm to update his model to include these scenarios and numbers.
Re: [PATCH v2] powerpc/pci: unmap legacy INTx interrupts when a PHB is removed
On 9/24/20 7:11 AM, Alexey Kardashevskiy wrote: > > > On 23/09/2020 17:06, Cédric Le Goater wrote: >> On 9/23/20 2:33 AM, Qian Cai wrote: >>> On Fri, 2020-08-07 at 12:18 +0200, Cédric Le Goater wrote: When a passthrough IO adapter is removed from a pseries machine using hash MMU and the XIVE interrupt mode, the POWER hypervisor expects the guest OS to clear all page table entries related to the adapter. If some are still present, the RTAS call which isolates the PCI slot returns error 9001 "valid outstanding translations" and the removal of the IO adapter fails. This is because when the PHBs are scanned, Linux maps automatically the INTx interrupts in the Linux interrupt number space but these are never removed. To solve this problem, we introduce a PPC platform specific pcibios_remove_bus() routine which clears all interrupt mappings when the bus is removed. This also clears the associated page table entries of the ESB pages when using XIVE. For this purpose, we record the logical interrupt numbers of the mapped interrupt under the PHB structure and let pcibios_remove_bus() do the clean up. Since some PCI adapters, like GPUs, use the "interrupt-map" property to describe interrupt mappings other than the legacy INTx interrupts, we can not restrict the size of the mapping array to PCI_NUM_INTX. The number of interrupt mappings is computed from the "interrupt-map" property and the mapping array is allocated accordingly. Cc: "Oliver O'Halloran" Cc: Alexey Kardashevskiy Signed-off-by: Cédric Le Goater >>> >>> Some syscall fuzzing will trigger this on POWER9 NV where the traces >>> pointed to >>> this patch. >>> >>> .config: https://gitlab.com/cailca/linux-mm/-/blob/master/powerpc.config >> >> OK. The patch is missing a NULL assignement after kfree() and that >> might be the issue. >> >> I did try PHB removal under PowerNV, so I would like to understand >> how we managed to remove twice the PCI bus and possibly reproduce. >> Any chance we could grab what the syscall fuzzer (syzkaller) did ? > > > > My guess would be it is doing this in parallel to provoke races. Concurrency removal and rescan should be controlled by : pci_stop_and_remove_bus_device_locked() pci_lock_rescan_remove() And, in the report, the stack traces are on the same CPU and PID. What I think is happening is that we did a couple of remove/rescan of the same PHB. The problem is that ->irq_map is not reallocated the second time because the PHB is re-scanned differently on the PowerNV platform. At the second remove, the ->irq_map being not NULL, we try to kfree it again and the allocator warns of a double free :/ This works fine on pseries/KVM because the PHB is never removed and on pseries/pHyp, pcibios_scan_phb() is called at PHB hotplug. But on PowerNV, pcibios_scan_phb() is only called at probe/boot time and not at hotplug time :/ I was a good thing to spot that before merge. But I need to revise that patch again. Thanks, C.
Re: [PATCH -next] powerpc/papr_scm: Fix warnings about undeclared variable
Thanks for the patch. This looks good to me. Wang Wensheng writes: > Build the kernel with 'make C=2': > arch/powerpc/platforms/pseries/papr_scm.c:825:1: warning: symbol > 'dev_attr_perf_stats' was not declared. Should it be static? > Signed-off-by: Wang Wensheng Reviewed-by: Vaibhav Jain -- Cheers ~ Vaibhav
Re: [PATCH v2 0/7] powerpc: Fix a few W=1 compile warnings
On Mon, 14 Sep 2020 23:10:00 +0200, Cédric Le Goater wrote: > Here is a small contribution improving compile with W=1. > > Thanks, > > C. > > Changes in v2: > > [...] Patches 1, 3, 4 and 7 applied to powerpc/next. [1/7] powerpc/sysfs: Remove unused 'err' variable in sysfs_create_dscr_default() https://git.kernel.org/powerpc/c/7b2aab5f22f0f7cc9e2f8672c9e65e2e88d30102 [3/7] powerpc/sstep: Remove empty if statement checking for invalid form https://git.kernel.org/powerpc/c/5ab187e01a5310e1f9cd2f6b192b2343b8bd14cb [4/7] powerpc/xive: Make debug routines static https://git.kernel.org/powerpc/c/2228f19cf90ef796c8d84f54f3a5db2dcc85c83f [7/7] powerpc/32: Declare stack_overflow_exception() prototype https://git.kernel.org/powerpc/c/ebbfeef0d8093a06ff39c60105b6650be3344cbe cheers
Re: [PATCH -next] powerpc/pseries: convert to use DEFINE_SEQ_ATTRIBUTE macro
On Wed, 16 Sep 2020 10:50:26 +0800, Liu Shixin wrote: > Use DEFINE_SEQ_ATTRIBUTE macro to simplify the code. Applied to powerpc/next. [1/1] powerpc/pseries: convert to use DEFINE_SEQ_ATTRIBUTE macro https://git.kernel.org/powerpc/c/96543e7352bded5d6d1a0e0022376ebdd6c1b8ab cheers
Re: [PATCH -next] drivers/macintosh/smu.c: use for_each_child_of_node() macro
On Wed, 16 Sep 2020 14:21:22 +0800, Qinglang Miao wrote: > Use for_each_child_of_node() macro instead of open coding it. Applied to powerpc/next. [1/1] drivers/macintosh/smu.c: use for_each_child_of_node() macro https://git.kernel.org/powerpc/c/9c826d31a73815464bd3df81e56d39b3d908ac73 cheers
Re: [PATCH -next] macintosh: smu_sensors: use for_each_child_of_node() macro
On Wed, 16 Sep 2020 14:21:25 +0800, Qinglang Miao wrote: > Use for_each_child_of_node() macro instead of open coding it. Applied to powerpc/next. [1/1] macintosh: smu_sensors: use for_each_child_of_node() macro https://git.kernel.org/powerpc/c/acff5e6c37fa4bf8d002c917a762c4f7615f6eaf cheers
Re: [PATCH -next] powerpc/powernv: fix wrong warning message in opalcore_config_init()
On Wed, 16 Sep 2020 14:21:29 +0800, Qinglang Miao wrote: > The logic of the warn output is incorrect. The two args should be > exchanged. Applied to powerpc/next. [1/1] powerpc/powernv: fix wrong warning message in opalcore_config_init() https://git.kernel.org/powerpc/c/8ec5cb12cd957e59b0470b75d26c901aaf645bc3 cheers
Re: [PATCH -next] serial: pmac_zilog: use for_each_child_of_node() macro
On Wed, 16 Sep 2020 14:21:38 +0800, Qinglang Miao wrote: > Use for_each_child_of_node() macro instead of open coding it. Applied to powerpc/next. [1/1] serial: pmac_zilog: use for_each_child_of_node() macro https://git.kernel.org/powerpc/c/1d42e07e9c249b7a032fba82b673ee8a8d6bd7b7 cheers
Re: [PATCH 1/2] powerpc/mm/64s: Fix slb_setup_new_exec() sparse warning
On Wed, 16 Sep 2020 21:56:36 +1000, Michael Ellerman wrote: > Sparse says: > symbol slb_setup_new_exec was not declared. Should it be static? > > No, it should have a declaration in a header, add one. Applied to powerpc/next. [1/2] powerpc/mm/64s: Fix slb_setup_new_exec() sparse warning https://git.kernel.org/powerpc/c/ef1edbba52883907caf02ab85e0d00a2e4648f05 [2/2] powerpc/perf: Add declarations to fix sparse warnings https://git.kernel.org/powerpc/c/d10ebe79dfae7dc59b6cf77ffa615f0b8dae21bf cheers
Re: [PATCH 1/3] powerpc: Move arch_cpu_idle_dead() into smp.c
On Wed, 19 Aug 2020 11:56:32 +1000, Michael Ellerman wrote: > arch_cpu_idle_dead() is in idle.c, which makes sense, but it's inside > a CONFIG_HOTPLUG_CPU block. > > It would be more at home in smp.c, inside the existing > CONFIG_HOTPLUG_CPU block. Note that CONFIG_HOTPLUG_CPU depends on > CONFIG_SMP so even though smp.c is not built for SMP=n builds, that's > fine. Applied to powerpc/next. [1/3] powerpc: Move arch_cpu_idle_dead() into smp.c https://git.kernel.org/powerpc/c/1ea21ba231f248034e8c794aa675869ca2b97d42 [2/3] powerpc/smp: Fold cpu_die() into its only caller https://git.kernel.org/powerpc/c/bf3c1464db883a953ad7bbed64924480b8b2b244 [3/3] powerpc/smp: Move ppc_md.cpu_die() to smp_ops.cpu_offline_self() https://git.kernel.org/powerpc/c/39f87561454dc33efb2a3d8354d066207acac8a6 cheers
Re: [PATCH] powerpc/prom_init: Check display props exist before enabling btext
On Fri, 21 Aug 2020 20:34:07 +1000, Michael Ellerman wrote: > It's possible to enable CONFIG_PPC_EARLY_DEBUG_BOOTX for a pseries > kernel (maybe it shouldn't be), which is then booted with qemu/slof. > > But if you do that the kernel crashes in draw_byte(), with a DAR > pointing somewhere near INT_MAX. > > Adding some debug to prom_init we see that we're not able to read the > "address" property from OF, so we're just using whatever junk value > was on the stack. > > [...] Applied to powerpc/next. [1/1] powerpc/prom_init: Check display props exist before enabling btext https://git.kernel.org/powerpc/c/6c71cfcc01685ef495ca7886471a76e73446424e cheers
Re: [PATCH v2 0/4] more mm switching vs TLB shootdown and lazy tlb fixes
On Mon, 14 Sep 2020 14:52:15 +1000, Nicholas Piggin wrote: > This is an attempt to fix a few different related issues around > switching mm, TLB flushing, and lazy tlb mm handling. > > This will require all architectures to eventually move to disabling > irqs over activate_mm, but it's possible we could add another arch > call after irqs are re-enabled for those few which can't do their > entire activation with irqs disabled. > > [...] Applied to powerpc/next. [1/4] mm: fix exec activate_mm vs TLB shootdown and lazy tlb switching race https://git.kernel.org/powerpc/c/d53c3dfb23c45f7d4f910c3a3ca84bf0a99c6143 [2/4] powerpc: select ARCH_WANT_IRQS_OFF_ACTIVATE_MM https://git.kernel.org/powerpc/c/66acd46080bd9e5ad2be4b0eb1d498d5145d058e [3/4] sparc64: remove mm_cpumask clearing to fix kthread_use_mm race https://git.kernel.org/powerpc/c/bafb056ce27940c9994ea905336aa8f27b4f7275 [4/4] powerpc/64s/radix: Fix mm_cpumask trimming race vs kthread_use_mm https://git.kernel.org/powerpc/c/a665eec0a22e11cdde708c1c256a465ebe768047 cheers
Re: [PATCH -next v2] powerpc/book3s64: fix link error with CONFIG_PPC_RADIX_MMU=n
On Thu, 17 Sep 2020 10:06:43 +0800, Yang Yingliang wrote: > Fix link error when CONFIG_PPC_RADIX_MMU is disabled: > powerpc64-linux-gnu-ld: arch/powerpc/platforms/pseries/lpar.o:(.toc+0x0): > undefined reference to `mmu_pid_bits' Applied to powerpc/next. [1/1] powerpc/book3s64: fix link error with CONFIG_PPC_RADIX_MMU=n https://git.kernel.org/powerpc/c/bda7673d64b6c2e92423363a756caa657464e096 cheers
Re: [PATCH] powerpc/process: Fix uninitialised variable error
On Thu, 17 Sep 2020 12:45:09 +1000, Michael Ellerman wrote:
> Clang, and GCC with -Wmaybe-uninitialized, can't see that val is
> unused in get_fpexec_mode():
>
> arch/powerpc/kernel/process.c:1940:7: error: variable 'val' is used
> uninitialized whenever 'if' condition is true
> if (cpu_has_feature(CPU_FTR_SPE)) {
> ^~~~
>
> [...]
