LinuxPPC-Dev Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH 2/2] powerpc: Add POWER10 raw mode cputable entry
From: Madhavan Srinivasan @ 2020-08-17  0:56 UTC (permalink / raw)
  To: mpe; +Cc: Madhavan Srinivasan, linuxppc-dev
In-Reply-To: <20200817005618.3305028-1-maddy@linux.ibm.com>

Add a raw mode cputable entry for POWER10. Copies most of the fields
from commit a3ea40d5c736 ("powerpc: Add POWER10 architected mode")
except for oprofile_cpu_type, machine_check_early, pvr_mask and pvr_mask
fields. On bare metal systems we use DT CPU features, which doesn't need a
cputable entry. But in VMs we still rely on the raw cputable entry to
set the correct values for the PMU related fields.

Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
---
 arch/powerpc/kernel/cputable.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 4ca9cf556be92..2aa89c6b28967 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -539,6 +539,25 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.machine_check_early	= __machine_check_early_realmode_p9,
 		.platform		= "power9",
 	},
+	{	/* Power10 */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x00800000,
+		.cpu_name		= "POWER10 (raw)",
+		.cpu_features		= CPU_FTRS_POWER10,
+		.cpu_user_features	= COMMON_USER_POWER10,
+		.cpu_user_features2	= COMMON_USER2_POWER10,
+		.mmu_features		= MMU_FTRS_POWER10,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_IBM,
+		.oprofile_cpu_type	= "ppc64/power10",
+		.oprofile_type		= PPC_OPROFILE_INVALID,
+		.cpu_setup		= __setup_cpu_power10,
+		.cpu_restore		= __restore_cpu_power10,
+		.machine_check_early	= __machine_check_early_realmode_p10,
+		.platform		= "power10",
+	},
 	{	/* Cell Broadband Engine */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x00700000,
-- 
2.26.2


^ permalink raw reply related

* [PATCH 1/2] powerpc/kernel/cputable: cleanup the function declarations
From: Madhavan Srinivasan @ 2020-08-17  0:56 UTC (permalink / raw)
  To: mpe; +Cc: Madhavan Srinivasan, linuxppc-dev

__machine_check_early_realmode_p*() are currently declared
as extern in cputable.c and because of this when compiled
with "C=1" (which enables semantic checker) produces these
warnings.

  CHECK   arch/powerpc/kernel/mce_power.c
arch/powerpc/kernel/mce_power.c:709:6: warning: symbol '__machine_check_early_realmode_p7' was not declared. Should it be static?
arch/powerpc/kernel/mce_power.c:717:6: warning: symbol '__machine_check_early_realmode_p8' was not declared. Should it be static?
arch/powerpc/kernel/mce_power.c:722:6: warning: symbol '__machine_check_early_realmode_p9' was not declared. Should it be static?
arch/powerpc/kernel/mce_power.c:740:6: warning: symbol '__machine_check_early_realmode_p10' was not declared. Should it be static?

Patch here moves the declaration to asm/mce.h
and includes the same in cputable.c

Fixes: ae744f3432d3 ("powerpc/book3s: Flush SLB/TLBs if we get SLB/TLB machine check errors on power8")
Fixes: 7b9f71f974a1 ("powerpc/64s: POWER9 machine check handler")
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
---
 arch/powerpc/include/asm/cputable.h | 5 +++++
 arch/powerpc/include/asm/mce.h      | 7 +++++++
 arch/powerpc/kernel/cputable.c      | 3 ---
 arch/powerpc/kernel/dt_cpu_ftrs.c   | 4 ----
 4 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index fdddb822d564b..e005b45810232 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -9,6 +9,11 @@
 
 #ifndef __ASSEMBLY__
 
+/*
+ * Added to include __machine_check_early_realmode_* functions
+ */
+#include <asm/mce.h>
+
 /* This structure can grow, it's real size is used by head.S code
  * via the mkdefs mechanism.
  */
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index adf2cda67f9a4..89aa8248a57dd 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -210,6 +210,9 @@ struct mce_error_info {
 #define MCE_EVENT_RELEASE	true
 #define MCE_EVENT_DONTRELEASE	false
 
+struct pt_regs;
+struct notifier_block;
+
 extern void save_mce_event(struct pt_regs *regs, long handled,
 			   struct mce_error_info *mce_err, uint64_t nip,
 			   uint64_t addr, uint64_t phys_addr);
@@ -225,5 +228,9 @@ int mce_register_notifier(struct notifier_block *nb);
 int mce_unregister_notifier(struct notifier_block *nb);
 #ifdef CONFIG_PPC_BOOK3S_64
 void flush_and_reload_slb(void);
+long __machine_check_early_realmode_p7(struct pt_regs *regs);
+long __machine_check_early_realmode_p8(struct pt_regs *regs);
+long __machine_check_early_realmode_p9(struct pt_regs *regs);
+long __machine_check_early_realmode_p10(struct pt_regs *regs);
 #endif /* CONFIG_PPC_BOOK3S_64 */
 #endif /* __ASM_PPC64_MCE_H__ */
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 3d406a9626e86..4ca9cf556be92 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -72,9 +72,6 @@ extern void __setup_cpu_power9(unsigned long offset, struct cpu_spec* spec);
 extern void __restore_cpu_power9(void);
 extern void __setup_cpu_power10(unsigned long offset, struct cpu_spec* spec);
 extern void __restore_cpu_power10(void);
-extern long __machine_check_early_realmode_p7(struct pt_regs *regs);
-extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
-extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
 #endif /* CONFIG_PPC64 */
 #if defined(CONFIG_E500)
 extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec);
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 6f8c0c6b937a1..8dc46f38680b2 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -64,10 +64,6 @@ struct dt_cpu_feature {
  * Set up the base CPU
  */
 
-extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
-extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
-extern long __machine_check_early_realmode_p10(struct pt_regs *regs);
-
 static int hv_mode;
 
 static struct {
-- 
2.26.2


^ permalink raw reply related

* Re: [PATCH v2 2/5] powerpc/lib: Initialize a temporary mm for code patching
From: Christopher M. Riedl @ 2020-08-17  2:21 UTC (permalink / raw)
  To: Daniel Axtens, linuxppc-dev; +Cc: kernel-hardening
In-Reply-To: <87lfiso3rk.fsf@dja-thinkpad.axtens.net>

On Thu Aug 6, 2020 at 8:24 AM CDT, Daniel Axtens wrote:
> "Christopher M. Riedl" <cmr@informatik.wtf> writes:
>
> > When code patching a STRICT_KERNEL_RWX kernel the page containing the
> > address to be patched is temporarily mapped with permissive memory
> > protections. Currently, a per-cpu vmalloc patch area is used for this
> > purpose. While the patch area is per-cpu, the temporary page mapping is
> > inserted into the kernel page tables for the duration of the patching.
> > The mapping is exposed to CPUs other than the patching CPU - this is
> > undesirable from a hardening perspective.
> >
> > Use the `poking_init` init hook to prepare a temporary mm and patching
> > address. Initialize the temporary mm by copying the init mm. Choose a
> > randomized patching address inside the temporary mm userspace address
> > portion. The next patch uses the temporary mm and patching address for
> > code patching.
> >
> > Based on x86 implementation:
> >
> > commit 4fc19708b165
> > ("x86/alternatives: Initialize temporary mm for patching")
> >
> > Signed-off-by: Christopher M. Riedl <cmr@informatik.wtf>
> > ---
> >  arch/powerpc/lib/code-patching.c | 33 ++++++++++++++++++++++++++++++++
> >  1 file changed, 33 insertions(+)
> >
> > diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
> > index 0a051dfeb177..8ae1a9e5fe6e 100644
> > --- a/arch/powerpc/lib/code-patching.c
> > +++ b/arch/powerpc/lib/code-patching.c
> > @@ -11,6 +11,8 @@
> >  #include <linux/cpuhotplug.h>
> >  #include <linux/slab.h>
> >  #include <linux/uaccess.h>
> > +#include <linux/sched/task.h>
> > +#include <linux/random.h>
> >  
> >  #include <asm/tlbflush.h>
> >  #include <asm/page.h>
> > @@ -44,6 +46,37 @@ int raw_patch_instruction(struct ppc_inst *addr, struct ppc_inst instr)
> >  }
> >  
> >  #ifdef CONFIG_STRICT_KERNEL_RWX
> > +
> > +static struct mm_struct *patching_mm __ro_after_init;
> > +static unsigned long patching_addr __ro_after_init;
> > +
> > +void __init poking_init(void)
> > +{
> > +	spinlock_t *ptl; /* for protecting pte table */
> > +	pte_t *ptep;
> > +
> > +	/*
> > +	 * Some parts of the kernel (static keys for example) depend on
> > +	 * successful code patching. Code patching under STRICT_KERNEL_RWX
> > +	 * requires this setup - otherwise we cannot patch at all. We use
> > +	 * BUG_ON() here and later since an early failure is preferred to
> > +	 * buggy behavior and/or strange crashes later.
> > +	 */
> > +	patching_mm = copy_init_mm();
> > +	BUG_ON(!patching_mm);
> > +
> > +	/*
> > +	 * In hash we cannot go above DEFAULT_MAP_WINDOW easily.
> > +	 * XXX: Do we want additional bits of entropy for radix?
> > +	 */
> > +	patching_addr = (get_random_long() & PAGE_MASK) %
> > +		(DEFAULT_MAP_WINDOW - PAGE_SIZE);
>
> It took me a while to understand this calculation. I see that it's
> calculating a base address for a page in which to do patching. It does
> the following:

I will add a comment explaining the calulcation in the next spin.

>
> - get a random long
>
> - mask with PAGE_MASK so as to get a page aligned value
>
> - make sure that the base address is at least one PAGE_SIZE below
> DEFAULT_MAP_WINDOW so we have a clear page between the base and
> DEFAULT_MAP_WINDOW.
>
> On 64-bit Book3S with 64K pages, that works out to be
>
> PAGE_SIZE = 0x0000 0000 0001 0000
> PAGE_MASK = 0xFFFF FFFF FFFF 0000
>
> DEFAULT_MAP_WINDOW = DEFAULT_MAP_WINDOW_USER64 = TASK_SIZE_128TB
> = 0x0000_8000_0000_0000
>
> DEFAULT_MAP_WINDOW - PAGE_SIZE = 0x0000 7FFF FFFF 0000
>
> It took a while (and a conversation with my wife who studied pure
> maths!) but I am convinced that the modulo preserves the page-alignement
> of the patching address.

I am glad a proper mathematician agrees because my maths are decidedly
unpure :)

>
> One thing I did realise is that patching_addr can be zero at the end of
> this process. That seems dubious and slightly error-prone to me - is
> the patching process robust to that or should we exclude it?

Good catch! I will fix this in the next spin.

>
> Anyway, if I have the maths right, that there are 0x7fffffff or ~2
> billion possible locations for the patching page, which is just shy of
> 31 bits of entropy.
>
> I think this compares pretty favourably to most (K)ASLR implementations?

I will stress that I am not an expert here, but it looks like this does
compares favorably against other 64b ASLR [0].

[0]: https://www.cs.ucdavis.edu/~peisert/research/2017-SecDev-AnalysisASLR.pdf

>
> What's the range if built with 4k pages?