Applied to powerpc/next.
[1/1] powerpc/process: Fix uninitialised variable error
https://git.kernel.org/powerpc/c/d208e13c6a2277d9fb71fad6a1394c70bdd7b634
cheers
Re: [patch RFC 00/15] mm/highmem: Provide a preemptible variant of kmap_atomic & friends
On Thu, 24 Sep 2020 08:57:52 +0200 Thomas Gleixner wrote: > > Now as for migration disabled nesting, at least now we would have > > groupings of this, and perhaps the theorists can handle that. I mean, > > how is this much different that having a bunch of tasks blocked on a > > mutex with the owner is pinned on a CPU? > > > > migrate_disable() is a BKL of pinning affinity. > > No. That's just wrong. preempt disable is a concurrency control, I think you totally misunderstood what I was saying. The above wasn't about comparing preempt_disable to migrate_disable. It was comparing migrate_disable to a chain of tasks blocked on mutexes where the top owner has preempt_disable set. You still have a bunch of tasks that can't move to other CPUs. > > If we only have local_lock() available (even on !RT), then it makes > > the blocking in groups. At least this way you could grep for all the > > different local_locks in the system and plug that into the algorithm > > for WCS, just like one would with a bunch of mutexes. > > You cannot do that on RT at all where migrate disable is substituting > preempt disable in spin and rw locks. The result would be the same as > with a !RT kernel just with horribly bad performance. Note, the spin and rwlocks already have a lock associated with them. Why would it be any different on RT? I wasn't suggesting adding another lock inside a spinlock. Why would I recommend THAT? I wasn't recommending blindly replacing migrate_disable() with local_lock(). I just meant expose local_lock() but not migrate_disable(). > > That means the stacking problem has to be solved anyway. > > So why on earth do you want to create yet another special duct tape case > for kamp_local() which proliferates inconsistency instead of aiming for > consistency accross all preemption models? The idea was to help with the scheduling issue. Anyway, instead of blocking. What about having a counter of number of migrate disabled tasks per cpu, and when taking a migrate_disable(), and there's already another task with migrate_disabled() set, and the current task has an affinity greater than 1, it tries to migrate to another CPU? This way migrate_disable() is less likely to have a bunch of tasks blocked on one CPU serialized by each task exiting the migrate_disable() section. Yes, there's more overhead, but it only happens if multiple tasks are in a migrate disable section on the same CPU. -- Steve
Re: [patch RFC 00/15] mm/highmem: Provide a preemptible variant of kmap_atomic & friends
On Thu, Sep 24, 2020 at 08:32:41AM -0400, Steven Rostedt wrote: > Anyway, instead of blocking. What about having a counter of number of > migrate disabled tasks per cpu, and when taking a migrate_disable(), and > there's > already another task with migrate_disabled() set, and the current task has > an affinity greater than 1, it tries to migrate to another CPU? That doesn't solve the problem. On wakeup we should already prefer an idle CPU over one running a (RT) task, but you can always wake more tasks than there's CPUs around and you'll _have_ to stack at some point. The trick is how to unstack them correctly. We need to detect when a migrate_disable() task _should_ start running again, and migrate away whoever is in the way at that point. It turns out, that getting selected for pull-balance is exactly that condition, and clearly a migrate_disable() task cannot be pulled, but we can use that signal to try and pull away the running task that's in the way.
Re: C vdso
Hi Michael Le 17/09/2020 à 14:33, Michael Ellerman a écrit : Hi Christophe, Christophe Leroy writes: Hi Michael, What is the status with the generic C vdso merge ? In some mail, you mentionned having difficulties getting it working on ppc64, any progress ? What's the problem ? Can I help ? Yeah sorry I was hoping to get time to work on it but haven't been able to. It's causing crashes on ppc64 ie. big endian. As you can see from the instruction dump we have jumped into the weeds somewhere. We also had the report from the kbuild robot about rela.opd being discarded, which I think is indicative of a bigger problem. ie. we don't process relocations for the VDSO, but opds require relocations (they contain an absolute pointer). I thought we could get away with that, because the VDSO entry points aren't proper functions (so they don't have opds), and I didn't think we'd be calling via function pointers in the VDSO code (which would require opds). But seems something is not working right. Sorry I haven't got back to you with those details. Things are a bit of a mess inside IBM at the moment (always?), and I've been trying to get everything done before I take a holiday next week. Can you tell what defconfig you are using ? I have been able to setup a full glibc PPC64 cross compilation chain and been able to test it under QEMU with success, using Nathan's vdsotest tool. I tested with both ppc64_defconfig and pseries_defconfig. The only problem I got is with getcpu, which segfaults but both before and after applying my series, so I guess this is unrelated. Not sure we can pay too much attention to the exact measurement as it is a ppc64 QEMU running on a x86 Linux which is running in a Virtual Box on a x86 windows Laptop, but at least it works: Without the series: clock-getres-monotonic:vdso: 389 nsec/call clock-gettime-monotonic:vdso: 781 nsec/call clock-getres-monotonic-coarse:vdso: 13715 nsec/call clock-gettime-monotonic-coarse:vdso: 312 nsec/call clock-getres-monotonic-raw:vdso: 13589 nsec/call clock-getres-tai:vdso: 13827 nsec/call clock-gettime-tai:vdso: 14846 nsec/call clock-getres-boottime:vdso: 13596 nsec/call clock-gettime-boottime:vdso: 14758 nsec/call clock-getres-realtime:vdso: 327 nsec/call clock-gettime-realtime:vdso: 717 nsec/call clock-getres-realtime-coarse:vdso: 14102 nsec/call clock-gettime-realtime-coarse:vdso: 299 nsec/call gettimeofday:vdso: 771 nsec/call With the series: clock-getres-monotonic:vdso: 350 nsec/call clock-gettime-monotonic:vdso: 726 nsec/call clock-getres-monotonic-coarse:vdso: 356 nsec/call clock-gettime-monotonic-coarse:vdso: 423 nsec/call clock-getres-monotonic-raw:vdso: 349 nsec/call clock-getres-tai:vdso: 419 nsec/call clock-gettime-tai:vdso: 724 nsec/call clock-getres-boottime:vdso: 352 nsec/call clock-gettime-boottime:vdso: 752 nsec/call clock-getres-realtime:vdso: 351 nsec/call clock-gettime-realtime:vdso: 733 nsec/call clock-getres-realtime-coarse:vdso: 356 nsec/call clock-gettime-realtime-coarse:vdso: 367 nsec/call gettimeofday:vdso: 796 nsec/call Thanks Christophe
Re: [patch RFC 00/15] mm/highmem: Provide a preemptible variant of kmap_atomic & friends
On Thu, 24 Sep 2020 14:42:41 +0200 Peter Zijlstra wrote: > On Thu, Sep 24, 2020 at 08:32:41AM -0400, Steven Rostedt wrote: > > Anyway, instead of blocking. What about having a counter of number of > > migrate disabled tasks per cpu, and when taking a migrate_disable(), and > > there's > > already another task with migrate_disabled() set, and the current task has > > an affinity greater than 1, it tries to migrate to another CPU? > > That doesn't solve the problem. On wakeup we should already prefer an > idle CPU over one running a (RT) task, but you can always wake more > tasks than there's CPUs around and you'll _have_ to stack at some point. Yes, understood. > > The trick is how to unstack them correctly. We need to detect when a > migrate_disable() task _should_ start running again, and migrate away > whoever is in the way at that point. > > It turns out, that getting selected for pull-balance is exactly that > condition, and clearly a migrate_disable() task cannot be pulled, but we > can use that signal to try and pull away the running task that's in the > way. Unless of course that running task is in a migrate disable section itself ;-) But I guess we will always have that SHC, and there will always be a scenario that you can't balance properly. But hopefully in practice we wont see that. How to handle kmap_local(), will migrate_disable() be used only for 32bit or, for consistency, will it also apply to 64bit? -- Steve
Re: [patch RFC 00/15] mm/highmem: Provide a preemptible variant of kmap_atomic & friends
On Thu, Sep 24, 2020 at 09:51:38AM -0400, Steven Rostedt wrote: > > It turns out, that getting selected for pull-balance is exactly that > > condition, and clearly a migrate_disable() task cannot be pulled, but we > > can use that signal to try and pull away the running task that's in the > > way. > > Unless of course that running task is in a migrate disable section > itself ;-) See my ramblings here: https://lkml.kernel.org/r/20200924082717.ga1362...@hirez.programming.kicks-ass.net My plan was to have the migrate_enable() of the running task trigger the migration in that case.
RE: [PATCH v6 04/11] PCI: designware-ep: Modify MSI and MSIX CAP way of finding
Hi Bjorn,
Thanks a lot for your comments!
> -Original Message-
> From: Bjorn Helgaas
> Sent: 2020年9月24日 4:16
> To: Xiaowei Bao
> Cc: Z.q. Hou ; M.h. Lian
> ; Mingkai Hu ;
> bhelg...@google.com; robh...@kernel.org; shawn...@kernel.org; Leo Li
> ; kis...@ti.com; lorenzo.pieral...@arm.com; Roy
> Zang ; amur...@thegoodpenguin.co.uk;
> jingooh...@gmail.com; gustavo.pimen...@synopsys.com;
> andrew.mur...@arm.com; linux-...@vger.kernel.org;
> devicet...@vger.kernel.org; linux-ker...@vger.kernel.org;
> linux-arm-ker...@lists.infradead.org; linuxppc-dev@lists.ozlabs.org
> Subject: Re: [PATCH v6 04/11] PCI: designware-ep: Modify MSI and MSIX
> CAP way of finding
>
> s/MSIX/MSI-X/ (subject and below)
>
> On Sat, Mar 14, 2020 at 11:30:31AM +0800, Xiaowei Bao wrote:
> > Each PF of EP device should have it's own MSI or MSIX capabitily
> > struct, so create a dw_pcie_ep_func struct and remove the msi_cap and
> > msix_cap to this struct from dw_pcie_ep, and manage the PFs with a
> > list.
>
> s/capabitily/capability/
>
> I know Lorenzo has already applied this, but for the future, or in case there
> are other reasons to update this patch.
>
> There are a bunch of unnecessary initializations below for future cleanup.
Yes, and there are many calling of dw_pcie_ep_func_select() to get func_offset,
I plan to submit a separate patch to clean up.
Thanks,
Zhiqiang
>
> > Signed-off-by: Xiaowei Bao
> > ---
> > v3:
> > - This is a new patch, to fix the issue of MSI and MSIX CAP way of
> >finding.
> > v4:
> > - Correct some word of commit message.
> > v5:
> > - No change.
> > v6:
> > - Fix up the compile error.
> >
> > drivers/pci/controller/dwc/pcie-designware-ep.c | 135
> +---
> > drivers/pci/controller/dwc/pcie-designware.h| 18 +++-
> > 2 files changed, 134 insertions(+), 19 deletions(-)
> >
> > diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c
> > b/drivers/pci/controller/dwc/pcie-designware-ep.c
> > index 933bb89..fb915f2 100644
> > --- a/drivers/pci/controller/dwc/pcie-designware-ep.c
> > +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
> > @@ -19,6 +19,19 @@ void dw_pcie_ep_linkup(struct dw_pcie_ep *ep)
> > pci_epc_linkup(epc);
> > }
> >
> > +struct dw_pcie_ep_func *
> > +dw_pcie_ep_get_func_from_ep(struct dw_pcie_ep *ep, u8 func_no) {
> > + struct dw_pcie_ep_func *ep_func;
> > +
> > + list_for_each_entry(ep_func, &ep->func_list, list) {
> > + if (ep_func->func_no == func_no)
> > + return ep_func;
> > + }
> > +
> > + return NULL;
> > +}
> > +
> > static unsigned int dw_pcie_ep_func_select(struct dw_pcie_ep *ep, u8
> > func_no) {
> > unsigned int func_offset = 0;
> > @@ -59,6 +72,47 @@ void dw_pcie_ep_reset_bar(struct dw_pcie *pci,
> enum pci_barno bar)
> > __dw_pcie_ep_reset_bar(pci, func_no, bar, 0); }
> >
> > +static u8 __dw_pcie_ep_find_next_cap(struct dw_pcie_ep *ep, u8
> func_no,
> > + u8 cap_ptr, u8 cap)
> > +{
> > + struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
> > + unsigned int func_offset = 0;
>
> Unnecessary initialization.
>
> > + u8 cap_id, next_cap_ptr;
> > + u16 reg;
> > +
> > + if (!cap_ptr)
> > + return 0;
> > +
> > + func_offset = dw_pcie_ep_func_select(ep, func_no);
> > +
> > + reg = dw_pcie_readw_dbi(pci, func_offset + cap_ptr);
> > + cap_id = (reg & 0x00ff);
> > +
> > + if (cap_id > PCI_CAP_ID_MAX)
> > + return 0;
> > +
> > + if (cap_id == cap)
> > + return cap_ptr;
> > +
> > + next_cap_ptr = (reg & 0xff00) >> 8;
> > + return __dw_pcie_ep_find_next_cap(ep, func_no, next_cap_ptr, cap); }
> > +
> > +static u8 dw_pcie_ep_find_capability(struct dw_pcie_ep *ep, u8
> > +func_no, u8 cap) {
> > + struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
> > + unsigned int func_offset = 0;
>
> Unnecessary initialization.
>
> > + u8 next_cap_ptr;
> > + u16 reg;
> > +
> > + func_offset = dw_pcie_ep_func_select(ep, func_no);
> > +
> > + reg = dw_pcie_readw_dbi(pci, func_offset + PCI_CAPABILITY_LIST);
> > + next_cap_ptr = (reg & 0x00ff);
> > +
> > + return __dw_pcie_ep_find_next_cap(ep, func_no, next_cap_ptr, cap); }
> > +
> > static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no,
> >struct pci_epf_header *hdr)
> > {
> > @@ -246,13 +300,18 @@ static int dw_pcie_ep_get_msi(struct pci_epc
> *epc, u8 func_no)
> > struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
> > u32 val, reg;
> > unsigned int func_offset = 0;
>
> Unnecessary initialization (not from your patch).
>
> > + struct dw_pcie_ep_func *ep_func;
> >
> > - if (!ep->msi_cap)
> > + ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
> > + if (!ep_func)
> > + return -EINVAL;
> > +
> > + if (!ep_func->msi_cap)
> > return -EINVAL;
> >
> > func_offset = dw_pcie_ep_func_select(ep, func_no);
> >
> > - reg = ep->msi_cap + func_offset + PCI_MSI_FLAGS;
> > + reg = ep_func->
Re: [PATCH V2] Doc: admin-guide: Add entry for kvm_cma_resv_ratio kernel param
On Mon, 21 Sep 2020 14:32:20 +0530 sathn...@linux.vnet.ibm.com wrote: > From: Satheesh Rajendran > > Add document entry for kvm_cma_resv_ratio kernel param which > is used to alter the KVM contiguous memory allocation percentage > for hash pagetable allocation used by hash mode PowerPC KVM guests. > > Cc: linux-ker...@vger.kernel.org > Cc: kvm-...@vger.kernel.org > Cc: linuxppc-dev@lists.ozlabs.org > Cc: Paul Mackerras > Cc: Michael Ellerman > Cc: Jonathan Corbet > Reviewed-by: Randy Dunlap > Signed-off-by: Satheesh Rajendran > --- > > V2: > Addressed review comments from Randy. > > V1: https://lkml.org/lkml/2020/9/16/72 Applied, thanks. jon
Re: [patch RFC 00/15] mm/highmem: Provide a preemptible variant of kmap_atomic & friends
On Thu, Sep 24 2020 at 08:32, Steven Rostedt wrote: > On Thu, 24 Sep 2020 08:57:52 +0200 > Thomas Gleixner wrote: > >> > Now as for migration disabled nesting, at least now we would have >> > groupings of this, and perhaps the theorists can handle that. I mean, >> > how is this much different that having a bunch of tasks blocked on a >> > mutex with the owner is pinned on a CPU? >> > >> > migrate_disable() is a BKL of pinning affinity. >> >> No. That's just wrong. preempt disable is a concurrency control, > > I think you totally misunderstood what I was saying. The above wasn't about > comparing preempt_disable to migrate_disable. It was comparing > migrate_disable to a chain of tasks blocked on mutexes where the top owner > has preempt_disable set. You still have a bunch of tasks that can't move to > other CPUs. What? The top owner does not prevent any task from moving. The tasks cannot move because they are blocked on the mutex, which means they are not runnable and non runnable tasks are not migrated at all. I really don't understand what you are trying to say. >> > If we only have local_lock() available (even on !RT), then it makes >> > the blocking in groups. At least this way you could grep for all the >> > different local_locks in the system and plug that into the algorithm >> > for WCS, just like one would with a bunch of mutexes. >> >> You cannot do that on RT at all where migrate disable is substituting >> preempt disable in spin and rw locks. The result would be the same as >> with a !RT kernel just with horribly bad performance. > > Note, the spin and rwlocks already have a lock associated with them. Why > would it be any different on RT? I wasn't suggesting adding another lock > inside a spinlock. Why would I recommend THAT? I wasn't recommending > blindly replacing migrate_disable() with local_lock(). I just meant expose > local_lock() but not migrate_disable(). We already exposed local_lock() to non RT and it's for places which do preempt_disable() or local_irq_disable() without having a lock associated. But both primitives are scope less and therefore behave like CPU local BKLs. What local_lock() provides in these cases is: - Making the protection scope clear by associating a named local lock which is coverred by lockdep. - It still maps to preempt_disable() or local_irq_disable() in !RT kernels - The scope and the named lock allows RT kernels to substitute with real (recursion aware) locking primitives which keep preemption and interupts enabled, but provide the fine grained protection for the scoped critical section. So how would you substitute migrate_disable() with a local_lock()? You can't. Again migrate_disable() is NOT a concurrency control and therefore it cannot be substituted by any concurrency control primitive. >> That means the stacking problem has to be solved anyway. >> >> So why on earth do you want to create yet another special duct tape case >> for kamp_local() which proliferates inconsistency instead of aiming for >> consistency accross all preemption models? > > The idea was to help with the scheduling issue. I don't see how mixing concepts and trying to duct tape a problem which is clearly in the realm of the scheduler, i.e. load balancing and placing algorithms, is helpful. Thanks, tglx