Using the formula from my series coverletter, we should expect 34 bits
of entropy since DEFAULT_MAP_WINDOW_USER64 is 64TB for 4K pages:

	bits of entropy = log2(DEFAULT_MAP_WINDOW_USER64 / PAGE_SIZE)

	PAGE_SIZE=4K, DEFAULT_MAP_WINDOW_USER64=64TB
	bits of entropy = log2(64TB / 4K)
	bits of entropy = 34

>
> Kind regards,
> Daniel
>
> > +
> > +	ptep = get_locked_pte(patching_mm, patching_addr, &ptl);
> > +	BUG_ON(!ptep);
> > +	pte_unmap_unlock(ptep, ptl);
> > +}
> > +
> >  static DEFINE_PER_CPU(struct vm_struct *, text_poke_area);
> >  
> >  static int text_area_cpu_up(unsigned int cpu)
> > -- 
> > 2.27.0


^ permalink raw reply

* Re: [PATCH v2] powerpc/pseries: explicitly reschedule during drmem_lmb list traversal
From: Michael Ellerman @ 2020-08-17  3:45 UTC (permalink / raw)
  To: Nathan Lynch, Tyrel Datwyler, linuxppc-dev; +Cc: cheloha, ldufour
In-Reply-To: <874kp7z73m.fsf@linux.ibm.com>

Nathan Lynch <nathanl@linux.ibm.com> writes:
> Michael Ellerman <mpe@ellerman.id.au> writes:
>> Tyrel Datwyler <tyreld@linux.ibm.com> writes:
>>> On 8/11/20 6:20 PM, Nathan Lynch wrote:
>>>>  
>>>> +static inline struct drmem_lmb *drmem_lmb_next(struct drmem_lmb *lmb)
>>>> +{
>>>> +	const unsigned int resched_interval = 20;
>>>> +
>>>> +	BUG_ON(lmb < drmem_info->lmbs);
>>>> +	BUG_ON(lmb >= drmem_info->lmbs + drmem_info->n_lmbs);
>>>
>>> I think BUG_ON is a pretty big no-no these days unless there is no other option.
>>
>> It's complicated, but yes we would like to avoid adding them if we can.
>>
>> In a case like this there is no other option, *if* the check has to be
>> in drmem_lmb_next().
>>
>> But I don't think we really need to check that there.
>>
>> If for some reason this was called with an *lmb pointing outside of the
>> lmbs array it would confuse the cond_resched() logic, but it's not worth
>> crashing the box for that IMHO.
>
> The BUG_ONs are pretty much orthogonal to the cond_resched().

Yes that was kind of my point. We don't need them to implement the
cond_resched() logic.

> It's not apparent from the context of the change, but some users of the
> for_each_drmem_lmb* macros modify elements of the drmem_info->lmbs
> array. If the lmb passed to drmem_lmb_next() violates the bounds check
> (say, if the callsite inappropriately modifies it within the loop), such
> users are guaranteed to corrupt other objects in memory. This was my
> thinking in adding the BUG_ONs, and I don't see another place to do
> it.

If it's really something we're worried about, I think we'd be better off
putting checks for that in the code that's doing those modifications.

That way you have enough context to do something more nuanced than a
BUG(), ie. you can print a useful message and fail whatever operation is
in progress.

If we did that then we could also add those BUG_ONs() as a safety net.

What you really want is a way for the for_each_xxx() construct to
express that there was an error traversing the list, but there isn't
really a nice way to do that in C.

cheers

^ permalink raw reply

* Re: [PATCH v2 1/5] powerpc/mm: Introduce temporary mm
From: Christopher M. Riedl @ 2020-08-17  5:16 UTC (permalink / raw)
  To: Daniel Axtens, linuxppc-dev; +Cc: kernel-hardening
In-Reply-To: <87o8noo96l.fsf@dja-thinkpad.axtens.net>

On Thu Aug 6, 2020 at 6:27 AM CDT, Daniel Axtens wrote:
> Hi Chris,
>   
> >  void __set_breakpoint(int nr, struct arch_hw_breakpoint *brk);
> > +void __get_breakpoint(int nr, struct arch_hw_breakpoint *brk);
> >  bool ppc_breakpoint_available(void);
> >  #ifdef CONFIG_PPC_ADV_DEBUG_REGS
> >  extern void do_send_trap(struct pt_regs *regs, unsigned long address,
> > diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
> > index 1a474f6b1992..9269c7c7b04e 100644
> > --- a/arch/powerpc/include/asm/mmu_context.h
> > +++ b/arch/powerpc/include/asm/mmu_context.h
> > @@ -10,6 +10,7 @@
> >  #include <asm/mmu.h>	
> >  #include <asm/cputable.h>
> >  #include <asm/cputhreads.h>
> > +#include <asm/debug.h>
> >  
> >  /*
> >   * Most if the context management is out of line
> > @@ -300,5 +301,68 @@ static inline int arch_dup_mmap(struct mm_struct *oldmm,
> >  	return 0;
> >  }
> >  
> > +struct temp_mm {
> > +	struct mm_struct *temp;
> > +	struct mm_struct *prev;
> > +	bool is_kernel_thread;
> > +	struct arch_hw_breakpoint brk[HBP_NUM_MAX];
> > +};
>
> This is on the nitpicky end, but I wonder if this should be named
> temp_mm, or should be labelled something else to capture its broader
> purpose as a context for code patching? I'm thinking that a store of
> breakpoints is perhaps unusual in a memory-managment structure?
>
> I don't have a better suggestion off the top of my head and I'm happy
> for you to leave it, I just wanted to flag it as a possible way we could
> be clearer.

First of all thank you for the review!

I had actually planned to move all this code into lib/code-patching.c
directly (and it turns out that's what x86 ended up doing as well).

>
> > +
> > +static inline void init_temp_mm(struct temp_mm *temp_mm, struct mm_struct *mm)
> > +{
> > +	temp_mm->temp = mm;
> > +	temp_mm->prev = NULL;
> > +	temp_mm->is_kernel_thread = false;
> > +	memset(&temp_mm->brk, 0, sizeof(temp_mm->brk));
> > +}
> > +
> > +static inline void use_temporary_mm(struct temp_mm *temp_mm)
> > +{
> > +	lockdep_assert_irqs_disabled();
> > +
> > +	temp_mm->is_kernel_thread = current->mm == NULL;
> > +	if (temp_mm->is_kernel_thread)
> > +		temp_mm->prev = current->active_mm;
>
> You don't seem to restore active_mm below. I don't know what active_mm
> does, so I don't know if this is a problem.

For kernel threads 'current->mm' is NULL since a kthread does not need
a userspace mm; however they still need a mm so they "borrow" one which
is indicated by 'current->active_mm'.

'current->mm' needs to be restored because Hash requires a non-NULL
value when handling a page fault and so 'current->mm' gets set to the
temp_mm. This is a special case for kernel threads and Hash translation.

>
> > +	else
> > +		temp_mm->prev = current->mm;
> > +
> > +	/*
> > +	 * Hash requires a non-NULL current->mm to allocate a userspace address
> > +	 * when handling a page fault. Does not appear to hurt in Radix either.
> > +	 */
> > +	current->mm = temp_mm->temp;
> > +	switch_mm_irqs_off(NULL, temp_mm->temp, current);
> > +
> > +	if (ppc_breakpoint_available()) {
>
> I wondered if this could be changed during a text-patching operation.
> AIUI, it potentially can on a P9 via "dawr_enable_dangerous" in debugfs.
>
> I don't know if that's a problem. My concern is that you could turn off
> breakpoints, call 'use_temporary_mm', then turn them back on again
> before 'unuse_temporary_mm' and get a breakpoint while that can access
> the temporary mm. Is there something else that makes that safe?
> disabling IRQs maybe?

Hmm, I will have to investigate this more. I'm not sure if there is a
better way to just completely disable breakpoints while the temporary mm
is in use.

>
> > +		struct arch_hw_breakpoint null_brk = {0};
> > +		int i = 0;
> > +
> > +		for (; i < nr_wp_slots(); ++i) {
>
> super nitpicky, and I'm not sure if this is actually documented, but I'd
> usually see this written as:
>
> for (i = 0; i < nr_wp_slots(); i++) {
>
> Not sure if there's any reason that it _shouldn't_ be written the way
> you've written it (and I do like initialising the variable when it's
> defined!), I'm just not used to it. (Likewise with the unuse function.)
>

I've found other places (even in arch/powerpc!) where this is done so I
think it's fine. I prefer using this style when the variable
declaration and initialization are "close" to the loop statement.

> > +			__get_breakpoint(i, &temp_mm->brk[i]);
> > +			if (temp_mm->brk[i].type != 0)
> > +				__set_breakpoint(i, &null_brk);
> > +		}
> > +	}
> > +}
> > +
>
> Kind regards,
> Daniel
>
> > +static inline void unuse_temporary_mm(struct temp_mm *temp_mm)
> > +{
> > +	lockdep_assert_irqs_disabled();
> > +
> > +	if (temp_mm->is_kernel_thread)
> > +		current->mm = NULL;
> > +	else
> > +		current->mm = temp_mm->prev;
> > +	switch_mm_irqs_off(NULL, temp_mm->prev, current);
> > +
> > +	if (ppc_breakpoint_available()) {
> > +		int i = 0;
> > +
> > +		for (; i < nr_wp_slots(); ++i)
> > +			if (temp_mm->brk[i].type != 0)
> > +				__set_breakpoint(i, &temp_mm->brk[i]);
> > +	}
> > +}
> > +
> >  #endif /* __KERNEL__ */
> >  #endif /* __ASM_POWERPC_MMU_CONTEXT_H */
> > diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
> > index 4650b9bb217f..b6c123bf5edd 100644
> > --- a/arch/powerpc/kernel/process.c
> > +++ b/arch/powerpc/kernel/process.c
> > @@ -824,6 +824,11 @@ static inline int set_breakpoint_8xx(struct arch_hw_breakpoint *brk)
> >  	return 0;
> >  }
> >  
> > +void __get_breakpoint(int nr, struct arch_hw_breakpoint *brk)
> > +{
> > +	memcpy(brk, this_cpu_ptr(&current_brk[nr]), sizeof(*brk));
> > +}
> > +
> >  void __set_breakpoint(int nr, struct arch_hw_breakpoint *brk)
> >  {
> >  	memcpy(this_cpu_ptr(&current_brk[nr]), brk, sizeof(*brk));
> > -- 
> > 2.27.0


^ permalink raw reply

* [PATCH v1] powerpc/process: Replace an #ifdef CONFIG_PPC_47x by IS_ENABLED()
From: Christophe Leroy @ 2020-08-17  5:46 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
  Cc: linuxppc-dev, linux-kernel

isync() is always defined, no need for an #ifdef.

Replace it by IS_ENABLED(CONFIG_PPC_47x).