Re: [patch RFC 00/15] mm/highmem: Provide a preemptible variant of kmap_atomic & friends
On Thu, 24 Sep 2020 19:55:10 +0200 Thomas Gleixner wrote: > On Thu, Sep 24 2020 at 08:32, Steven Rostedt wrote: > > On Thu, 24 Sep 2020 08:57:52 +0200 > > Thomas Gleixner wrote: > > > >> > Now as for migration disabled nesting, at least now we would have > >> > groupings of this, and perhaps the theorists can handle that. I mean, > >> > how is this much different that having a bunch of tasks blocked on a > >> > mutex with the owner is pinned on a CPU? > >> > > >> > migrate_disable() is a BKL of pinning affinity. > >> > >> No. That's just wrong. preempt disable is a concurrency control, > > > > I think you totally misunderstood what I was saying. The above wasn't about > > comparing preempt_disable to migrate_disable. It was comparing > > migrate_disable to a chain of tasks blocked on mutexes where the top owner > > has preempt_disable set. You still have a bunch of tasks that can't move to > > other CPUs. > > What? The top owner does not prevent any task from moving. The tasks > cannot move because they are blocked on the mutex, which means they are > not runnable and non runnable tasks are not migrated at all. And neither are migrated disabled tasks preempted by a high priority task. > > I really don't understand what you are trying to say. Don't worry about it. I was just making a high level comparison of how migrate disabled tasks blocked on a higher priority task is similar to that of tasks blocked on a mutex held by a pinned task that is preempted by a high priority task. But we can forget this analogy as it's not appropriate for the current conversation. > > >> > If we only have local_lock() available (even on !RT), then it makes > >> > the blocking in groups. At least this way you could grep for all the > >> > different local_locks in the system and plug that into the algorithm > >> > for WCS, just like one would with a bunch of mutexes. > >> > >> You cannot do that on RT at all where migrate disable is substituting > >> preempt disable in spin and rw locks. The result would be the same as > >> with a !RT kernel just with horribly bad performance. > > > > Note, the spin and rwlocks already have a lock associated with them. Why > > would it be any different on RT? I wasn't suggesting adding another lock > > inside a spinlock. Why would I recommend THAT? I wasn't recommending > > blindly replacing migrate_disable() with local_lock(). I just meant expose > > local_lock() but not migrate_disable(). > > We already exposed local_lock() to non RT and it's for places which do > preempt_disable() or local_irq_disable() without having a lock > associated. But both primitives are scope less and therefore behave like > CPU local BKLs. What local_lock() provides in these cases is: > > - Making the protection scope clear by associating a named local > lock which is coverred by lockdep. > > - It still maps to preempt_disable() or local_irq_disable() in !RT > kernels > > - The scope and the named lock allows RT kernels to substitute with > real (recursion aware) locking primitives which keep preemption and > interupts enabled, but provide the fine grained protection for the > scoped critical section. I'm very much aware of the above. > > So how would you substitute migrate_disable() with a local_lock()? You > can't. Again migrate_disable() is NOT a concurrency control and > therefore it cannot be substituted by any concurrency control primitive. When I was first writing my email, I was writing about a way to replace migrate_disable with a construct similar to local locks without actually mentioning local locks, but then rewrote it to state local locks, trying to simplify what I was writing. I shouldn't have done that, because it portrayed that I wanted to use local_lock() unmodified. I was actually thinking of a new construct that was similar but not exactly the same as local lock. But this will just make things more complex and we can forget about it. I'll wait to see what Peter produces. -- Steve
Re: [patch RFC 00/15] mm/highmem: Provide a preemptible variant of kmap_atomic & friends
On 9/24/20 10:27 AM, pet...@infradead.org wrote: > So my current todo list is: > > - Change RT PULL > - Change DL PULL > - Add migrate_disable() tracer; exactly like preempt/irqoff, except >measuring task-runtime instead of cpu-time. > - Add a mode that measures actual interference. > - Add a traceevent to detect preemption in migrate_disable(). > > > And then I suppose I should twist Daniel's arm to update his model to > include these scenarios and numbers. Challenge accepted :-) -- Daniel
[powerpc:next-test 179/194] arch/powerpc/platforms/pseries/eeh_pseries.c:420:6: error: variable 'ret' is used uninitialized whenever 'if' condition is true
tree: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git
next-test
head: 2e60265c1feb6848c77dbea22d38bbe262ec49db
commit: b90e1cfa05bddc2fa0e314a790df603479259637 [179/194] powerpc/pseries/eeh:
Rework device EEH PE determination
config: powerpc64-randconfig-r035-20200923 (attached as .config)
compiler: clang version 12.0.0 (https://github.com/llvm/llvm-project
d6ac649ccda289ecc2d2c0cb51892d57e8ec328c)
reproduce (this is a W=1 build):
wget
https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O
~/bin/make.cross
chmod +x ~/bin/make.cross
# install powerpc64 cross compiling tool for clang build
# apt-get install binutils-powerpc64-linux-gnu
git checkout b90e1cfa05bddc2fa0e314a790df603479259637
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross
ARCH=powerpc64
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot
All errors (new ones prefixed by >>):
arch/powerpc/platforms/pseries/eeh_pseries.c:46:6: error: no previous
prototype for function 'pseries_pcibios_bus_add_device'
[-Werror,-Wmissing-prototypes]
void pseries_pcibios_bus_add_device(struct pci_dev *pdev)
^
arch/powerpc/platforms/pseries/eeh_pseries.c:46:1: note: declare 'static' if
the function is not intended to be used outside of this translation unit
void pseries_pcibios_bus_add_device(struct pci_dev *pdev)
^
static
>> arch/powerpc/platforms/pseries/eeh_pseries.c:420:6: error: variable 'ret' is
>> used uninitialized whenever 'if' condition is true
>> [-Werror,-Wsometimes-uninitialized]
if (addr == 0) {
^
arch/powerpc/platforms/pseries/eeh_pseries.c:449:67: note: uninitialized use
occurs here
eeh_edev_dbg(edev, "EEH is unsupported on device (code = %d)\n",
ret);
^~~
arch/powerpc/include/asm/eeh.h:162:75: note: expanded from macro
'eeh_edev_dbg'
#define eeh_edev_dbg(edev, fmt, ...) EEH_EDEV_PRINT(debug, (edev), fmt,
##__VA_ARGS__)
^~~
arch/powerpc/include/asm/eeh.h:161:52: note: expanded from macro
'EEH_EDEV_PRINT'
((edev)->pe ? (edev)->pe_config_addr : 0x), ##__VA_ARGS__)
^~~
include/linux/printk.h:423:35: note: expanded from macro 'pr_debug'
printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
^~~
arch/powerpc/platforms/pseries/eeh_pseries.c:420:2: note: remove the 'if' if
its condition is always false
if (addr == 0) {
^~~~
arch/powerpc/platforms/pseries/eeh_pseries.c:362:9: note: initialize the
variable 'ret' to silence this warning
int ret;
^
= 0
2 errors generated.
#
https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git/commit/?id=b90e1cfa05bddc2fa0e314a790df603479259637
git remote add powerpc
https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git
git fetch --no-tags powerpc next-test
git checkout b90e1cfa05bddc2fa0e314a790df603479259637
vim +420 arch/powerpc/platforms/pseries/eeh_pseries.c
345
346 /**
347 * pseries_eeh_init_edev - initialise the eeh_dev and eeh_pe for a
pci_dn
348 *
349 * @pdn: PCI device node
350 *
351 * When we discover a new PCI device via the device-tree we create a
352 * corresponding pci_dn and we allocate, but don't initialise, an
eeh_dev.
353 * This function takes care of the initialisation and inserts the
eeh_dev
354 * into the correct eeh_pe. If no eeh_pe exists we'll allocate one.
355 */
356 void pseries_eeh_init_edev(struct pci_dn *pdn)
357 {
358 struct eeh_pe pe, *parent;
359 struct eeh_dev *edev;
360 int addr;
361 u32 pcie_flags;
362 int ret;
363
364 if (WARN_ON_ONCE(!eeh_has_flag(EEH_PROBE_MODE_DEVTREE)))
365 return;
366
367 /*
368 * Find the eeh_dev for this pdn. The storage for the eeh_dev
was
369 * allocated at the same time as the pci_dn.
370 *
371 * XXX: We should probably re-visit that.
372 */
373 edev = pdn_to_eeh_dev(pdn);
374 if (!edev)
375 return;
376
377 /*
378 * If ->pe is set then we've already probed this device. We hit
379 * this path when a pci_dev is removed and rescanned while
recovering
380 * a PE (i.e. for devices where the driver doesn't support error
381 * recovery).