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/process.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index e86e28c28259..fd3e11663613 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -777,9 +777,8 @@ static void switch_hw_breakpoint(struct task_struct *new)
 static inline int __set_dabr(unsigned long dabr, unsigned long dabrx)
 {
 	mtspr(SPRN_DAC1, dabr);
-#ifdef CONFIG_PPC_47x
-	isync();
-#endif
+	if (IS_ENABLED(CONFIG_PPC_47x))
+		isync();
 	return 0;
 }
 #elif defined(CONFIG_PPC_BOOK3S)
-- 
2.25.0


^ permalink raw reply related

* [PATCH v1] powerpc/process: Replace #ifdef CONFIG_KALLSYMS by IS_ENABLED()
From: Christophe Leroy @ 2020-08-17  5:46 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
  Cc: linuxppc-dev, linux-kernel

The #ifdef CONFIG_KALLSYMS encloses some printk which can
compile in all cases.

Replace by IS_ENABLED().

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/process.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 087711aa0126..987bc8e73d5e 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1469,14 +1469,14 @@ void show_regs(struct pt_regs * regs)
 			break;
 	}
 	pr_cont("\n");
-#ifdef CONFIG_KALLSYMS
 	/*
 	 * Lookup NIP late so we have the best change of getting the
 	 * above info out without failing
 	 */
-	printk("NIP ["REG"] %pS\n", regs->nip, (void *)regs->nip);
-	printk("LR ["REG"] %pS\n", regs->link, (void *)regs->link);
-#endif
+	if (IS_ENABLED(CONFIG_KALLSYMS)) {
+		printk("NIP ["REG"] %pS\n", regs->nip, (void *)regs->nip);
+		printk("LR ["REG"] %pS\n", regs->link, (void *)regs->link);
+	}
 	show_stack(current, (unsigned long *) regs->gpr[1], KERN_DEFAULT);
 	if (!user_mode(regs))
 		show_instructions(regs);
-- 
2.25.0


^ permalink raw reply related

* [PATCH v1] powerpc/process: Remove unnecessary #ifdef CONFIG_FUNCTION_GRAPH_TRACER
From: Christophe Leroy @ 2020-08-17  5:46 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
  Cc: linuxppc-dev, linux-kernel

ftrace_graph_ret_addr() is always defined and returns 'ip' when
CONFIG_FUNCTION GRAPH_TRACER is not set.

So the #ifdef is not needed, remove it.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/process.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index ffbe79960c73..e86e28c28259 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -2096,10 +2096,8 @@ void show_stack(struct task_struct *tsk, unsigned long *stack,
 	unsigned long sp, ip, lr, newsp;
 	int count = 0;
 	int firstframe = 1;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	unsigned long ret_addr;
 	int ftrace_idx = 0;
-#endif
 
 	if (tsk == NULL)
 		tsk = current;
@@ -2127,12 +2125,10 @@ void show_stack(struct task_struct *tsk, unsigned long *stack,
 		if (!firstframe || ip != lr) {
 			printk("%s["REG"] ["REG"] %pS",
 				loglvl, sp, ip, (void *)ip);
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
 			ret_addr = ftrace_graph_ret_addr(current,
 						&ftrace_idx, ip, stack);
 			if (ret_addr != ip)
 				pr_cont(" (%pS)", (void *)ret_addr);
-#endif
 			if (firstframe)
 				pr_cont(" (unreliable)");
 			pr_cont("\n");
-- 
2.25.0


^ permalink raw reply related

* [PATCH v1] powerpc/process: Replace an #ifdef CONFIG_PPC_BOOK3S_64 by IS_ENABLED()
From: Christophe Leroy @ 2020-08-17  5:46 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
  Cc: linuxppc-dev, linux-kernel

This #ifdef CONFIG_PPC_BOOK3S_64 calls preload_new_slb_context()
when radix is not enabled.

radix_enabled() is always defined, and the prototype for
preload_new_slb_context() is always present, so the #ifdef
is unneeded.

Replace it by IS_ENABLED().

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/process.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 987bc8e73d5e..a17d0746d55f 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1725,10 +1725,8 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 #ifdef CONFIG_PPC64
 	unsigned long load_addr = regs->gpr[2];	/* saved by ELF_PLAT_INIT */
 
-#ifdef CONFIG_PPC_BOOK3S_64
-	if (!radix_enabled())
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !radix_enabled())
 		preload_new_slb_context(start, sp);
-#endif
 #endif
 
 	/*
-- 
2.25.0


^ permalink raw reply related

* [PATCH v1] powerpc/process: Replace an #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) by IS_ENABLED()
From: Christophe Leroy @ 2020-08-17  5:46 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
  Cc: linuxppc-dev, linux-kernel

The #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) encloses some
printk which can be compiled in all cases.

Replace by IS_ENABLED().

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/process.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index fd3e11663613..087711aa0126 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1446,12 +1446,13 @@ void show_regs(struct pt_regs * regs)
 	trap = TRAP(regs);
 	if (!trap_is_syscall(regs) && cpu_has_feature(CPU_FTR_CFAR))
 		pr_cont("CFAR: "REG" ", regs->orig_gpr3);
-	if (trap == 0x200 || trap == 0x300 || trap == 0x600)
-#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
-		pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr);
-#else
-		pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
-#endif
+	if (trap == 0x200 || trap == 0x300 || trap == 0x600) {
+		if (IS_ENABLED(CONFIG_4xx) || IS_ENABLED(CONFIG_BOOKE))
+			pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr);
+		else
+			pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
+	}
+
 #ifdef CONFIG_PPC64
 	pr_cont("IRQMASK: %lx ", regs->softe);
 #endif
-- 
2.25.0


^ permalink raw reply related

* [PATCH v1] powerpc/process: Tag an #endif to help locate the matching #ifdef.
From: Christophe Leroy @ 2020-08-17  5:46 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
  Cc: linuxppc-dev, linux-kernel

That #endif is more than 100 lines after the matching #ifdef,
and there are several #ifdef/#else/#endif inbetween.

Tag it as /* CONFIG_PPC_BOOK3S_64 */ to help locate the
matching #ifdef.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/process.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 016bd831908e..ffbe79960c73 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -575,7 +575,7 @@ void notrace restore_math(struct pt_regs *regs)
 		regs->msr |= new_msr;
 	}
 }
-#endif
+#endif /* CONFIG_PPC_BOOK3S_64 */
 
 static void save_all(struct task_struct *tsk)
 {
-- 
2.25.0


^ permalink raw reply related

* [PATCH v1 1/4] powerpc/process: Remove useless #ifdef CONFIG_VSX
From: Christophe Leroy @ 2020-08-17  5:47 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
  Cc: linuxppc-dev, linux-kernel

cpu_has_feature(CPU_FTR_VSX) returns false when CONFIG_VSX is
not set.

There is no need to enclose the test in an #ifdef CONFIG_VSX.
Remove it.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/process.c | 13 +------------
 1 file changed, 1 insertion(+), 12 deletions(-)

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index a17d0746d55f..b64d71188715 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -124,10 +124,8 @@ unsigned long notrace msr_check_and_set(unsigned long bits)
 
 	newmsr = oldmsr | bits;
 
-#ifdef CONFIG_VSX
 	if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP))
 		newmsr |= MSR_VSX;
-#endif
 
 	if (oldmsr != newmsr)
 		mtmsr_isync(newmsr);
@@ -144,10 +142,8 @@ void notrace __msr_check_and_clear(unsigned long bits)
 
 	newmsr = oldmsr & ~bits;
 
-#ifdef CONFIG_VSX
 	if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP))
 		newmsr &= ~MSR_VSX;
-#endif
 
 	if (oldmsr != newmsr)
 		mtmsr_isync(newmsr);
@@ -162,10 +158,8 @@ static void __giveup_fpu(struct task_struct *tsk)
 	save_fpu(tsk);
 	msr = tsk->thread.regs->msr;
 	msr &= ~(MSR_FP|MSR_FE0|MSR_FE1);
-#ifdef CONFIG_VSX
 	if (cpu_has_feature(CPU_FTR_VSX))
 		msr &= ~MSR_VSX;
-#endif
 	tsk->thread.regs->msr = msr;
 }
 
@@ -245,10 +239,8 @@ static void __giveup_altivec(struct task_struct *tsk)
 	save_altivec(tsk);
 	msr = tsk->thread.regs->msr;
 	msr &= ~MSR_VEC;
-#ifdef CONFIG_VSX
 	if (cpu_has_feature(CPU_FTR_VSX))
 		msr &= ~MSR_VSX;
-#endif
 	tsk->thread.regs->msr = msr;
 }
 
@@ -421,10 +413,8 @@ static int __init init_msr_all_available(void)
 	if (cpu_has_feature(CPU_FTR_ALTIVEC))
 		msr_all_available |= MSR_VEC;
 #endif
-#ifdef CONFIG_VSX
 	if (cpu_has_feature(CPU_FTR_VSX))
 		msr_all_available |= MSR_VSX;
-#endif
 #ifdef CONFIG_SPE
 	if (cpu_has_feature(CPU_FTR_SPE))
 		msr_all_available |= MSR_SPE;
@@ -509,19 +499,18 @@ static bool should_restore_altivec(void) { return false; }
 static void do_restore_altivec(void) { }
 #endif /* CONFIG_ALTIVEC */
 
-#ifdef CONFIG_VSX
 static bool should_restore_vsx(void)
 {
 	if (cpu_has_feature(CPU_FTR_VSX))
 		return true;
 	return false;
 }
+#ifdef CONFIG_VSX
 static void do_restore_vsx(void)
 {
 	current->thread.used_vsr = 1;
 }
 #else
-static bool should_restore_vsx(void) { return false; }
 static void do_restore_vsx(void) { }
 #endif /* CONFIG_VSX */
 
-- 
2.25.0


^ permalink raw reply related

* [PATCH v1 2/4] powerpc/process: Remove useless #ifdef CONFIG_ALTIVEC
From: Christophe Leroy @ 2020-08-17  5:47 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <0eb61cf0dc66d781d47deb2228498cd61d03a754.1597643221.git.christophe.leroy@csgroup.eu>

cpu_has_feature(CPU_FTR_ALTIVEC) returns false when CONFIG_ALTIVEC is
not set.

There is no need to enclose the test in an #ifdef CONFIG_ALTIVEC.
Remove it.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/process.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index b64d71188715..360415689f8a 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -409,10 +409,8 @@ static int __init init_msr_all_available(void)
 #ifdef CONFIG_PPC_FPU
 	msr_all_available |= MSR_FP;
 #endif
-#ifdef CONFIG_ALTIVEC
 	if (cpu_has_feature(CPU_FTR_ALTIVEC))
 		msr_all_available |= MSR_VEC;
-#endif
 	if (cpu_has_feature(CPU_FTR_VSX))
 		msr_all_available |= MSR_VSX;
 #ifdef CONFIG_SPE
@@ -446,10 +444,8 @@ void giveup_all(struct task_struct *tsk)
 	if (usermsr & MSR_FP)
 		__giveup_fpu(tsk);
 #endif
-#ifdef CONFIG_ALTIVEC
 	if (usermsr & MSR_VEC)
 		__giveup_altivec(tsk);
-#endif
 #ifdef CONFIG_SPE
 	if (usermsr & MSR_SPE)
 		__giveup_spe(tsk);
-- 
2.25.0


^ permalink raw reply related

* [PATCH v1 4/4] powerpc/process: Remove useless #ifdef CONFIG_PPC_FPU
From: Christophe Leroy @ 2020-08-17  5:47 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <0eb61cf0dc66d781d47deb2228498cd61d03a754.1597643221.git.christophe.leroy@csgroup.eu>

Add a stub for __giveup_fpu() when CONFIG_PPC_FPU is
not selected, as done for CONFIG_SPE and CONFIG_ALTIVEC.

This allows to remove some #ifdef CONFIG_PPC_FPU.

Also change one to IS_ENABLED().

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/process.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 7090c99a60d9..8133a6ce3242 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -229,6 +229,8 @@ void enable_kernel_fp(void)
 	}
 }
 EXPORT_SYMBOL(enable_kernel_fp);
+#else
+static inline void __giveup_fpu(struct task_struct *tsk) { }
 #endif /* CONFIG_PPC_FPU */
 
 #ifdef CONFIG_ALTIVEC
@@ -406,9 +408,8 @@ static unsigned long msr_all_available;
 
 static int __init init_msr_all_available(void)
 {
-#ifdef CONFIG_PPC_FPU
-	msr_all_available |= MSR_FP;
-#endif
+	if (IS_ENABLED(CONFIG_PPC_FPU))
+		msr_all_available |= MSR_FP;
 	if (cpu_has_feature(CPU_FTR_ALTIVEC))
 		msr_all_available |= MSR_VEC;
 	if (cpu_has_feature(CPU_FTR_VSX))
@@ -438,10 +439,8 @@ void giveup_all(struct task_struct *tsk)
 
 	WARN_ON((usermsr & MSR_VSX) && !((usermsr & MSR_FP) && (usermsr & MSR_VEC)));
 
-#ifdef CONFIG_PPC_FPU
 	if (usermsr & MSR_FP)
 		__giveup_fpu(tsk);
-#endif
 	if (usermsr & MSR_VEC)
 		__giveup_altivec(tsk);
 	if (usermsr & MSR_SPE)
-- 
2.25.0


^ permalink raw reply related

* [PATCH v1 3/4] powerpc/process: Remove useless #ifdef CONFIG_SPE
From: Christophe Leroy @ 2020-08-17  5:47 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <0eb61cf0dc66d781d47deb2228498cd61d03a754.1597643221.git.christophe.leroy@csgroup.eu>

cpu_has_feature(CPU_FTR_SPE) returns false when CONFIG_SPE is
not set.

There is no need to enclose the test in an #ifdef CONFIG_SPE.
Remove it.

CPU_FTR_SPE only exists on 32 bits. Define it as 0 on 64 bits.

We have a couple of places like:

 #ifdef CONFIG_SPE
	if (cpu_has_feature(CPU_FTR_SPE)) {
		do_something_that_requires_CONFIG_SPE
	} else {
		return -EINVAL;
	}
 #else
	return -EINVAL;
 #endif

Replace them by a cleaner version:

	if (cpu_has_feature(CPU_FTR_SPE)) {
 #ifdef CONFIG_SPE
		do_something_that_requires_CONFIG_SPE
 #endif
	} else {
		return -EINVAL;
	}

When CONFIG_SPE is not set, this resolves to an unconditional
return of -EINVAL

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/include/asm/cputable.h |  1 +
 arch/powerpc/kernel/process.c       | 21 +++++++--------------
 2 files changed, 8 insertions(+), 14 deletions(-)

diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index fdddb822d564..cc21dbcc6794 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -165,6 +165,7 @@ static inline void cpu_feature_keys_init(void) { }
 #else	/* CONFIG_PPC32 */
 /* Define these to 0 for the sake of tests in common code */
 #define CPU_FTR_PPC_LE			(0)
+#define CPU_FTR_SPE			(0)
 #endif
 
 /*
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 360415689f8a..7090c99a60d9 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -413,10 +413,8 @@ static int __init init_msr_all_available(void)
 		msr_all_available |= MSR_VEC;
 	if (cpu_has_feature(CPU_FTR_VSX))
 		msr_all_available |= MSR_VSX;
-#ifdef CONFIG_SPE
 	if (cpu_has_feature(CPU_FTR_SPE))
 		msr_all_available |= MSR_SPE;
-#endif
 
 	return 0;
 }
@@ -446,10 +444,8 @@ void giveup_all(struct task_struct *tsk)
 #endif
 	if (usermsr & MSR_VEC)
 		__giveup_altivec(tsk);
-#ifdef CONFIG_SPE
 	if (usermsr & MSR_SPE)
 		__giveup_spe(tsk);
-#endif
 
 	msr_check_and_clear(msr_all_available);
 }
@@ -1843,7 +1839,6 @@ int set_fpexc_mode(struct task_struct *tsk, unsigned int val)
 	 * fpexc_mode.  fpexc_mode is also used for setting FP exception
 	 * mode (asyn, precise, disabled) for 'Classic' FP. */
 	if (val & PR_FP_EXC_SW_ENABLE) {
-#ifdef CONFIG_SPE
 		if (cpu_has_feature(CPU_FTR_SPE)) {
 			/*
 			 * When the sticky exception bits are set
@@ -1857,16 +1852,15 @@ int set_fpexc_mode(struct task_struct *tsk, unsigned int val)
 			 * anyway to restore the prctl settings from
 			 * the saved environment.
 			 */
+#ifdef CONFIG_SPE
 			tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR);
 			tsk->thread.fpexc_mode = val &
 				(PR_FP_EXC_SW_ENABLE | PR_FP_ALL_EXCEPT);
+#endif
 			return 0;
 		} else {
 			return -EINVAL;
 		}
-#else
-		return -EINVAL;
-#endif
 	}
 
 	/* on a CONFIG_SPE this does not hurt us.  The bits that
@@ -1887,8 +1881,7 @@ int get_fpexc_mode(struct task_struct *tsk, unsigned long adr)
 {
 	unsigned int val;
 
-	if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE)
-#ifdef CONFIG_SPE
+	if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE) {
 		if (cpu_has_feature(CPU_FTR_SPE)) {
 			/*
 			 * When the sticky exception bits are set
@@ -1902,15 +1895,15 @@ int get_fpexc_mode(struct task_struct *tsk, unsigned long adr)
 			 * anyway to restore the prctl settings from
 			 * the saved environment.
 			 */
+#ifdef CONFIG_SPE
 			tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR);
 			val = tsk->thread.fpexc_mode;
+#endif
 		} else
 			return -EINVAL;
-#else
-		return -EINVAL;
-#endif
-	else
+	} else {
 		val = __unpack_fe01(tsk->thread.fpexc_mode);
+	}
 	return put_user(val, (unsigned int __user *) adr);
 }
 
-- 
2.25.0


^ permalink raw reply related

* [PATCH v3] powerpc/numa: Restrict possible nodes based on platform
From: Srikar Dronamraju @ 2020-08-17  5:52 UTC (permalink / raw)
  To: Michael Ellerman
  Cc: Nathan Lynch, Tyrel Datwyler, Srikar Dronamraju, Bharata B Rao,
	linuxppc-dev

As per draft LoPAPR (Revision 2.9_pre7), section B.5.3 "Run Time Abstaction
Services (RTAS) Node at
https://openpowerfoundation.org/wp-content/uploads/2020/07/LoPAR-20200611.pdf,
there are 2 device tree property ibm,max-associativity-domains (which
defines the maximum number of domains that the firmware i.e PowerVM can
support) and ibm,current-associativity-domains (which defines the maximum
number of domains that the platform can support). Value of
ibm,max-associativity-domains property is always greater than or equal to
ibm,current-associativity-domains property. If the said property is not
available, use ibm,max-associativity-domain as fallback. In this yet to be
released LoPAPR, ibm,current-associativity-domains is mentioned in page 833
/ B.5.3 which is covered under under "Appendix B. System Binding" section

Currently Powerpc uses ibm,max-associativity-domains property while
setting the possible number of nodes. This is currently set at 32.
However the possible number of nodes for a platform may be significantly
less. Hence set the possible number of nodes based on
ibm,current-associativity-domains property.

Nathan Lynch had raised a valid concern that post LPM, a user could DLPAR
add processors and memory after LPM with "new" associativity properties.
https://lore.kernel.org/linuxppc-dev/871rljfet9.fsf@linux.ibm.com/t/#u

He also pointed out that ibm,max-associativity-domains has the same contents
on all currently available PowerVM systems, unlike
ibm,current-associativity-domains and hence may be better able to handle the
new numa associativity properties.

However with the recent commit dbce45628085 ("powerpc/numa: Limit possible
nodes to within num_possible_nodes"), all new numa  associativity properties
are capped to initially set nr_node_ids. Hence this commit should be safe
with any new dlpar add post LPM.

$ lsprop /proc/device-tree/rtas/ibm,*associ*-domains
/proc/device-tree/rtas/ibm,current-associativity-domains
		 00000005 00000001 00000002 00000002 00000002 00000010
/proc/device-tree/rtas/ibm,max-associativity-domains
		 00000005 00000001 00000008 00000020 00000020 00000100

$ cat /sys/devices/system/node/possible ##Before patch
0-31

$ cat /sys/devices/system/node/possible ##After patch
0-1

Note the maximum nodes this platform can support is only 2 but the
possible nodes is set to 32.

This is important because lot of kernel and user space code allocate
structures for all possible nodes leading to a lot of memory that is
allocated but not used.

I ran a simple experiment to create and destroy 100 memory cgroups on
boot on a 8 node machine (Power8 Alpine).

Before patch
free -k at boot
              total        used        free      shared  buff/cache   available
Mem:      523498176     4106816   518820608       22272      570752   516606720
Swap:       4194240           0     4194240

free -k after creating 100 memory cgroups
              total        used        free      shared  buff/cache   available
Mem:      523498176     4628416   518246464       22336      623296   516058688
Swap:       4194240           0     4194240

free -k after destroying 100 memory cgroups
              total        used        free      shared  buff/cache   available
Mem:      523498176     4697408   518173760       22400      627008   515987904
Swap:       4194240           0     4194240

After patch
free -k at boot
              total        used        free      shared  buff/cache   available
Mem:      523498176     3969472   518933888       22272      594816   516731776
Swap:       4194240           0     4194240

free -k after creating 100 memory cgroups
              total        used        free      shared  buff/cache   available
Mem:      523498176     4181888   518676096       22208      640192   516496448
Swap:       4194240           0     4194240

free -k after destroying 100 memory cgroups
              total        used        free      shared  buff/cache   available
Mem:      523498176     4232320   518619904       22272      645952   516443264
Swap:       4194240           0     4194240

Observations:
Fixed kernel takes 137344 kb (4106816-3969472) less to boot.
Fixed kernel takes 309184 kb (4628416-4181888-137344) less to create 100 memcgs.

Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Bharata B Rao <bharata@linux.ibm.com>
Cc: Tyrel Datwyler <tyreld@linux.ibm.com>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
Changelog v2->v3:
v2: https://lore.kernel.org/linuxppc-dev/20200707140644.7241-1-srikar@linux.vnet.ibm.com/t/#u
Updated commit msg to mention LoPAPR reference section  and url details
					(Michael Ellerman)
Updated commit msg to discuss about possible new numa associativity properties.
					(Nathan Lynch)

Changelog v1->v2:
v1: https://lore.kernel.org/linuxppc-dev/20200706064002.14848-1-srikar@linux.vnet.ibm.com/t/#u
Fallback to ibm,max-associativity-domains if ibm,current-associativity
is not available. Suggested by Tyrel Datwyler.

 arch/powerpc/mm/numa.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 9fcf2d195830..fc7b0505bdd8 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -896,10 +896,19 @@ static void __init find_possible_nodes(void)
 	if (!rtas)
 		return;
 
-	if (of_property_read_u32_index(rtas,
-				"ibm,max-associativity-domains",
+	if (of_property_read_u32_index(rtas, "ibm,current-associativity-domains",
+				min_common_depth, &numnodes)) {
+		/*
+		 * ibm,current-associativity-domains is a fairly recent
+		 * property. If it doesn't exist, then fallback on
+		 * ibm,max-associativity-domains. Current denotes what the
+		 * platform can support compared to max which denotes what the
+		 * Hypervisor can support.
+		 */
+		if (of_property_read_u32_index(rtas, "ibm,max-associativity-domains",
 				min_common_depth, &numnodes))
-		goto out;
+			goto out;
+	}
 
 	for (i = 0; i < numnodes; i++) {
 		if (!node_possible(i))
-- 
2.18.2


^ permalink raw reply related

* [PATCH] powerpc/fixmap: Fix the size of the early debug area
From: Christophe Leroy @ 2020-08-17  6:03 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
  Cc: linuxppc-dev, linux-kernel

Commit ("03fd42d458fb powerpc/fixmap: Fix FIX_EARLY_DEBUG_BASE when
page size is 256k") reworked the setup of the early debug area and
mistakenly replaced 128 * 1024 by SZ_128.

Change to SZ_128K to restore the original 128 kbytes size of the area.

Fixes: 03fd42d458fb ("powerpc/fixmap: Fix FIX_EARLY_DEBUG_BASE when page size is 256k")
Cc: stable@vger.kernel.org
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/include/asm/fixmap.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h
index 925cf89cbf4b..6bfc87915d5d 100644
--- a/arch/powerpc/include/asm/fixmap.h
+++ b/arch/powerpc/include/asm/fixmap.h
@@ -52,7 +52,7 @@ enum fixed_addresses {
 	FIX_HOLE,
 	/* reserve the top 128K for early debugging purposes */
 	FIX_EARLY_DEBUG_TOP = FIX_HOLE,
-	FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128, PAGE_SIZE)/PAGE_SIZE)-1,
+	FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128K, PAGE_SIZE)/PAGE_SIZE)-1,
 #ifdef CONFIG_HIGHMEM
 	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
 	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
-- 
2.25.0


^ permalink raw reply related

* [PATCH 05/11] test_bitmap: skip user bitmap tests for !CONFIG_SET_FS
From: Christoph Hellwig @ 2020-08-17  7:32 UTC (permalink / raw)
  To: Al Viro, Michael Ellerman, x86
  Cc: linux-fsdevel, linux-arch, linuxppc-dev, Kees Cook, linux-kernel
In-Reply-To: <20200817073212.830069-1-hch@lst.de>

We can't run the tests for userspace bitmap parsing if set_fs() doesn't
exist.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 lib/test_bitmap.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index df903c53952bb9..49b1d25fbaf546 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -365,6 +365,7 @@ static void __init __test_bitmap_parselist(int is_user)
 	for (i = 0; i < ARRAY_SIZE(parselist_tests); i++) {
 #define ptest parselist_tests[i]
 
+#ifdef CONFIG_SET_FS
 		if (is_user) {
 			mm_segment_t orig_fs = get_fs();
 			size_t len = strlen(ptest.in);
@@ -375,7 +376,9 @@ static void __init __test_bitmap_parselist(int is_user)
 						    bmap, ptest.nbits);
 			time = ktime_get() - time;
 			set_fs(orig_fs);
-		} else {
+		} else
+#endif /* CONFIG_SET_FS */
+		{
 			time = ktime_get();
 			err = bitmap_parselist(ptest.in, bmap, ptest.nbits);
 			time = ktime_get() - time;
@@ -454,6 +457,7 @@ static void __init __test_bitmap_parse(int is_user)
 	for (i = 0; i < ARRAY_SIZE(parse_tests); i++) {
 		struct test_bitmap_parselist test = parse_tests[i];
 
+#ifdef CONFIG_SET_FS
 		if (is_user) {
 			size_t len = strlen(test.in);
 			mm_segment_t orig_fs = get_fs();
@@ -464,7 +468,9 @@ static void __init __test_bitmap_parse(int is_user)
 						bmap, test.nbits);
 			time = ktime_get() - time;
 			set_fs(orig_fs);
-		} else {
+		} else
+#endif /* CONFIG_SET_FS */
+		{
 			size_t len = test.flags & NO_LEN ?
 				UINT_MAX : strlen(test.in);
 			time = ktime_get();
-- 
2.28.0


^ permalink raw reply related

* [PATCH 03/11] fs: don't allow splice read/write without explicit ops
From: Christoph Hellwig @ 2020-08-17  7:32 UTC (permalink / raw)
  To: Al Viro, Michael Ellerman, x86
  Cc: linux-fsdevel, linux-arch, linuxppc-dev, Kees Cook, linux-kernel
In-Reply-To: <20200817073212.830069-1-hch@lst.de>

default_file_splice_write is the last piece of generic code that uses
set_fs to make the uaccess routines operate on kernel pointers.  It
implements a "fallback loop" for splicing from files that do not actually
provide a proper splice_read method.  The usual file systems and other
high bandwith instances all provide a ->splice_read, so this just removes
support for various device drivers and procfs/debugfs files.  If splice
support for any of those turns out to be important it can be added back
by switching them to the iter ops and using generic_file_splice_read.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/read_write.c    |   2 +-
 fs/splice.c        | 130 +++++----------------------------------------
 include/linux/fs.h |   2 -
 3 files changed, 15 insertions(+), 119 deletions(-)

diff --git a/fs/read_write.c b/fs/read_write.c
index 702c4301d9eb6b..8c61f67453e3d3 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1077,7 +1077,7 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
 }
 EXPORT_SYMBOL(vfs_iter_write);
 
-ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
+static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
 		  unsigned long vlen, loff_t *pos, rwf_t flags)
 {
 	struct iovec iovstack[UIO_FASTIOV];
diff --git a/fs/splice.c b/fs/splice.c
index d7c8a7c4db07ff..412df7b48f9eb7 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -342,89 +342,6 @@ const struct pipe_buf_operations nosteal_pipe_buf_ops = {
 };
 EXPORT_SYMBOL(nosteal_pipe_buf_ops);
 
-static ssize_t kernel_readv(struct file *file, const struct kvec *vec,
-			    unsigned long vlen, loff_t offset)
-{
-	mm_segment_t old_fs;
-	loff_t pos = offset;
-	ssize_t res;
-
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	/* The cast to a user pointer is valid due to the set_fs() */
-	res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0);
-	set_fs(old_fs);
-
-	return res;
-}
-
-static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
-				 struct pipe_inode_info *pipe, size_t len,
-				 unsigned int flags)
-{
-	struct kvec *vec, __vec[PIPE_DEF_BUFFERS];
-	struct iov_iter to;
-	struct page **pages;
-	unsigned int nr_pages;
-	unsigned int mask;
-	size_t offset, base, copied = 0;
-	ssize_t res;
-	int i;
-
-	if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
-		return -EAGAIN;
-
-	/*
-	 * Try to keep page boundaries matching to source pagecache ones -
-	 * it probably won't be much help, but...
-	 */
-	offset = *ppos & ~PAGE_MASK;
-
-	iov_iter_pipe(&to, READ, pipe, len + offset);
-
-	res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &base);
-	if (res <= 0)
-		return -ENOMEM;
-
-	nr_pages = DIV_ROUND_UP(res + base, PAGE_SIZE);
-
-	vec = __vec;
-	if (nr_pages > PIPE_DEF_BUFFERS) {
-		vec = kmalloc_array(nr_pages, sizeof(struct kvec), GFP_KERNEL);
-		if (unlikely(!vec)) {
-			res = -ENOMEM;
-			goto out;
-		}
-	}
-
-	mask = pipe->ring_size - 1;
-	pipe->bufs[to.head & mask].offset = offset;
-	pipe->bufs[to.head & mask].len -= offset;
-
-	for (i = 0; i < nr_pages; i++) {
-		size_t this_len = min_t(size_t, len, PAGE_SIZE - offset);
-		vec[i].iov_base = page_address(pages[i]) + offset;
-		vec[i].iov_len = this_len;
-		len -= this_len;
-		offset = 0;
-	}
-
-	res = kernel_readv(in, vec, nr_pages, *ppos);
-	if (res > 0) {
-		copied = res;
-		*ppos += res;
-	}
-
-	if (vec != __vec)
-		kfree(vec);
-out:
-	for (i = 0; i < nr_pages; i++)
-		put_page(pages[i]);
-	kvfree(pages);
-	iov_iter_advance(&to, copied);	/* truncates and discards */
-	return res;
-}
-
 /*
  * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
  * using sendpage(). Return the number of bytes sent.
@@ -788,33 +705,6 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 
 EXPORT_SYMBOL(iter_file_splice_write);
 
-static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
-			  struct splice_desc *sd)
-{
-	int ret;
-	void *data;
-	loff_t tmp = sd->pos;
-
-	data = kmap(buf->page);
-	ret = __kernel_write(sd->u.file, data + buf->offset, sd->len, &tmp);
-	kunmap(buf->page);
-
-	return ret;
-}
-
-static ssize_t default_file_splice_write(struct pipe_inode_info *pipe,
-					 struct file *out, loff_t *ppos,
-					 size_t len, unsigned int flags)
-{
-	ssize_t ret;
-
-	ret = splice_from_pipe(pipe, out, ppos, len, flags, write_pipe_buf);
-	if (ret > 0)
-		*ppos += ret;
-
-	return ret;
-}
-
 /**
  * generic_splice_sendpage - splice data from a pipe to a socket
  * @pipe:	pipe to splice from
@@ -836,15 +726,23 @@ ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out,
 
 EXPORT_SYMBOL(generic_splice_sendpage);
 
+static int warn_unsupported(struct file *file, const char *op)
+{
+	pr_debug_ratelimited(
+		"splice %s not supported for file %pD4 (pid: %d comm: %.20s)\n",
+		op, file, current->pid, current->comm);
+	return -EINVAL;
+}
+
 /*
  * Attempt to initiate a splice from pipe to file.
  */
 static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
 			   loff_t *ppos, size_t len, unsigned int flags)
 {
-	if (out->f_op->splice_write)
-		return out->f_op->splice_write(pipe, out, ppos, len, flags);
-	return default_file_splice_write(pipe, out, ppos, len, flags);
+	if (unlikely(!out->f_op->splice_write))
+		return warn_unsupported(out, "write");
+	return out->f_op->splice_write(pipe, out, ppos, len, flags);
 }
 
 /*
@@ -866,9 +764,9 @@ static long do_splice_to(struct file *in, loff_t *ppos,
 	if (unlikely(len > MAX_RW_COUNT))
 		len = MAX_RW_COUNT;
 
-	if (in->f_op->splice_read)
-		return in->f_op->splice_read(in, ppos, pipe, len, flags);
-	return default_file_splice_read(in, ppos, pipe, len, flags);
+	if (unlikely(!in->f_op->splice_read))
+		return warn_unsupported(in, "read");
+	return in->f_op->splice_read(in, ppos, pipe, len, flags);
 }
 
 /**
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e019ea2f1347e6..d33cc3e8ed410b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1894,8 +1894,6 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 
 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 *,
-		unsigned long, loff_t *, rwf_t);
 extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
 				   loff_t, size_t, unsigned int);
 extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
-- 
2.28.0


^ permalink raw reply related

* [PATCH 02/11] fs: don't allow kernel reads and writes without iter ops
From: Christoph Hellwig @ 2020-08-17  7:32 UTC (permalink / raw)
  To: Al Viro, Michael Ellerman, x86
  Cc: linux-fsdevel, linux-arch, linuxppc-dev, Kees Cook, linux-kernel
In-Reply-To: <20200817073212.830069-1-hch@lst.de>

Don't allow calling ->read or ->write with set_fs as a preparation for
killing off set_fs.  All the instances that we use kernel_read/write on
are using the iter ops already.