382 */
383 if (edev->pe)
384
[powerpc:next] BUILD SUCCESS ebbfeef0d8093a06ff39c60105b6650be3344cbe
m68kstmark2_defconfig sh se7780_defconfig sh landisk_defconfig mips loongson1b_defconfig mips xway_defconfig sh lboxre2_defconfig arc nsimosci_hs_smp_defconfig riscvallmodconfig openrisc simple_smp_defconfig powerpc tqm8541_defconfig arm s3c6400_defconfig mipsomega2p_defconfig h8300 defconfig mips capcella_defconfig mips rb532_defconfig mipsnlm_xlp_defconfig powerpc mpc8315_rdb_defconfig powerpc tqm5200_defconfig arc haps_hs_defconfig arm simpad_defconfig mips ci20_defconfig powerpc mpc834x_itxgp_defconfig openriscdefconfig arm sunxi_defconfig arm imx_v4_v5_defconfig arm am200epdkit_defconfig powerpc rainier_defconfig powerpcicon_defconfig armmulti_v7_defconfig arcnsimosci_defconfig m68kmvme16x_defconfig sparc64 alldefconfig arm versatile_defconfig powerpc mpc83xx_defconfig arm moxart_defconfig powerpc linkstation_defconfig mips decstation_defconfig shedosk7760_defconfig powerpccell_defconfig s390 debug_defconfig c6x dsk6455_defconfig sh se7721_defconfig h8300 h8s-sim_defconfig sh se7724_defconfig mips decstation_64_defconfig m68k atari_defconfig sh sdk7786_defconfig arm palmz72_defconfig powerpc eiger_defconfig sh sdk7780_defconfig powerpcgamecube_defconfig h8300alldefconfig sh defconfig arm lpc18xx_defconfig mips ip27_defconfig sh sh7724_generic_defconfig sh polaris_defconfig nds32 allnoconfig shedosk7705_defconfig arm netwinder_defconfig arm spitz_defconfig powerpcmpc7448_hpc2_defconfig powerpc pmac32_defconfig powerpc mpc5200_defconfig s390defconfig mips ath25_defconfig mipsjmr3927_defconfig mips rbtx49xx_defconfig mips cu1830-neo_defconfig arc defconfig mips maltasmvp_defconfig ia64 allmodconfig m68k allmodconfig m68kdefconfig nios2 defconfig arc allyesconfig nds32 defconfig nios2allyesconfig alphaallyesconfig xtensa allyesconfig h8300allyesconfig sh allmodconfig parisc defconfig parisc allyesconfig mips allyesconfig powerpc allmodconfig powerpc allnoconfig i386 randconfig-a002-20200924 i386 randconfig-a006-20200924 i386 randconfig-a003-20200924 i386 randconfig-a004-20200924 i386 randconfig-a005-20200924 i386 randconfig-a001-20200924 i386 randconfig-a002-20200921 i386 randconfig-a006-20200921 i386 randconfig-a003-20200921 i386 randconfig-a004-20200921 i386 randconfig-a005-20200921 i386 randconfig-a001-20200921 i386 randconfig-a002-20200923 i386 randconfig-a006-20200923 i386 randconfig-a003-20200923 i386 randconfig-a004-20200923 i386 randconfig-a005-20200923 i386 randconfig-a001-20200923 i386 randconfig-a004-20200917 i386 randconfig-a006-20200917 i386 randconfig-a003-20200917 i386 randconfig
[powerpc:next-test] BUILD REGRESSION 2e60265c1feb6848c77dbea22d38bbe262ec49db
allmodconfig powerpc allyesconfig powerpc allmodconfig powerpc allnoconfig i386 randconfig-a002-20200924 i386 randconfig-a006-20200924 i386 randconfig-a003-20200924 i386 randconfig-a004-20200924 i386 randconfig-a005-20200924 i386 randconfig-a001-20200924 i386 randconfig-a002-20200923 i386 randconfig-a006-20200923 i386 randconfig-a003-20200923 i386 randconfig-a004-20200923 i386 randconfig-a005-20200923 i386 randconfig-a001-20200923 x86_64 randconfig-a011-20200923 x86_64 randconfig-a013-20200923 x86_64 randconfig-a014-20200923 x86_64 randconfig-a015-20200923 x86_64 randconfig-a012-20200923 x86_64 randconfig-a016-20200923 i386 randconfig-a012-20200923 i386 randconfig-a014-20200923 i386 randconfig-a013-20200923 i386 randconfig-a011-20200923 i386 randconfig-a016-20200923 i386 randconfig-a015-20200923 riscvnommu_k210_defconfig riscvallyesconfig riscvnommu_virt_defconfig riscv allnoconfig riscv defconfig riscv rv32_defconfig riscvallmodconfig x86_64 rhel x86_64 allyesconfig x86_64rhel-7.6-kselftests x86_64 defconfig x86_64 rhel-8.3 x86_64 kexec clang tested configs: x86_64 randconfig-a005-20200923 x86_64 randconfig-a003-20200923 x86_64 randconfig-a004-20200923 x86_64 randconfig-a002-20200923 x86_64 randconfig-a006-20200923 x86_64 randconfig-a001-20200923 --- 0-DAY CI Kernel Test Service, Intel Corporation https://lists.01.org/hyperkitty/list/kbuild-...@lists.01.org
[powerpc:merge] BUILD SUCCESS 548ccca2a8864b7498ad8cc420fa01aecd4d4114
tree/branch: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git merge branch HEAD: 548ccca2a8864b7498ad8cc420fa01aecd4d4114 Automatic merge of 'master' into merge (2020-09-24 22:12) elapsed time: 807m configs tested: 137 configs skipped: 3 The following configs have been built successfully. More configs may be tested in the coming days. gcc tested configs: arm defconfig arm64allyesconfig arm64 defconfig arm allyesconfig arm allmodconfig sh r7780mp_defconfig mips pnx8335_stb225_defconfig sh r7785rp_defconfig armxcep_defconfig arm badge4_defconfig mips maltasmvp_eva_defconfig m68k apollo_defconfig mips bmips_stb_defconfig arc nsimosci_hs_defconfig shecovec24-romimage_defconfig arm u8500_defconfig powerpcwarp_defconfig arm assabet_defconfig sh rsk7201_defconfig arm davinci_all_defconfig m68k m5275evb_defconfig powerpc tqm8548_defconfig arm nhk8815_defconfig mips rt305x_defconfig arm mainstone_defconfig powerpc64 defconfig xtensa defconfig m68kstmark2_defconfig armqcom_defconfig powerpc ebony_defconfig xtensasmp_lx200_defconfig m68km5272c3_defconfig openrisc alldefconfig powerpc mpc8313_rdb_defconfig powerpc pseries_defconfig powerpc akebono_defconfig powerpcadder875_defconfig arc axs103_smp_defconfig m68k amiga_defconfig powerpcmpc7448_hpc2_defconfig powerpc tqm8540_defconfig m68k hp300_defconfig sparc sparc32_defconfig powerpc mpc837x_mds_defconfig powerpc pcm030_defconfig parisc alldefconfig mips malta_defconfig powerpc sbc8548_defconfig arc nps_defconfig h8300h8300h-sim_defconfig arm pxa_defconfig powerpc powernv_defconfig openriscdefconfig armrealview_defconfig powerpc eiger_defconfig armspear6xx_defconfig arcvdk_hs38_smp_defconfig powerpc pmac32_defconfig m68k multi_defconfig arm axm55xx_defconfig sh polaris_defconfig sh lboxre2_defconfig ia64 allmodconfig ia64defconfig ia64 allyesconfig m68k allmodconfig m68kdefconfig m68k allyesconfig nios2 defconfig arc allyesconfig nds32 allnoconfig c6x allyesconfig nds32 defconfig nios2allyesconfig cskydefconfig alpha defconfig alphaallyesconfig xtensa allyesconfig h8300allyesconfig arc defconfig sh allmodconfig parisc defconfig s390 allyesconfig parisc allyesconfig s390defconfig i386 allyesconfig sparcallyesconfig sparc defconfig i386defconfig mips allyesconfig mips allmodconfig powerpc allyesconfig powerpc allmodconfig powerpc allnoconfig i386 randconfig-a002-20200924 i386 randconfig-a006-20200924 i386 randconfig-a003-20200924 i386 randconfig-a004-20200924 i386 randconfig-a005-20200924 i386 randconfig-a001-202
[PATCH 4/9] iov_iter: transparently handle compat iovecs in import_iovec
Use in compat_syscall to import either native or the compat iovecs, and
remove the now superflous compat_import_iovec.
This removes the need for special compat logic in most callers, and
the remaining ones can still be simplified by using __import_iovec
with a bool compat parameter.
Signed-off-by: Christoph Hellwig
---
block/scsi_ioctl.c | 12 ++--
drivers/scsi/sg.c | 9 +
fs/aio.c | 8 ++--
fs/io_uring.c | 20
fs/read_write.c| 6 --
fs/splice.c| 2 +-
include/linux/uio.h| 8
lib/iov_iter.c | 14 ++
mm/process_vm_access.c | 3 ++-
net/compat.c | 4 ++--
security/keys/compat.c | 5 ++---
11 files changed, 26 insertions(+), 65 deletions(-)
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index ef722f04f88a93..e08df86866ee5d 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -333,16 +333,8 @@ static int sg_io(struct request_queue *q, struct gendisk
*bd_disk,
struct iov_iter i;
struct iovec *iov = NULL;
-#ifdef CONFIG_COMPAT
- if (in_compat_syscall())
- ret = compat_import_iovec(rq_data_dir(rq),
- hdr->dxferp, hdr->iovec_count,
- 0, &iov, &i);
- else
-#endif
- ret = import_iovec(rq_data_dir(rq),
- hdr->dxferp, hdr->iovec_count,
- 0, &iov, &i);
+ ret = import_iovec(rq_data_dir(rq), hdr->dxferp,
+ hdr->iovec_count, 0, &iov, &i);
if (ret < 0)
goto out_free_cdb;
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 20472aaaf630a4..bfa8d77322d732 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1820,14 +1820,7 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
struct iovec *iov = NULL;
struct iov_iter i;
-#ifdef CONFIG_COMPAT
- if (in_compat_syscall())
- res = compat_import_iovec(rw, hp->dxferp, iov_count,
- 0, &iov, &i);
- else
-#endif
- res = import_iovec(rw, hp->dxferp, iov_count,
- 0, &iov, &i);
+ res = import_iovec(rw, hp->dxferp, iov_count, 0, &iov, &i);
if (res < 0)
return res;
diff --git a/fs/aio.c b/fs/aio.c
index d5ec303855669d..c45c20d875388c 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1489,12 +1489,8 @@ static ssize_t aio_setup_rw(int rw, const struct iocb
*iocb,
*iovec = NULL;
return ret;
}
-#ifdef CONFIG_COMPAT
- if (compat)
- return compat_import_iovec(rw, buf, len, UIO_FASTIOV, iovec,
- iter);
-#endif
- return import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter);
+
+ return __import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter, compat);
}
static inline void aio_rw_done(struct kiocb *req, ssize_t ret)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 8b426aa29668cb..8c27dc28da182a 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2852,13 +2852,8 @@ static ssize_t __io_import_iovec(int rw, struct io_kiocb
*req,
return ret;
}
-#ifdef CONFIG_COMPAT
- if (req->ctx->compat)
- return compat_import_iovec(rw, buf, sqe_len, UIO_FASTIOV,
- iovec, iter);
-#endif
-
- return import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter);
+ return __import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter,
+ req->ctx->compat);
}
static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
@@ -4200,8 +4195,9 @@ static int __io_recvmsg_copy_hdr(struct io_kiocb *req,
sr->len);
iomsg->iov = NULL;
} else {
- ret = import_iovec(READ, uiov, iov_len, UIO_FASTIOV,
- &iomsg->iov, &iomsg->msg.msg_iter);
+ ret = __import_iovec(READ, uiov, iov_len, UIO_FASTIOV,
+&iomsg->iov, &iomsg->msg.msg_iter,
+false);
if (ret > 0)
ret = 0;
}
@@ -4241,9 +4237,9 @@ static int __io_compat_recvmsg_copy_hdr(struct io_kiocb
*req,
sr->len = iomsg->iov[0].iov_len;
iomsg->iov = NULL;
} else {
- ret = compat_import_iovec(READ, uiov, len, UIO_FASTIOV,
- &iomsg->iov,
- &iomsg->msg.msg_iter);
+ ret = __import_iovec(READ, (struct iovec __user *)uiov, len,
+
[PATCH 8/9] mm: remove compat_process_vm_{readv,writev}
Now that import_iovec handles compat iovecs, the native syscalls can be used for the compat case as well. Signed-off-by: Christoph Hellwig --- arch/arm64/include/asm/unistd32.h | 4 +- arch/mips/kernel/syscalls/syscall_n32.tbl | 4 +- arch/mips/kernel/syscalls/syscall_o32.tbl | 4 +- arch/parisc/kernel/syscalls/syscall.tbl | 4 +- arch/powerpc/kernel/syscalls/syscall.tbl | 4 +- arch/s390/kernel/syscalls/syscall.tbl | 4 +- arch/sparc/kernel/syscalls/syscall.tbl| 4 +- arch/x86/entry/syscall_x32.c | 2 + arch/x86/entry/syscalls/syscall_32.tbl| 4 +- arch/x86/entry/syscalls/syscall_64.tbl| 4 +- include/linux/compat.h| 8 --- include/uapi/asm-generic/unistd.h | 6 +- mm/process_vm_access.c| 69 --- tools/include/uapi/asm-generic/unistd.h | 6 +- .../arch/powerpc/entry/syscalls/syscall.tbl | 4 +- .../perf/arch/s390/entry/syscalls/syscall.tbl | 4 +- .../arch/x86/entry/syscalls/syscall_64.tbl| 4 +- 17 files changed, 30 insertions(+), 109 deletions(-) diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 11dfae3a8563bd..0c280a05f699bf 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -763,9 +763,9 @@ __SYSCALL(__NR_sendmmsg, compat_sys_sendmmsg) #define __NR_setns 375 __SYSCALL(__NR_setns, sys_setns) #define __NR_process_vm_readv 376 -__SYSCALL(__NR_process_vm_readv, compat_sys_process_vm_readv) +__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv) #define __NR_process_vm_writev 377 -__SYSCALL(__NR_process_vm_writev, compat_sys_process_vm_writev) +__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev) #define __NR_kcmp 378 __SYSCALL(__NR_kcmp, sys_kcmp) #define __NR_finit_module 379 diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 5a39d4de0ac85b..0bc2e0fcf1ee56 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -317,8 +317,8 @@ 306n32 syncfs sys_syncfs 307n32 sendmmsgcompat_sys_sendmmsg 308n32 setns sys_setns -309n32 process_vm_readvcompat_sys_process_vm_readv -310n32 process_vm_writev compat_sys_process_vm_writev +309n32 process_vm_readvsys_process_vm_readv +310n32 process_vm_writev sys_process_vm_writev 311n32 kcmpsys_kcmp 312n32 finit_modulesys_finit_module 313n32 sched_setattr sys_sched_setattr diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 136efc6b8c5444..b408c13b934296 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -356,8 +356,8 @@ 342o32 syncfs sys_syncfs 343o32 sendmmsgsys_sendmmsg compat_sys_sendmmsg 344o32 setns sys_setns -345o32 process_vm_readvsys_process_vm_readv compat_sys_process_vm_readv -346o32 process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev +345o32 process_vm_readvsys_process_vm_readv +346o32 process_vm_writev sys_process_vm_writev 347o32 kcmpsys_kcmp 348o32 finit_modulesys_finit_module 349o32 sched_setattr sys_sched_setattr diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index a9e184192caedd..2015a5124b78ad 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -372,8 +372,8 @@ 327common syncfs sys_syncfs 328common setns sys_setns 329common sendmmsgsys_sendmmsg compat_sys_sendmmsg -330common process_vm_readvsys_process_vm_readv compat_sys_process_vm_readv -331common process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev +330common process_vm_readvsys_process_vm_readv +331common process_vm_writev sys_process_vm_writev 332common kcmpsys_kcmp 333common finit_modulesys_finit_module 334common sched_setattr sys_sched_setattr diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 0d4985919ca34d..66a472aa635d3f 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall
[PATCH 6/9] fs: remove the compat readv/writev syscalls
Now that import_iovec handles compat iovecs, the native readv and writev syscalls can be used for the compat case as well. Signed-off-by: Christoph Hellwig --- arch/arm64/include/asm/unistd32.h | 4 ++-- arch/mips/kernel/syscalls/syscall_n32.tbl | 4 ++-- arch/mips/kernel/syscalls/syscall_o32.tbl | 4 ++-- arch/parisc/kernel/syscalls/syscall.tbl| 4 ++-- arch/powerpc/kernel/syscalls/syscall.tbl | 4 ++-- arch/s390/kernel/syscalls/syscall.tbl | 4 ++-- arch/sparc/kernel/syscalls/syscall.tbl | 4 ++-- arch/x86/entry/syscall_x32.c | 2 ++ arch/x86/entry/syscalls/syscall_32.tbl | 4 ++-- arch/x86/entry/syscalls/syscall_64.tbl | 4 ++-- fs/read_write.c| 14 -- include/linux/compat.h | 4 include/uapi/asm-generic/unistd.h | 4 ++-- tools/include/uapi/asm-generic/unistd.h| 4 ++-- tools/perf/arch/powerpc/entry/syscalls/syscall.tbl | 4 ++-- tools/perf/arch/s390/entry/syscalls/syscall.tbl| 4 ++-- tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 4 ++-- 17 files changed, 30 insertions(+), 46 deletions(-) diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 734860ac7cf9d5..4a236493dca5b9 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -301,9 +301,9 @@ __SYSCALL(__NR_flock, sys_flock) #define __NR_msync 144 __SYSCALL(__NR_msync, sys_msync) #define __NR_readv 145 -__SYSCALL(__NR_readv, compat_sys_readv) +__SYSCALL(__NR_readv, sys_readv) #define __NR_writev 146 -__SYSCALL(__NR_writev, compat_sys_writev) +__SYSCALL(__NR_writev, sys_writev) #define __NR_getsid 147 __SYSCALL(__NR_getsid, sys_getsid) #define __NR_fdatasync 148 diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index f9df9edb67a407..c99a92646f8ee9 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -25,8 +25,8 @@ 15 n32 ioctl compat_sys_ioctl 16 n32 pread64 sys_pread64 17 n32 pwrite64sys_pwrite64 -18 n32 readv compat_sys_readv -19 n32 writev compat_sys_writev +18 n32 readv sys_readv +19 n32 writev sys_writev 20 n32 access sys_access 21 n32 pipesysm_pipe 22 n32 _newselect compat_sys_select diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 195b43cf27c848..075064d10661bf 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -156,8 +156,8 @@ 142o32 _newselect sys_select compat_sys_select 143o32 flock sys_flock 144o32 msync sys_msync -145o32 readv sys_readv compat_sys_readv -146o32 writev sys_writev compat_sys_writev +145o32 readv sys_readv +146o32 writev sys_writev 147o32 cacheflush sys_cacheflush 148o32 cachectlsys_cachectl 149o32 sysmips __sys_sysmips diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index def64d221cd4fb..192abde0001d9d 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -159,8 +159,8 @@ 142common _newselect sys_select compat_sys_select 143common flock sys_flock 144common msync sys_msync -145common readv sys_readv compat_sys_readv -146common writev sys_writev compat_sys_writev +145common readv sys_readv +146common writev sys_writev 147common getsid sys_getsid 148common fdatasync sys_fdatasync 149common _sysctl sys_ni_syscall diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index c2d737ff2e7bec..6f1e2ecf0edad9 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -193,8 +193,8 @@ 142common _newselect sys_select compat_sys_select 143common floc
[PATCH 5/9] fs: remove various compat readv/writev helpers
Now that import_iovec handles compat iovecs as well, all the duplicated
code in the compat readv/writev helpers is not needed. Remove them
and switch the compat syscall handlers to use the native helpers.
Signed-off-by: Christoph Hellwig
---
fs/read_write.c| 179 +++--
include/linux/compat.h | 20 ++---
2 files changed, 40 insertions(+), 159 deletions(-)
diff --git a/fs/read_write.c b/fs/read_write.c
index 0a68037580b455..eab427b7cc0a3f 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1068,226 +1068,107 @@ SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const
struct iovec __user *, vec,
return do_pwritev(fd, vec, vlen, pos, flags);
}
+/*
+ * Various compat syscalls. Note that they all pretend to take a native
+ * iovec - import_iovec will properly treat those as compat_iovecs based on
+ * in_compat_syscall().
+ */
#ifdef CONFIG_COMPAT
-static size_t compat_readv(struct file *file,
- const struct compat_iovec __user *vec,
- unsigned long vlen, loff_t *pos, rwf_t flags)
-{
- struct iovec iovstack[UIO_FASTIOV];
- struct iovec *iov = iovstack;
- struct iov_iter iter;
- ssize_t ret;
-
- ret = import_iovec(READ, (const struct iovec __user *)vec, vlen,
- UIO_FASTIOV, &iov, &iter);
- if (ret >= 0) {
- ret = do_iter_read(file, &iter, pos, flags);
- kfree(iov);
- }
- if (ret > 0)
- add_rchar(current, ret);
- inc_syscr(current);
- return ret;
-}
-
-static size_t do_compat_readv(compat_ulong_t fd,
-const struct compat_iovec __user *vec,
-compat_ulong_t vlen, rwf_t flags)
-{
- struct fd f = fdget_pos(fd);
- ssize_t ret;
- loff_t pos;
-
- if (!f.file)
- return -EBADF;
- pos = f.file->f_pos;
- ret = compat_readv(f.file, vec, vlen, &pos, flags);
- if (ret >= 0)
- f.file->f_pos = pos;
- fdput_pos(f);
- return ret;
-
-}
-
COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
- const struct compat_iovec __user *,vec,
+ const struct iovec __user *, vec,
compat_ulong_t, vlen)
{
- return do_compat_readv(fd, vec, vlen, 0);
-}
-
-static long do_compat_preadv64(unsigned long fd,
- const struct compat_iovec __user *vec,
- unsigned long vlen, loff_t pos, rwf_t flags)
-{
- struct fd f;
- ssize_t ret;
-
- if (pos < 0)
- return -EINVAL;
- f = fdget(fd);
- if (!f.file)
- return -EBADF;
- ret = -ESPIPE;
- if (f.file->f_mode & FMODE_PREAD)
- ret = compat_readv(f.file, vec, vlen, &pos, flags);
- fdput(f);
- return ret;
+ return do_readv(fd, vec, vlen, 0);
}
#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
- const struct compat_iovec __user *,vec,
+ const struct iovec __user *, vec,
unsigned long, vlen, loff_t, pos)
{
- return do_compat_preadv64(fd, vec, vlen, pos, 0);
+ return do_preadv(fd, vec, vlen, pos, 0);
}
#endif
COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
- const struct compat_iovec __user *,vec,
+ const struct iovec __user *, vec,
compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
{
loff_t pos = ((loff_t)pos_high << 32) | pos_low;
- return do_compat_preadv64(fd, vec, vlen, pos, 0);
+ return do_preadv(fd, vec, vlen, pos, 0);
}
#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2
COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd,
- const struct compat_iovec __user *,vec,
+ const struct iovec __user *, vec,
unsigned long, vlen, loff_t, pos, rwf_t, flags)
{
if (pos == -1)
- return do_compat_readv(fd, vec, vlen, flags);
-
- return do_compat_preadv64(fd, vec, vlen, pos, flags);
+ return do_readv(fd, vec, vlen, flags);
+ return do_preadv(fd, vec, vlen, pos, flags);
}
#endif
COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd,
- const struct compat_iovec __user *,vec,
+ const struct iovec __user *, vec,
compat_ulong_t, vlen, u32, pos_low, u32, pos_high,
rwf_t, flags)
{
loff_t pos = ((loff_t)pos_high << 32) | pos_low;
if (pos == -1)
- return do_compat_readv(fd, vec, vlen, flags);
-
- return do_compat_preadv64(fd, vec, vlen, pos, flags);
-}
-
-static size_t compat_writev(struct file *file,
- const struct compat_iovec __user *vec,
- unsigned long vlen, loff_t *pos, rwf_t flags)
-{
- struct iovec iovstack[UIO_FASTIOV];
-
[PATCH 7/9] fs: remove compat_sys_vmsplice
Now that import_iovec handles compat iovecs, the native vmsplice syscall can be used for the compat case as well. Signed-off-by: Christoph Hellwig --- arch/arm64/include/asm/unistd32.h | 2 +- arch/mips/kernel/syscalls/syscall_n32.tbl | 2 +- arch/mips/kernel/syscalls/syscall_o32.tbl | 2 +- arch/parisc/kernel/syscalls/syscall.tbl | 2 +- arch/powerpc/kernel/syscalls/syscall.tbl | 2 +- arch/s390/kernel/syscalls/syscall.tbl | 2 +- arch/sparc/kernel/syscalls/syscall.tbl| 2 +- arch/x86/entry/syscall_x32.c | 1 + arch/x86/entry/syscalls/syscall_32.tbl| 2 +- arch/x86/entry/syscalls/syscall_64.tbl| 2 +- fs/splice.c | 57 +-- include/linux/compat.h| 4 -- include/uapi/asm-generic/unistd.h | 2 +- tools/include/uapi/asm-generic/unistd.h | 2 +- .../arch/powerpc/entry/syscalls/syscall.tbl | 2 +- .../perf/arch/s390/entry/syscalls/syscall.tbl | 2 +- .../arch/x86/entry/syscalls/syscall_64.tbl| 2 +- 17 files changed, 28 insertions(+), 62 deletions(-) diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 4a236493dca5b9..11dfae3a8563bd 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -697,7 +697,7 @@ __SYSCALL(__NR_sync_file_range2, compat_sys_aarch32_sync_file_range2) #define __NR_tee 342 __SYSCALL(__NR_tee, sys_tee) #define __NR_vmsplice 343 -__SYSCALL(__NR_vmsplice, compat_sys_vmsplice) +__SYSCALL(__NR_vmsplice, sys_vmsplice) #define __NR_move_pages 344 __SYSCALL(__NR_move_pages, compat_sys_move_pages) #define __NR_getcpu 345 diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index c99a92646f8ee9..5a39d4de0ac85b 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -278,7 +278,7 @@ 267n32 splice sys_splice 268n32 sync_file_range sys_sync_file_range 269n32 tee sys_tee -270n32 vmsplicecompat_sys_vmsplice +270n32 vmsplicesys_vmsplice 271n32 move_pages compat_sys_move_pages 272n32 set_robust_list compat_sys_set_robust_list 273n32 get_robust_list compat_sys_get_robust_list diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 075064d10661bf..136efc6b8c5444 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -318,7 +318,7 @@ 304o32 splice sys_splice 305o32 sync_file_range sys_sync_file_range sys32_sync_file_range 306o32 tee sys_tee -307o32 vmsplicesys_vmsplice compat_sys_vmsplice +307o32 vmsplicesys_vmsplice 308o32 move_pages sys_move_pages compat_sys_move_pages 309o32 set_robust_list sys_set_robust_list compat_sys_set_robust_list 310o32 get_robust_list sys_get_robust_list compat_sys_get_robust_list diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index 192abde0001d9d..a9e184192caedd 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -330,7 +330,7 @@ 29232 sync_file_range parisc_sync_file_range 29264 sync_file_range sys_sync_file_range 293common tee sys_tee -294common vmsplicesys_vmsplice compat_sys_vmsplice +294common vmsplicesys_vmsplice 295common move_pages sys_move_pages compat_sys_move_pages 296common getcpu sys_getcpu 297common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 6f1e2ecf0edad9..0d4985919ca34d 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -369,7 +369,7 @@ 282common unshare sys_unshare 283common splice sys_splice 284common tee sys_tee -285common vmsplicesys_vmsplice compat_sys_vmsplice +285common vmsplicesys_vmsplice 286common openat sys_openat compat_sys_openat 287common m
let import_iovec deal with compat_iovecs as well v4
Hi Al, this series changes import_iovec to transparently deal with compat iovec structures, and then cleanups up a lot of code dupliation. Changes since v3: - fix up changed prototypes in compat.h as well Changes since v2: - revert the switch of the access process vm sysclls to iov_iter - refactor the import_iovec internals differently - switch aio to use __import_iovec Changes since v1: - improve a commit message - drop a pointless unlikely - drop the PF_FORCE_COMPAT flag - add a few more cleanups (including two from David Laight) Diffstat: arch/arm64/include/asm/unistd32.h | 10 arch/mips/kernel/syscalls/syscall_n32.tbl | 10 arch/mips/kernel/syscalls/syscall_o32.tbl | 10 arch/parisc/kernel/syscalls/syscall.tbl| 10 arch/powerpc/kernel/syscalls/syscall.tbl | 10 arch/s390/kernel/syscalls/syscall.tbl | 10 arch/sparc/kernel/syscalls/syscall.tbl | 10 arch/x86/entry/syscall_x32.c |5 arch/x86/entry/syscalls/syscall_32.tbl | 10 arch/x86/entry/syscalls/syscall_64.tbl | 10 block/scsi_ioctl.c | 12 drivers/scsi/sg.c |9 fs/aio.c | 38 -- fs/io_uring.c | 20 - fs/read_write.c| 362 + fs/splice.c| 57 --- include/linux/compat.h | 24 - include/linux/fs.h | 11 include/linux/uio.h| 10 include/uapi/asm-generic/unistd.h | 12 lib/iov_iter.c | 161 +++-- mm/process_vm_access.c | 85 net/compat.c |4 security/keys/compat.c | 37 -- security/keys/internal.h |5 security/keys/keyctl.c |2 tools/include/uapi/asm-generic/unistd.h| 12 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl | 10 tools/perf/arch/s390/entry/syscalls/syscall.tbl| 10 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 10 30 files changed, 280 insertions(+), 706 deletions(-)
[PATCH 9/9] security/keys: remove compat_keyctl_instantiate_key_iov
Now that import_iovec handles compat iovecs, the native version of
keyctl_instantiate_key_iov can be used for the compat case as well.
Signed-off-by: Christoph Hellwig
---
security/keys/compat.c | 36 ++--
security/keys/internal.h | 5 -
security/keys/keyctl.c | 2 +-
3 files changed, 3 insertions(+), 40 deletions(-)
diff --git a/security/keys/compat.c b/security/keys/compat.c
index 7ae531db031cf8..1545efdca56227 100644
--- a/security/keys/compat.c
+++ b/security/keys/compat.c
@@ -11,38 +11,6 @@
#include
#include "internal.h"
-/*
- * Instantiate a key with the specified compatibility multipart payload and
- * link the key into the destination keyring if one is given.
- *
- * The caller must have the appropriate instantiation permit set for this to
- * work (see keyctl_assume_authority). No other permissions are required.
- *
- * If successful, 0 will be returned.
- */
-static long compat_keyctl_instantiate_key_iov(
- key_serial_t id,
- const struct compat_iovec __user *_payload_iov,
- unsigned ioc,
- key_serial_t ringid)
-{
- struct iovec iovstack[UIO_FASTIOV], *iov = iovstack;
- struct iov_iter from;
- long ret;
-
- if (!_payload_iov)
- ioc = 0;
-
- ret = import_iovec(WRITE, (const struct iovec __user *)_payload_iov,
- ioc, ARRAY_SIZE(iovstack), &iov, &from);
- if (ret < 0)
- return ret;
-
- ret = keyctl_instantiate_key_common(id, &from, ringid);
- kfree(iov);
- return ret;
-}
-
/*
* The key control system call, 32-bit compatibility version for 64-bit archs
*/
@@ -113,8 +81,8 @@ COMPAT_SYSCALL_DEFINE5(keyctl, u32, option,
return keyctl_reject_key(arg2, arg3, arg4, arg5);
case KEYCTL_INSTANTIATE_IOV:
- return compat_keyctl_instantiate_key_iov(
- arg2, compat_ptr(arg3), arg4, arg5);
+ return keyctl_instantiate_key_iov(arg2, compat_ptr(arg3), arg4,
+ arg5);
case KEYCTL_INVALIDATE:
return keyctl_invalidate_key(arg2);
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 338a526cbfa516..9b9cf3b6fcbb4d 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -262,11 +262,6 @@ extern long keyctl_instantiate_key_iov(key_serial_t,
const struct iovec __user *,
unsigned, key_serial_t);
extern long keyctl_invalidate_key(key_serial_t);
-
-struct iov_iter;
-extern long keyctl_instantiate_key_common(key_serial_t,
- struct iov_iter *,
- key_serial_t);
extern long keyctl_restrict_keyring(key_serial_t id,
const char __user *_type,
const char __user *_restriction);
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 9febd37a168fd0..e26bbccda7ccee 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -1164,7 +1164,7 @@ static int keyctl_change_reqkey_auth(struct key *key)
*
* If successful, 0 will be returned.
*/
-long keyctl_instantiate_key_common(key_serial_t id,
+static long keyctl_instantiate_key_common(key_serial_t id,
struct iov_iter *from,
key_serial_t ringid)
{
--
2.28.0
[PATCH 3/9] iov_iter: refactor rw_copy_check_uvector and import_iovec
Split rw_copy_check_uvector into two new helpers with more sensible calling conventions: - iovec_from_user copies a iovec from userspace either into the provided stack buffer if it fits, or allocates a new buffer for it. Returns the actually used iovec. It also verifies that iov_len does fit a signed type, and handles compat iovecs if the compat flag is set. - __import_iovec consolidates the native and compat versions of import_iovec. It calls iovec_from_user, then validates each iovec actually points to user addresses, and ensures the total length doesn't overflow. This has two major implications: - the access_process_vm case loses the total lenght checking, which wasn't required anyway, given that each call receives two iovecs for the local and remote side of the operation, and it verifies the total length on the local side already. - instead of a single loop there now are two loops over the iovecs. Given that the iovecs are cache hot this doesn't make a major difference Signed-off-by: Christoph Hellwig --- include/linux/compat.h | 6 - include/linux/fs.h | 13 -- include/linux/uio.h| 12 +- lib/iov_iter.c | 300 - mm/process_vm_access.c | 34 +++-- 5 files changed, 138 insertions(+), 227 deletions(-) diff --git a/include/linux/compat.h b/include/linux/compat.h index 654c1ec36671a4..b930de791ff16b 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -451,12 +451,6 @@ extern long compat_arch_ptrace(struct task_struct *child, compat_long_t request, struct epoll_event;/* fortunately, this one is fixed-layout */ -extern ssize_t compat_rw_copy_check_uvector(int type, - const struct compat_iovec __user *uvector, - unsigned long nr_segs, - unsigned long fast_segs, struct iovec *fast_pointer, - struct iovec **ret_pointer); - extern void __user *compat_alloc_user_space(unsigned long len); int compat_restore_altstack(const compat_stack_t __user *uss); diff --git a/include/linux/fs.h b/include/linux/fs.h index 7519ae003a082c..e69b45b6cc7b5f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -178,14 +178,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File supports async buffered reads */ #define FMODE_BUF_RASYNC ((__force fmode_t)0x4000) -/* - * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector - * that indicates that they should check the contents of the iovec are - * valid, but not check the memory that the iovec elements - * points too. - */ -#define CHECK_IOVEC_ONLY -1 - /* * Attribute flags. These should be or-ed together to figure out what * has been changed! @@ -1887,11 +1879,6 @@ static inline int call_mmap(struct file *file, struct vm_area_struct *vma) return file->f_op->mmap(file, vma); } -ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, - unsigned long nr_segs, unsigned long fast_segs, - struct iovec *fast_pointer, - struct iovec **ret_pointer); - extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, diff --git a/include/linux/uio.h b/include/linux/uio.h index 3835a8a8e9eae0..92c11fe41c6228 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -266,9 +266,15 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, struct iov_iter *i); -ssize_t import_iovec(int type, const struct iovec __user * uvector, -unsigned nr_segs, unsigned fast_segs, -struct iovec **iov, struct iov_iter *i); +struct iovec *iovec_from_user(const struct iovec __user *uvector, + unsigned long nr_segs, unsigned long fast_segs, + struct iovec *fast_iov, bool compat); +ssize_t import_iovec(int type, const struct iovec __user *uvec, +unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, +struct iov_iter *i); +ssize_t __import_iovec(int type, const struct iovec __user *uvec, +unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, +struct iov_iter *i, bool compat); #ifdef CONFIG_COMPAT struct compat_iovec; diff --git a/lib/iov_iter.c b/lib/iov_iter.c index ccea9db3f72be8..d5d8afe31fca16 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -1650,107 +1651,133 @@ const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags) } EXPORT_SYMBOL(dup_iter); -/** - * rw_copy_check_uvector() - Copy an array of &struct iovec from userspa
[PATCH 2/9] iov_iter: move rw_copy_check_uvector() into lib/iov_iter.c
From: David Laight
This lets the compiler inline it into import_iovec() generating
much better code.
Signed-off-by: David Laight
Signed-off-by: Christoph Hellwig
---
fs/read_write.c | 179
lib/iov_iter.c | 176 +++
2 files changed, 176 insertions(+), 179 deletions(-)
diff --git a/fs/read_write.c b/fs/read_write.c
index 5db58b8c78d0dd..e5e891a88442ef 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -752,185 +752,6 @@ static ssize_t do_loop_readv_writev(struct file *filp,
struct iov_iter *iter,
return ret;
}
-/**
- * rw_copy_check_uvector() - Copy an array of &struct iovec from userspace
- * into the kernel and check that it is valid.
- *
- * @type: One of %CHECK_IOVEC_ONLY, %READ, or %WRITE.
- * @uvector: Pointer to the userspace array.
- * @nr_segs: Number of elements in userspace array.
- * @fast_segs: Number of elements in @fast_pointer.
- * @fast_pointer: Pointer to (usually small on-stack) kernel array.
- * @ret_pointer: (output parameter) Pointer to a variable that will point to
- * either @fast_pointer, a newly allocated kernel array, or NULL,
- * depending on which array was used.
- *
- * This function copies an array of &struct iovec of @nr_segs from
- * userspace into the kernel and checks that each element is valid (e.g.
- * it does not point to a kernel address or cause overflow by being too
- * large, etc.).
- *
- * As an optimization, the caller may provide a pointer to a small
- * on-stack array in @fast_pointer, typically %UIO_FASTIOV elements long
- * (the size of this array, or 0 if unused, should be given in @fast_segs).
- *
- * @ret_pointer will always point to the array that was used, so the
- * caller must take care not to call kfree() on it e.g. in case the
- * @fast_pointer array was used and it was allocated on the stack.
- *
- * Return: The total number of bytes covered by the iovec array on success
- * or a negative error code on error.
- */
-ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
- unsigned long nr_segs, unsigned long fast_segs,
- struct iovec *fast_pointer,
- struct iovec **ret_pointer)
-{
- unsigned long seg;
- ssize_t ret;
- struct iovec *iov = fast_pointer;
-
- /*
-* SuS says "The readv() function *may* fail if the iovcnt argument
-* was less than or equal to 0, or greater than {IOV_MAX}. Linux has
-* traditionally returned zero for zero segments, so...
-*/
- if (nr_segs == 0) {
- ret = 0;
- goto out;
- }
-
- /*
-* First get the "struct iovec" from user memory and
-* verify all the pointers
-*/
- if (nr_segs > UIO_MAXIOV) {
- ret = -EINVAL;
- goto out;
- }
- if (nr_segs > fast_segs) {
- iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL);
- if (iov == NULL) {
- ret = -ENOMEM;
- goto out;
- }
- }
- if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) {
- ret = -EFAULT;
- goto out;
- }
-
- /*
-* According to the Single Unix Specification we should return EINVAL
-* if an element length is < 0 when cast to ssize_t or if the
-* total length would overflow the ssize_t return value of the
-* system call.
-*
-* Linux caps all read/write calls to MAX_RW_COUNT, and avoids the
-* overflow case.
-*/
- ret = 0;
- for (seg = 0; seg < nr_segs; seg++) {
- void __user *buf = iov[seg].iov_base;
- ssize_t len = (ssize_t)iov[seg].iov_len;
-
- /* see if we we're about to use an invalid len or if
-* it's about to overflow ssize_t */
- if (len < 0) {
- ret = -EINVAL;
- goto out;
- }
- if (type >= 0
- && unlikely(!access_ok(buf, len))) {
- ret = -EFAULT;
- goto out;
- }
- if (len > MAX_RW_COUNT - ret) {
- len = MAX_RW_COUNT - ret;
- iov[seg].iov_len = len;
- }
- ret += len;
- }
-out:
- *ret_pointer = iov;
- return ret;
-}
-
-#ifdef CONFIG_COMPAT
-ssize_t compat_rw_copy_check_uvector(int type,
- const struct compat_iovec __user *uvector, unsigned long
nr_segs,
- unsigned long fast_segs, struct iovec *fast_pointer,
- struct iovec **ret_pointer)
-{
- compat_ssize_t tot_len;
- struct iovec *iov = *ret_pointer = fast_pointer;
- ssize_t ret = 0;
- int seg;
-
- /*
-
[PATCH 1/9] compat.h: fix a spelling error in
There is no compat_sys_readv64v2 syscall, only a compat_sys_preadv64v2 one. Signed-off-by: Christoph Hellwig --- include/linux/compat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/compat.h b/include/linux/compat.h index b354ce58966e2d..654c1ec36671a4 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -812,7 +812,7 @@ asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd, const struct compat_iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 -asmlinkage long compat_sys_readv64v2(unsigned long fd, +asmlinkage long compat_sys_preadv64v2(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags); #endif -- 2.28.0
Re: [PATCH kernel] powerpc/dma: Fix dma_map_ops::get_required_mask
On Thu, Sep 24, 2020 at 05:03:11PM +1000, Alexey Kardashevskiy wrote: > May be... The current behavior is not wrong (after the fix) but not > optimal either. Even with legacy PCI it should just result in failing > attempt to set 64bit mask which drivers should still handle, i.e. choose > a shorter mask. Err, no. > Why not ditch the whole dma_get_required_mask() and just fail on setting > a bigger mask? Are these failures not handled in some drivers? Or there > are cases when a shorter mask is better? Thanks, Because that is a complete pain. Think of it, the device/driver knows what it supports. For 98% of the modern devices that means all 64-bit bits, and for most others this means 32-bits, with a few wackos that support 48 bits or something like that. The 98% just take any address thrown at them, and the others just care that they never see an address larger than what they support. They could not care any less if the systems supports 31, 36, 41, 48, 52, 55, 61 or 63-bit addressing, an they most certainly should not implement stupid boilerplate code to guess what addressing mode the system implements. They just declare what they support. Then you have the 12 drivers for devices that can do optimizations if they never see large DMA addresses. They use the somewhat misnamed dma_get_required_mask API to query what the largest address they might see is and act based on that, while not putting any burden on all the sane devices/drivers.
Re: [PATCH v3] powerpc/pci: unmap legacy INTx interrupts when a PHB is removed
On 9/23/20 9:40 AM, Cédric Le Goater wrote: > When a passthrough IO adapter is removed from a pseries machine using > hash MMU and the XIVE interrupt mode, the POWER hypervisor expects the > guest OS to clear all page table entries related to the adapter. If > some are still present, the RTAS call which isolates the PCI slot > returns error 9001 "valid outstanding translations" and the removal of > the IO adapter fails. This is because when the PHBs are scanned, Linux > maps automatically the INTx interrupts in the Linux interrupt number > space but these are never removed. > > To solve this problem, we introduce a PPC platform specific > pcibios_remove_bus() routine which clears all interrupt mappings when > the bus is removed. This also clears the associated page table entries > of the ESB pages when using XIVE. > > For this purpose, we record the logical interrupt numbers of the > mapped interrupt under the PHB structure and let pcibios_remove_bus() > do the clean up. > > Since some PCI adapters, like GPUs, use the "interrupt-map" property > to describe interrupt mappings other than the legacy INTx interrupts, > we can not restrict the size of the mapping array to PCI_NUM_INTX. The > number of interrupt mappings is computed from the "interrupt-map" > property and the mapping array is allocated accordingly. > > Cc: "Oliver O'Halloran" > Cc: Alexey Kardashevskiy > Reviewed-by: Alexey Kardashevskiy > Signed-off-by: Cédric Le Goater > --- > > Changes in v3 : > > - NULLified 'irq_map' in pci_irq_map_dispose() Forge that. I am going to move the kfree() in the routine freeing the PCI controller structure. Thanks, C.