If a file has both the regular ->read/->write methods and the iter
variants those could have different semantics for messed up enough
drivers.  Also fails the kernel access to them in that case.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/read_write.c | 67 +++++++++++++++++++++++++++++++------------------
 1 file changed, 42 insertions(+), 25 deletions(-)

diff --git a/fs/read_write.c b/fs/read_write.c
index 5db58b8c78d0dd..702c4301d9eb6b 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -419,27 +419,41 @@ static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo
 	return ret;
 }
 
+static int warn_unsupported(struct file *file, const char *op)
+{
+	pr_warn_ratelimited(
+		"kernel %s not supported for file %pD4 (pid: %d comm: %.20s)\n",
+		op, file, current->pid, current->comm);
+	return -EINVAL;
+}
+
 ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
 {
-	mm_segment_t old_fs = get_fs();
+	struct kvec iov = {
+		.iov_base	= buf,
+		.iov_len	= min_t(size_t, count, MAX_RW_COUNT),
+	};
+	struct kiocb kiocb;
+	struct iov_iter iter;
 	ssize_t ret;
 
 	if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ)))
 		return -EINVAL;
 	if (!(file->f_mode & FMODE_CAN_READ))
 		return -EINVAL;
+	/*
+	 * Also fail if ->read_iter and ->read are both wired up as that
+	 * implies very convoluted semantics.
+	 */
+	if (unlikely(!file->f_op->read_iter || file->f_op->read))
+		return warn_unsupported(file, "read");
 
-	if (count > MAX_RW_COUNT)
-		count =  MAX_RW_COUNT;
-	set_fs(KERNEL_DS);
-	if (file->f_op->read)
-		ret = file->f_op->read(file, (void __user *)buf, count, pos);
-	else if (file->f_op->read_iter)
-		ret = new_sync_read(file, (void __user *)buf, count, pos);
-	else
-		ret = -EINVAL;
-	set_fs(old_fs);
+	init_sync_kiocb(&kiocb, file);
+	kiocb.ki_pos = *pos;
+	iov_iter_kvec(&iter, READ, &iov, 1, iov.iov_len);
+	ret = file->f_op->read_iter(&kiocb, &iter);
 	if (ret > 0) {
+		*pos = kiocb.ki_pos;
 		fsnotify_access(file);
 		add_rchar(current, ret);
 	}
@@ -510,28 +524,31 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t
 /* caller is responsible for file_start_write/file_end_write */
 ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos)
 {
-	mm_segment_t old_fs;
-	const char __user *p;
+	struct kvec iov = {
+		.iov_base	= (void *)buf,
+		.iov_len	= min_t(size_t, count, MAX_RW_COUNT),
+	};
+	struct kiocb kiocb;
+	struct iov_iter iter;
 	ssize_t ret;
 
 	if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE)))
 		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_WRITE))
 		return -EINVAL;
+	/*
+	 * Also fail if ->write_iter and ->write are both wired up as that
+	 * implies very convoluted semantics.
+	 */
+	if (unlikely(!file->f_op->write_iter || file->f_op->write))
+		return warn_unsupported(file, "write");
 
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	p = (__force const char __user *)buf;
-	if (count > MAX_RW_COUNT)
-		count =  MAX_RW_COUNT;
-	if (file->f_op->write)
-		ret = file->f_op->write(file, p, count, pos);
-	else if (file->f_op->write_iter)
-		ret = new_sync_write(file, p, count, pos);
-	else
-		ret = -EINVAL;
-	set_fs(old_fs);
+	init_sync_kiocb(&kiocb, file);
+	kiocb.ki_pos = *pos;
+	iov_iter_kvec(&iter, WRITE, &iov, 1, iov.iov_len);
+	ret = file->f_op->write_iter(&kiocb, &iter);
 	if (ret > 0) {
+		*pos = kiocb.ki_pos;
 		fsnotify_modify(file);
 		add_wchar(current, ret);
 	}
-- 
2.28.0


^ permalink raw reply related

* [PATCH 06/11] lkdtm: disable set_fs-based tests for !CONFIG_SET_FS
From: Christoph Hellwig @ 2020-08-17  7:32 UTC (permalink / raw)
  To: Al Viro, Michael Ellerman, x86
  Cc: linux-fsdevel, linux-arch, linuxppc-dev, Kees Cook, linux-kernel
In-Reply-To: <20200817073212.830069-1-hch@lst.de>

Once we can't manipulate the address limit, we also can't test what
happens when the manipulation is abused.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/misc/lkdtm/bugs.c     | 2 ++
 drivers/misc/lkdtm/core.c     | 4 ++++
 drivers/misc/lkdtm/usercopy.c | 2 ++
 3 files changed, 8 insertions(+)

diff --git a/drivers/misc/lkdtm/bugs.c b/drivers/misc/lkdtm/bugs.c
index 4dfbfd51bdf774..66f1800b1cb82d 100644
--- a/drivers/misc/lkdtm/bugs.c
+++ b/drivers/misc/lkdtm/bugs.c
@@ -312,6 +312,7 @@ void lkdtm_CORRUPT_LIST_DEL(void)
 		pr_err("list_del() corruption not detected!\n");
 }
 
+#ifdef CONFIG_SET_FS
 /* Test if unbalanced set_fs(KERNEL_DS)/set_fs(USER_DS) check exists. */
 void lkdtm_CORRUPT_USER_DS(void)
 {
@@ -321,6 +322,7 @@ void lkdtm_CORRUPT_USER_DS(void)
 	/* Make sure we do not keep running with a KERNEL_DS! */
 	force_sig(SIGKILL);
 }
+#endif
 
 /* Test that VMAP_STACK is actually allocating with a leading guard page */
 void lkdtm_STACK_GUARD_PAGE_LEADING(void)
diff --git a/drivers/misc/lkdtm/core.c b/drivers/misc/lkdtm/core.c
index a5e344df916632..aae08b33a7ee2a 100644
--- a/drivers/misc/lkdtm/core.c
+++ b/drivers/misc/lkdtm/core.c
@@ -112,7 +112,9 @@ static const struct crashtype crashtypes[] = {
 	CRASHTYPE(CORRUPT_STACK_STRONG),
 	CRASHTYPE(CORRUPT_LIST_ADD),
 	CRASHTYPE(CORRUPT_LIST_DEL),
+#ifdef CONFIG_SET_FS
 	CRASHTYPE(CORRUPT_USER_DS),
+#endif
 	CRASHTYPE(STACK_GUARD_PAGE_LEADING),
 	CRASHTYPE(STACK_GUARD_PAGE_TRAILING),
 	CRASHTYPE(UNSET_SMEP),
@@ -172,7 +174,9 @@ static const struct crashtype crashtypes[] = {
 	CRASHTYPE(USERCOPY_STACK_FRAME_FROM),
 	CRASHTYPE(USERCOPY_STACK_BEYOND),
 	CRASHTYPE(USERCOPY_KERNEL),
+#ifdef CONFIG_SET_FS
 	CRASHTYPE(USERCOPY_KERNEL_DS),
+#endif
 	CRASHTYPE(STACKLEAK_ERASING),
 	CRASHTYPE(CFI_FORWARD_PROTO),
 #ifdef CONFIG_X86_32
diff --git a/drivers/misc/lkdtm/usercopy.c b/drivers/misc/lkdtm/usercopy.c
index b833367a45d053..4b632fe79ab6bb 100644
--- a/drivers/misc/lkdtm/usercopy.c
+++ b/drivers/misc/lkdtm/usercopy.c
@@ -325,6 +325,7 @@ void lkdtm_USERCOPY_KERNEL(void)
 	vm_munmap(user_addr, PAGE_SIZE);
 }
 
+#ifdef CONFIG_SET_FS
 void lkdtm_USERCOPY_KERNEL_DS(void)
 {
 	char __user *user_ptr =
@@ -339,6 +340,7 @@ void lkdtm_USERCOPY_KERNEL_DS(void)
 		pr_err("copy_to_user() to noncanonical address succeeded!?\n");
 	set_fs(old_fs);
 }
+#endif
 
 void __init lkdtm_usercopy_init(void)
 {
-- 
2.28.0


^ permalink raw reply related

* [PATCH 04/11] uaccess: add infrastructure for kernel builds with set_fs()
From: Christoph Hellwig @ 2020-08-17  7:32 UTC (permalink / raw)
  To: Al Viro, Michael Ellerman, x86
  Cc: linux-fsdevel, linux-arch, linuxppc-dev, Kees Cook, linux-kernel
In-Reply-To: <20200817073212.830069-1-hch@lst.de>

Add a CONFIG_SET_FS option that is selected by architecturess that
implement set_fs, which is all of them initially.  If the option is not
set stubs for routines related to overriding the address space are
provided so that architectures can start to opt out of providing set_fs.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/Kconfig            |  3 +++
 arch/alpha/Kconfig      |  1 +
 arch/arc/Kconfig        |  1 +
 arch/arm/Kconfig        |  1 +
 arch/arm64/Kconfig      |  1 +
 arch/c6x/Kconfig        |  1 +
 arch/csky/Kconfig       |  1 +
 arch/h8300/Kconfig      |  1 +
 arch/hexagon/Kconfig    |  1 +
 arch/ia64/Kconfig       |  1 +
 arch/m68k/Kconfig       |  1 +
 arch/microblaze/Kconfig |  1 +
 arch/mips/Kconfig       |  1 +
 arch/nds32/Kconfig      |  1 +
 arch/nios2/Kconfig      |  1 +
 arch/openrisc/Kconfig   |  1 +
 arch/parisc/Kconfig     |  1 +
 arch/powerpc/Kconfig    |  1 +
 arch/riscv/Kconfig      |  1 +
 arch/s390/Kconfig       |  1 +
 arch/sh/Kconfig         |  1 +
 arch/sparc/Kconfig      |  1 +
 arch/um/Kconfig         |  1 +
 arch/x86/Kconfig        |  1 +
 arch/xtensa/Kconfig     |  1 +
 include/linux/uaccess.h | 18 ++++++++++++++++++
 26 files changed, 45 insertions(+)

diff --git a/arch/Kconfig b/arch/Kconfig
index af14a567b493fc..3fab619a6aa51a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -24,6 +24,9 @@ config KEXEC_ELF
 config HAVE_IMA_KEXEC
 	bool
 
+config SET_FS
+	bool
+
 config HOTPLUG_SMT
 	bool
 
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 9c5f06e8eb9bc0..d6e9fc7a7b19e2 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -39,6 +39,7 @@ config ALPHA
 	select OLD_SIGSUSPEND
 	select CPU_NO_EFFICIENT_FFS if !ALPHA_EV67
 	select MMU_GATHER_NO_RANGE
+	select SET_FS
 	help
 	  The Alpha is a 64-bit general-purpose processor designed and
 	  marketed by the Digital Equipment Corporation of blessed memory,
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index ba00c4e1e1c271..c49f5754a11e40 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -48,6 +48,7 @@ config ARC
 	select PCI_SYSCALL if PCI
 	select PERF_USE_VMALLOC if ARC_CACHE_VIPT_ALIASING
 	select HAVE_ARCH_JUMP_LABEL if ISA_ARCV2 && !CPU_ENDIAN_BE32
+	select SET_FS
 
 config ARCH_HAS_CACHE_LINE_SIZE
 	def_bool y
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index e00d94b1665876..87e1478a42dc4f 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -118,6 +118,7 @@ config ARM
 	select PCI_SYSCALL if PCI
 	select PERF_USE_VMALLOC
 	select RTC_LIB
+	select SET_FS
 	select SYS_SUPPORTS_APM_EMULATION
 	# Above selects are sorted alphabetically; please add new ones
 	# according to that.  Thanks.
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 6d232837cbeee8..fbd9e35bef096f 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -192,6 +192,7 @@ config ARM64
 	select PCI_SYSCALL if PCI
 	select POWER_RESET
 	select POWER_SUPPLY
+	select SET_FS
 	select SPARSE_IRQ
 	select SWIOTLB
 	select SYSCTL_EXCEPTION_TRACE
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index 6444ebfd06a665..48d66bf0465d68 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -22,6 +22,7 @@ config C6X
 	select GENERIC_CLOCKEVENTS
 	select MODULES_USE_ELF_RELA
 	select MMU_GATHER_NO_RANGE if MMU
+	select SET_FS
 
 config MMU
 	def_bool n
diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index 3d5afb5f568543..2836f6e76fdb2d 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -78,6 +78,7 @@ config CSKY
 	select PCI_DOMAINS_GENERIC if PCI
 	select PCI_SYSCALL if PCI
 	select PCI_MSI if PCI
+	select SET_FS
 
 config LOCKDEP_SUPPORT
 	def_bool y
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index d11666d538fea8..7945de067e9fcc 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -25,6 +25,7 @@ config H8300
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_HASH
 	select CPU_NO_EFFICIENT_FFS
+	select SET_FS
 	select UACCESS_MEMCPY
 
 config CPU_BIG_ENDIAN
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 667cfc511cf999..f2afabbadd430e 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -31,6 +31,7 @@ config HEXAGON
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select MODULES_USE_ELF_RELA
 	select GENERIC_CPU_DEVICES
+	select SET_FS
 	help
 	  Qualcomm Hexagon is a processor architecture designed for high
 	  performance and low power across a wide variety of applications.
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 5b4ec80bf5863a..22a6853840e235 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -56,6 +56,7 @@ config IA64
 	select NEED_DMA_MAP_STATE
 	select NEED_SG_DMA_LENGTH
 	select NUMA if !FLATMEM
+	select SET_FS
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 6f2f38d05772ab..dcf4ae8c9b215f 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -32,6 +32,7 @@ config M68K
 	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION
 	select MMU_GATHER_NO_RANGE if MMU
+	select SET_FS
 
 config CPU_BIG_ENDIAN
 	def_bool y
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index d262ac0c8714bd..7e3d4583abf3e6 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -46,6 +46,7 @@ config MICROBLAZE
 	select CPU_NO_EFFICIENT_FFS
 	select MMU_GATHER_NO_RANGE if MMU
 	select SPARSE_IRQ
+	select SET_FS
 
 # Endianness selection
 choice
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index c95fa3a2484cf0..fbc26391b588f8 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -87,6 +87,7 @@ config MIPS
 	select MODULES_USE_ELF_RELA if MODULES && 64BIT
 	select PERF_USE_VMALLOC
 	select RTC_LIB
+	select SET_FS
 	select SYSCTL_EXCEPTION_TRACE
 	select VIRT_TO_BUS
 
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index e30298e99e1bdf..e8e541fd2267d0 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -48,6 +48,7 @@ config NDS32
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
+	select SET_FS
 	help
 	  Andes(nds32) Linux support.
 
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index c6645141bb2a88..c7c6ba6bec9dfc 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -27,6 +27,7 @@ config NIOS2
 	select USB_ARCH_HAS_HCD if USB_SUPPORT
 	select CPU_NO_EFFICIENT_FFS
 	select MMU_GATHER_NO_RANGE if MMU
+	select SET_FS
 
 config GENERIC_CSUM
 	def_bool y
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 7e94fe37cb2fdf..6233c62931803f 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -39,6 +39,7 @@ config OPENRISC
 	select ARCH_WANT_FRAME_POINTERS
 	select GENERIC_IRQ_MULTI_HANDLER
 	select MMU_GATHER_NO_RANGE if MMU
+	select SET_FS
 
 config CPU_BIG_ENDIAN
 	def_bool y
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 3b0f53dd70bc9b..be70af482b5a9a 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -63,6 +63,7 @@ config PARISC
 	select HAVE_FTRACE_MCOUNT_RECORD if HAVE_DYNAMIC_FTRACE
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
+	select SET_FS
 
 	help
 	  The PA-RISC microprocessor is designed by Hewlett-Packard and used
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1f48bbfb3ce99d..3f09d6fdf89405 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -249,6 +249,7 @@ config PPC
 	select PCI_SYSCALL			if PCI
 	select PPC_DAWR				if PPC64
 	select RTC_LIB
+	select SET_FS
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 7b590552914664..6e05a94f808a5a 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -82,6 +82,7 @@ config RISCV
 	select PCI_MSI if PCI
 	select RISCV_INTC
 	select RISCV_TIMER
+	select SET_FS
 	select SPARSEMEM_STATIC if 32BIT
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 3d86e12e8e3c21..fd81385a7787cb 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -185,6 +185,7 @@ config S390
 	select OLD_SIGSUSPEND3
 	select PCI_DOMAINS		if PCI
 	select PCI_MSI			if PCI
+	select SET_FS
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index d20927128fce05..2bd1653f3b3fea 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -71,6 +71,7 @@ config SUPERH
 	select PERF_EVENTS
 	select PERF_USE_VMALLOC
 	select RTC_LIB
+	select SET_FS
 	select SPARSE_IRQ
 	help
 	  The SuperH is a RISC processor targeted for use in embedded systems
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index efeff2c896a544..3e0cf0319a278a 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -49,6 +49,7 @@ config SPARC
 	select LOCKDEP_SMALL if LOCKDEP
 	select NEED_DMA_MAP_STATE
 	select NEED_SG_DMA_LENGTH
+	select SET_FS
 
 config SPARC32
 	def_bool !64BIT
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index eb51fec759484a..3aefcd81566809 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -19,6 +19,7 @@ config UML
 	select GENERIC_CPU_DEVICES
 	select GENERIC_CLOCKEVENTS
 	select HAVE_GCC_PLUGINS
+	select SET_FS
 	select TTY # Needed for line.c
 
 config MMU
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7101ac64bb209d..f85c13355732fe 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -237,6 +237,7 @@ config X86
 	select HAVE_ARCH_KCSAN			if X86_64
 	select X86_FEATURE_NAMES		if PROC_FS
 	select PROC_PID_ARCH_STATUS		if PROC_FS
+	select SET_FS
 	imply IMA_SECURE_AND_OR_TRUSTED_BOOT    if EFI
 
 config INSTRUCTION_DECODER
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index e997e0119c0251..94bad4d66b4bde 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -41,6 +41,7 @@ config XTENSA
 	select IRQ_DOMAIN
 	select MODULES_USE_ELF_RELA
 	select PERF_USE_VMALLOC
+	select SET_FS
 	select VIRT_TO_BUS
 	help
 	  Xtensa processors are 32-bit RISC machines designed by Tensilica
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 94b28541165929..70073c802b48ed 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -8,6 +8,7 @@
 
 #include <asm/uaccess.h>
 
+#ifdef CONFIG_SET_FS
 /*
  * Force the uaccess routines to be wired up for actual userspace access,
  * overriding any possible set_fs(KERNEL_DS) still lingering around.  Undone
@@ -25,6 +26,23 @@ static inline void force_uaccess_end(mm_segment_t oldfs)
 {
 	set_fs(oldfs);
 }
+#else /* CONFIG_SET_FS */
+typedef struct {
+	/* empty dummy */
+} mm_segment_t;
+
+#define uaccess_kernel()		(false)
+#define user_addr_max()			(TASK_SIZE_MAX)
+
+static inline mm_segment_t force_uaccess_begin(void)
+{
+	return (mm_segment_t) { };
+}
+
+static inline void force_uaccess_end(mm_segment_t oldfs)
+{
+}
+#endif /* CONFIG_SET_FS */
 
 /*
  * Architectures should provide two primitives (raw_copy_{to,from}_user())
-- 
2.28.0


^ permalink raw reply related

* [PATCH 01/11] mem: remove duplicate ops for /dev/zero and /dev/null
From: Christoph Hellwig @ 2020-08-17  7:32 UTC (permalink / raw)
  To: Al Viro, Michael Ellerman, x86
  Cc: linux-fsdevel, linux-arch, linuxppc-dev, Kees Cook, linux-kernel
In-Reply-To: <20200817073212.830069-1-hch@lst.de>

There is no good reason to implement both the traditional ->read and
->write as well as the iter based ops.  So implement just the iter
based ones.

Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/char/mem.c | 16 ----------------
 1 file changed, 16 deletions(-)

diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 687d4af6945d36..14851f36787372 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -670,18 +670,6 @@ static ssize_t write_port(struct file *file, const char __user *buf,
 	return tmp-buf;
 }
 
-static ssize_t read_null(struct file *file, char __user *buf,
-			 size_t count, loff_t *ppos)
-{
-	return 0;
-}
-
-static ssize_t write_null(struct file *file, const char __user *buf,
-			  size_t count, loff_t *ppos)
-{
-	return count;
-}
-
 static ssize_t read_iter_null(struct kiocb *iocb, struct iov_iter *to)
 {
 	return 0;
@@ -872,7 +860,6 @@ static int open_port(struct inode *inode, struct file *filp)
 
 #define zero_lseek	null_lseek
 #define full_lseek      null_lseek
-#define write_zero	write_null
 #define write_iter_zero	write_iter_null
 #define open_mem	open_port
 #define open_kmem	open_mem
@@ -903,8 +890,6 @@ static const struct file_operations __maybe_unused kmem_fops = {
 
 static const struct file_operations null_fops = {
 	.llseek		= null_lseek,
-	.read		= read_null,
-	.write		= write_null,
 	.read_iter	= read_iter_null,
 	.write_iter	= write_iter_null,
 	.splice_write	= splice_write_null,
@@ -919,7 +904,6 @@ static const struct file_operations __maybe_unused port_fops = {
 
 static const struct file_operations zero_fops = {
 	.llseek		= zero_lseek,
-	.write		= write_zero,
 	.read_iter	= read_iter_zero,
 	.write_iter	= write_iter_zero,
 	.mmap		= mmap_zero,
-- 
2.28.0


^ permalink raw reply related

* [PATCH 07/11] x86: move PAGE_OFFSET, TASK_SIZE & friends to page_{32, 64}_types.h
From: Christoph Hellwig @ 2020-08-17  7:32 UTC (permalink / raw)
  To: Al Viro, Michael Ellerman, x86
  Cc: linux-fsdevel, linux-arch, linuxppc-dev, Kees Cook, linux-kernel
In-Reply-To: <20200817073212.830069-1-hch@lst.de>

At least for 64-bit this moves them closer to some of the defines
they are based on, and it prepares for using the TASK_SIZE_MAX
definition from assembly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/x86/include/asm/page_32_types.h | 11 +++++++
 arch/x86/include/asm/page_64_types.h | 38 +++++++++++++++++++++
 arch/x86/include/asm/processor.h     | 49 ----------------------------
 3 files changed, 49 insertions(+), 49 deletions(-)

diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index 565ad755c785e2..26236925fb2c36 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -41,6 +41,17 @@
 #define __VIRTUAL_MASK_SHIFT	32
 #endif	/* CONFIG_X86_PAE */
 
+/*
+ * User space process size: 3GB (default).
+ */
+#define IA32_PAGE_OFFSET	PAGE_OFFSET
+#define TASK_SIZE		PAGE_OFFSET
+#define TASK_SIZE_LOW		TASK_SIZE
+#define TASK_SIZE_MAX		TASK_SIZE
+#define DEFAULT_MAP_WINDOW	TASK_SIZE
+#define STACK_TOP		TASK_SIZE
+#define STACK_TOP_MAX		STACK_TOP
+
 /*
  * Kernel image size is limited to 512 MB (see in arch/x86/kernel/head_32.S)
  */
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 288b065955b729..996595c9897e0a 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -58,6 +58,44 @@
 #define __VIRTUAL_MASK_SHIFT	47
 #endif
 
+/*
+ * User space process size.  This is the first address outside the user range.
+ * There are a few constraints that determine this:
+ *
+ * On Intel CPUs, if a SYSCALL instruction is at the highest canonical
+ * address, then that syscall will enter the kernel with a
+ * non-canonical return address, and SYSRET will explode dangerously.
+ * We avoid this particular problem by preventing anything executable
+ * from being mapped at the maximum canonical address.
+ *
+ * On AMD CPUs in the Ryzen family, there's a nasty bug in which the
+ * CPUs malfunction if they execute code from the highest canonical page.
+ * They'll speculate right off the end of the canonical space, and
+ * bad things happen.  This is worked around in the same way as the
+ * Intel problem.
+ *
+ * With page table isolation enabled, we map the LDT in ... [stay tuned]
+ */
+#define TASK_SIZE_MAX	((1UL << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE)
+
+#define DEFAULT_MAP_WINDOW	((1UL << 47) - PAGE_SIZE)
+
+/* This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define IA32_PAGE_OFFSET	((current->personality & ADDR_LIMIT_3GB) ? \
+					0xc0000000 : 0xFFFFe000)
+
+#define TASK_SIZE_LOW		(test_thread_flag(TIF_ADDR32) ? \
+					IA32_PAGE_OFFSET : DEFAULT_MAP_WINDOW)
+#define TASK_SIZE		(test_thread_flag(TIF_ADDR32) ? \
+					IA32_PAGE_OFFSET : TASK_SIZE_MAX)
+#define TASK_SIZE_OF(child)	((test_tsk_thread_flag(child, TIF_ADDR32)) ? \
+					IA32_PAGE_OFFSET : TASK_SIZE_MAX)
+
+#define STACK_TOP		TASK_SIZE_LOW
+#define STACK_TOP_MAX		TASK_SIZE_MAX
+
 /*
  * Maximum kernel image size is limited to 1 GiB, due to the fixmap living
  * in the next 1 GiB (see level2_kernel_pgt in arch/x86/kernel/head_64.S).
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 97143d87994c24..1618eeb08361a9 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -782,17 +782,6 @@ static inline void spin_lock_prefetch(const void *x)
 })
 
 #ifdef CONFIG_X86_32
-/*
- * User space process size: 3GB (default).
- */
-#define IA32_PAGE_OFFSET	PAGE_OFFSET
-#define TASK_SIZE		PAGE_OFFSET
-#define TASK_SIZE_LOW		TASK_SIZE
-#define TASK_SIZE_MAX		TASK_SIZE
-#define DEFAULT_MAP_WINDOW	TASK_SIZE
-#define STACK_TOP		TASK_SIZE
-#define STACK_TOP_MAX		STACK_TOP
-
 #define INIT_THREAD  {							  \
 	.sp0			= TOP_OF_INIT_STACK,			  \
 	.sysenter_cs		= __KERNEL_CS,				  \
@@ -802,44 +791,6 @@ static inline void spin_lock_prefetch(const void *x)
 #define KSTK_ESP(task)		(task_pt_regs(task)->sp)
 
 #else
-/*
- * User space process size.  This is the first address outside the user range.
- * There are a few constraints that determine this:
- *
- * On Intel CPUs, if a SYSCALL instruction is at the highest canonical
- * address, then that syscall will enter the kernel with a
- * non-canonical return address, and SYSRET will explode dangerously.
- * We avoid this particular problem by preventing anything executable
- * from being mapped at the maximum canonical address.
- *
- * On AMD CPUs in the Ryzen family, there's a nasty bug in which the
- * CPUs malfunction if they execute code from the highest canonical page.
- * They'll speculate right off the end of the canonical space, and
- * bad things happen.  This is worked around in the same way as the
- * Intel problem.
- *
- * With page table isolation enabled, we map the LDT in ... [stay tuned]
- */
-#define TASK_SIZE_MAX	((1UL << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE)
-
-#define DEFAULT_MAP_WINDOW	((1UL << 47) - PAGE_SIZE)
-
-/* This decides where the kernel will search for a free chunk of vm
- * space during mmap's.
- */
-#define IA32_PAGE_OFFSET	((current->personality & ADDR_LIMIT_3GB) ? \
-					0xc0000000 : 0xFFFFe000)
-
-#define TASK_SIZE_LOW		(test_thread_flag(TIF_ADDR32) ? \
-					IA32_PAGE_OFFSET : DEFAULT_MAP_WINDOW)
-#define TASK_SIZE		(test_thread_flag(TIF_ADDR32) ? \
-					IA32_PAGE_OFFSET : TASK_SIZE_MAX)
-#define TASK_SIZE_OF(child)	((test_tsk_thread_flag(child, TIF_ADDR32)) ? \
-					IA32_PAGE_OFFSET : TASK_SIZE_MAX)
-
-#define STACK_TOP		TASK_SIZE_LOW
-#define STACK_TOP_MAX		TASK_SIZE_MAX
-
 #define INIT_THREAD  {						\
 	.addr_limit		= KERNEL_DS,			\
 }
-- 
2.28.0


^ permalink raw reply related

* remove the last set_fs() in common code, and remove it for x86 and powerpc
From: Christoph Hellwig @ 2020-08-17  7:32 UTC (permalink / raw)
  To: Al Viro, Michael Ellerman, x86
  Cc: linux-fsdevel, linux-arch, linuxppc-dev, Kees Cook, linux-kernel

Hi all,

this series removes the last set_fs() used to force a kernel address
space for the uaccess code in the kernel read/write/splice code, and then
stops implementing the address space overrides entirely for x86 and
powerpc.

The file system part has been posted a few times, and the read/write side
has been pretty much unchanced.  For splice this series drops the
conversion of the seq_file and sysctl code to the iter ops, and thus loses
the splice support for them.  The reasons for that is that it caused a lot
of churn for not much use - splice for these small files really isn't much
of a win, even if existing userspace uses it.  All callers I found do the
proper fallback, but if this turns out to be an issue the conversion can
be resurrected.

Besides x86 and powerpc I plan to eventually convert all other
architectures, although this will be a slow process, starting with the
easier ones once the infrastructure is merged.  The process to convert
architectures is roughtly:

 - ensure there is no set_fs(KERNEL_DS) left in arch specific code
 - implement __get_kernel_nofault and __put_kernel_nofault
 - remove the arch specific address limitation functionality

Diffstat:
 arch/Kconfig                           |    3 
 arch/alpha/Kconfig                     |    1 
 arch/arc/Kconfig                       |    1 
 arch/arm/Kconfig                       |    1 
 arch/arm64/Kconfig                     |    1 
 arch/c6x/Kconfig                       |    1 
 arch/csky/Kconfig                      |    1 
 arch/h8300/Kconfig                     |    1 
 arch/hexagon/Kconfig                   |    1 
 arch/ia64/Kconfig                      |    1 
 arch/m68k/Kconfig                      |    1 
 arch/microblaze/Kconfig                |    1 
 arch/mips/Kconfig                      |    1 
 arch/nds32/Kconfig                     |    1 
 arch/nios2/Kconfig                     |    1 
 arch/openrisc/Kconfig                  |    1 
 arch/parisc/Kconfig                    |    1 
 arch/powerpc/include/asm/processor.h   |    7 -
 arch/powerpc/include/asm/thread_info.h |    5 -
 arch/powerpc/include/asm/uaccess.h     |   78 ++++++++-----------
 arch/powerpc/kernel/signal.c           |    3 
 arch/powerpc/lib/sstep.c               |    6 -
 arch/riscv/Kconfig                     |    1 
 arch/s390/Kconfig                      |    1 
 arch/sh/Kconfig                        |    1 
 arch/sparc/Kconfig                     |    1 
 arch/um/Kconfig                        |    1 
 arch/x86/ia32/ia32_aout.c              |    1 
 arch/x86/include/asm/page_32_types.h   |   11 ++
 arch/x86/include/asm/page_64_types.h   |   38 +++++++++
 arch/x86/include/asm/processor.h       |   60 ---------------
 arch/x86/include/asm/thread_info.h     |    2 
 arch/x86/include/asm/uaccess.h         |   26 ------
 arch/x86/kernel/asm-offsets.c          |    3 
 arch/x86/lib/getuser.S                 |   28 ++++---
 arch/x86/lib/putuser.S                 |   21 +++--
 arch/xtensa/Kconfig                    |    1 
 drivers/char/mem.c                     |   16 ----
 drivers/misc/lkdtm/bugs.c              |    2 
 drivers/misc/lkdtm/core.c              |    4 +
 drivers/misc/lkdtm/usercopy.c          |    2 
 fs/read_write.c                        |   69 ++++++++++-------
 fs/splice.c                            |  130 +++------------------------------
 include/linux/fs.h                     |    2 
 include/linux/uaccess.h                |   18 ++++
 lib/test_bitmap.c                      |   10 ++
 46 files changed, 235 insertions(+), 332 deletions(-)

^ permalink raw reply


This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox