Re: [PATCH v7 06/28] powerpc: Use a macro for creating instructions from u32s
I haven't reviewed our existing code to figure out if we've caught all places a
unsigned int is used as an instruction, but what's here looks correct and I
assume any missed cases will likely get caught by the compiler when the
datatype is actually introduced. At least past experience trying to build this
series suggests that assumption is reasonably accurate :-)
Michael - this requires a minor fix up when merged on top of Ravi's 2nd DAWR
series, let me know if you need it.
Reviewed-by: Alistair Popple
On Friday, 1 May 2020 1:41:58 PM AEST Jordan Niethe wrote:
> In preparation for instructions having a more complex data type start
> using a macro, ppc_inst(), for making an instruction out of a u32. A
> macro is used so that instructions can be used as initializer elements.
> Currently this does nothing, but it will allow for creating a data type
> that can represent prefixed instructions.
>
> Signed-off-by: Jordan Niethe
> ---
> v4: New to series
> v5: - Rename PPC_INST() -> ppc_inst().
> - Use on epapr_paravirt.c, kgdb.c
> v6: - Use in setup_32.c
> - epapr_paravirt.c: early_init_dt_scan_epapr(): move the use of
> ppc_inst() earlier.
> ---
> arch/powerpc/include/asm/code-patching.h | 3 +-
> arch/powerpc/include/asm/inst.h | 11 +
> arch/powerpc/kernel/align.c | 1 +
> arch/powerpc/kernel/epapr_paravirt.c | 3 +-
> arch/powerpc/kernel/hw_breakpoint.c | 3 +-
> arch/powerpc/kernel/jump_label.c | 3 +-
> arch/powerpc/kernel/kgdb.c | 5 ++-
> arch/powerpc/kernel/kprobes.c| 5 ++-
> arch/powerpc/kernel/module_64.c | 3 +-
> arch/powerpc/kernel/optprobes.c | 31 ++---
> arch/powerpc/kernel/security.c | 9 ++--
> arch/powerpc/kernel/setup_32.c | 2 +-
> arch/powerpc/kernel/trace/ftrace.c | 25 ++-
> arch/powerpc/kernel/uprobes.c| 1 +
> arch/powerpc/kvm/emulate_loadstore.c | 2 +-
> arch/powerpc/lib/code-patching.c | 57
> arch/powerpc/lib/feature-fixups.c| 39
> arch/powerpc/lib/test_emulate_step.c | 39
> arch/powerpc/xmon/xmon.c | 7 +--
> 19 files changed, 138 insertions(+), 111 deletions(-)
> create mode 100644 arch/powerpc/include/asm/inst.h
>
> diff --git a/arch/powerpc/include/asm/code-patching.h
> b/arch/powerpc/include/asm/code-patching.h index 351dda7215b6..48e021957ee5
> 100644
> --- a/arch/powerpc/include/asm/code-patching.h
> +++ b/arch/powerpc/include/asm/code-patching.h
> @@ -11,6 +11,7 @@
> #include
> #include
> #include
> +#include
>
> /* Flags for create_branch:
> * "b" == create_branch(addr, target, 0);
> @@ -48,7 +49,7 @@ static inline int patch_branch_site(s32 *site, unsigned
> long target, int flags) static inline int modify_instruction(unsigned int
> *addr, unsigned int clr, unsigned int set)
> {
> - return patch_instruction(addr, (*addr & ~clr) | set);
> + return patch_instruction(addr, ppc_inst((*addr & ~clr) | set));
> }
>
> static inline int modify_instruction_site(s32 *site, unsigned int clr,
> unsigned int set) diff --git a/arch/powerpc/include/asm/inst.h
> b/arch/powerpc/include/asm/inst.h new file mode 100644
> index ..5298ba33b6e5
> --- /dev/null
> +++ b/arch/powerpc/include/asm/inst.h
> @@ -0,0 +1,11 @@
> +/* SPDX-License-Identifier: GPL-2.0-or-later */
> +#ifndef _ASM_INST_H
> +#define _ASM_INST_H
> +
> +/*
> + * Instruction data type for POWER
> + */
> +
> +#define ppc_inst(x) (x)
> +
> +#endif /* _ASM_INST_H */
> diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
> index 92045ed64976..86e9bf62f18c 100644
> --- a/arch/powerpc/kernel/align.c
> +++ b/arch/powerpc/kernel/align.c
> @@ -24,6 +24,7 @@
> #include
> #include
> #include
> +#include
>
> struct aligninfo {
> unsigned char len;
> diff --git a/arch/powerpc/kernel/epapr_paravirt.c
> b/arch/powerpc/kernel/epapr_paravirt.c index 9d32158ce36f..e8eb72a65572
> 100644
> --- a/arch/powerpc/kernel/epapr_paravirt.c
> +++ b/arch/powerpc/kernel/epapr_paravirt.c
> @@ -11,6 +11,7 @@
> #include
> #include
> #include
> +#include
>
> #if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
> extern void epapr_ev_idle(void);
> @@ -36,7 +37,7 @@ static int __init early_init_dt_scan_epapr(unsigned long
> node, return -1;
>
> for (i = 0; i < (len / 4); i++) {
> - u32 inst = be32_to_cpu(insts[i]);
> + u32 inst = ppc_inst(be32_to_cpu(insts[i]));
> patch_instruction(epapr_hypercall_start + i, inst);
> #if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
> patch_instruction(epapr_ev_idle_start + i, inst);
> diff --git a/arch/powerpc/kernel/hw_breakpoint.c
> b/arch/powerpc/kernel/hw_breakpoint.c index 72f461bd70fb..46e09ac8b84a
> 100644
> --- a/arch/powerpc/kernel/hw_breakpoint.c
> +++
Re: [PATCH v7 02/28] powerpc/xmon: Move breakpoint instructions to own array
On Mon, May 4, 2020 at 3:41 PM Alistair Popple wrote:
>
> On Friday, 1 May 2020 1:41:54 PM AEST Jordan Niethe wrote:
> > To execute an instruction out of line after a breakpoint, the NIP is set
> > to the address of struct bpt::instr. Here a copy of the instruction that
> > was replaced with a breakpoint is kept, along with a trap so normal flow
> > can be resumed after XOLing. The struct bpt's are located within the
> > data section. This is problematic as the data section may be marked as
> > no execute.
> >
> > Instead of each struct bpt holding the instructions to be XOL'd, make a
> > new array, bpt_table[], with enough space to hold instructions for the
> > number of supported breakpoints. A later patch will move this to the
> > text section.
> > Make struct bpt::instr a pointer to the instructions in bpt_table[]
> > associated with that breakpoint. This association is a simple mapping:
> > bpts[n] -> bpt_table[n * words per breakpoint]. Currently we only need
> > the copied instruction followed by a trap, so 2 words per breakpoint.
> >
> > Signed-off-by: Jordan Niethe
> > ---
> > v4: New to series
> > v5: - Do not use __section(), use a .space directive in .S file
> > - Simplify in_breakpoint_table() calculation
> > - Define BPT_SIZE
> > v6: - Seperate moving to text section
> > ---
> > arch/powerpc/xmon/xmon.c | 21 -
> > 1 file changed, 12 insertions(+), 9 deletions(-)
> >
> > diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
> > index f91ae2c9adbe..6ba7f66c1dd0 100644
> > --- a/arch/powerpc/xmon/xmon.c
> > +++ b/arch/powerpc/xmon/xmon.c
> > @@ -98,7 +98,7 @@ static long *xmon_fault_jmp[NR_CPUS];
> > /* Breakpoint stuff */
> > struct bpt {
> > unsigned long address;
> > - unsigned intinstr[2];
> > + unsigned int*instr;
> > atomic_tref_count;
> > int enabled;
> > unsigned long pad;
> > @@ -117,6 +117,10 @@ static unsigned bpinstr = 0x7fe8;/* trap */
> >
> > #define BP_NUM(bp) ((bp) - bpts + 1)
> >
> > +#define BPT_SIZE (sizeof(unsigned int) * 2)
> > +#define BPT_WORDS (BPT_SIZE / sizeof(unsigned int))
>
> Minor nit-pick but IMHO this would be more logical if you defined BPT_WORDS
> first like so:
>
> #define BPT_WORDS (2)
> #define BPT_SIZE (sizeof(unsigned int) * BPT_WORDS)
>
> Otherwise this looks good and I think the offset calculations below are
> correct
> so:
What I was thinking was BPT_SIZE would later be defined in terms the
instruction type and by doing it this way
BPT_WORDS would be correct for the the instruction type if like on
ppc32, it did not include a suffix.
>
> Reviewed-by: Alistair Popple
>
> > +static unsigned int bpt_table[NBPTS * BPT_WORDS];
> > +
> > /* Prototypes */
> > static int cmds(struct pt_regs *);
> > static int mread(unsigned long, void *, int);
> > @@ -854,15 +858,13 @@ static struct bpt *in_breakpoint_table(unsigned long
> > nip, unsigned long *offp) {
> > unsigned long off;
> >
> > - off = nip - (unsigned long) bpts;
> > - if (off >= sizeof(bpts))
> > + off = nip - (unsigned long) bpt_table;
> > + if (off >= sizeof(bpt_table))
> > return NULL;
> > - off %= sizeof(struct bpt);
> > - if (off != offsetof(struct bpt, instr[0])
> > - && off != offsetof(struct bpt, instr[1]))
> > + *offp = off % BPT_SIZE;
> > + if (*offp != 0 && *offp != 4)
> > return NULL;
> > - *offp = off - offsetof(struct bpt, instr[0]);
> > - return (struct bpt *) (nip - off);
> > + return bpts + (off / BPT_SIZE);
> > }
> >
> > static struct bpt *new_breakpoint(unsigned long a)
> > @@ -877,7 +879,8 @@ static struct bpt *new_breakpoint(unsigned long a)
> > for (bp = bpts; bp < [NBPTS]; ++bp) {
> > if (!bp->enabled && atomic_read(>ref_count) == 0) {
> > bp->address = a;
> > - patch_instruction(>instr[1], bpinstr);
> > + bp->instr = bpt_table + ((bp - bpts) * BPT_WORDS);
> > + patch_instruction(bp->instr + 1, bpinstr);
> > return bp;
> > }
> > }
>
>
>
>
Re: [PATCH v7 04/28] powerpc/xmon: Use bitwise calculations in_breakpoint_table()
I probably would have just folded this change into patch 2 but it looks fine to me. Reviewed-by: Alistair Popple On Friday, 1 May 2020 1:41:56 PM AEST Jordan Niethe wrote: > A modulo operation is used for calculating the current offset from a > breakpoint within the breakpoint table. As instruction lengths are > always a power of 2, this can be replaced with a bitwise 'and'. The > current check for word alignment can be replaced with checking that the > lower 2 bits are not set. > > Suggested-by: Christophe Leroy > Signed-off-by: Jordan Niethe > --- > v6: New to series > --- > arch/powerpc/xmon/xmon.c | 4 ++-- > 1 file changed, 2 insertions(+), 2 deletions(-) > > diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c > index bbfea22f4a96..e122f0c8a044 100644 > --- a/arch/powerpc/xmon/xmon.c > +++ b/arch/powerpc/xmon/xmon.c > @@ -857,8 +857,8 @@ static struct bpt *in_breakpoint_table(unsigned long > nip, unsigned long *offp) off = nip - (unsigned long) bpt_table; > if (off >= sizeof(bpt_table)) > return NULL; > - *offp = off % BPT_SIZE; > - if (*offp != 0 && *offp != 4) > + *offp = off & (BPT_SIZE - 1); > + if (off & 3) > return NULL; > return bpts + (off / BPT_SIZE); > }
Re: [PATCH v7 02/28] powerpc/xmon: Move breakpoint instructions to own array
On Friday, 1 May 2020 1:41:54 PM AEST Jordan Niethe wrote:
> To execute an instruction out of line after a breakpoint, the NIP is set
> to the address of struct bpt::instr. Here a copy of the instruction that
> was replaced with a breakpoint is kept, along with a trap so normal flow
> can be resumed after XOLing. The struct bpt's are located within the
> data section. This is problematic as the data section may be marked as
> no execute.
>
> Instead of each struct bpt holding the instructions to be XOL'd, make a
> new array, bpt_table[], with enough space to hold instructions for the
> number of supported breakpoints. A later patch will move this to the
> text section.
> Make struct bpt::instr a pointer to the instructions in bpt_table[]
> associated with that breakpoint. This association is a simple mapping:
> bpts[n] -> bpt_table[n * words per breakpoint]. Currently we only need
> the copied instruction followed by a trap, so 2 words per breakpoint.
>
> Signed-off-by: Jordan Niethe
> ---
> v4: New to series
> v5: - Do not use __section(), use a .space directive in .S file
> - Simplify in_breakpoint_table() calculation
> - Define BPT_SIZE
> v6: - Seperate moving to text section
> ---
> arch/powerpc/xmon/xmon.c | 21 -
> 1 file changed, 12 insertions(+), 9 deletions(-)
>
> diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
> index f91ae2c9adbe..6ba7f66c1dd0 100644
> --- a/arch/powerpc/xmon/xmon.c
> +++ b/arch/powerpc/xmon/xmon.c
> @@ -98,7 +98,7 @@ static long *xmon_fault_jmp[NR_CPUS];
> /* Breakpoint stuff */
> struct bpt {
> unsigned long address;
> - unsigned intinstr[2];
> + unsigned int*instr;
> atomic_tref_count;
> int enabled;
> unsigned long pad;
> @@ -117,6 +117,10 @@ static unsigned bpinstr = 0x7fe8;/* trap */
>
> #define BP_NUM(bp) ((bp) - bpts + 1)
>
> +#define BPT_SIZE (sizeof(unsigned int) * 2)
> +#define BPT_WORDS (BPT_SIZE / sizeof(unsigned int))
Minor nit-pick but IMHO this would be more logical if you defined BPT_WORDS
first like so:
#define BPT_WORDS (2)
#define BPT_SIZE (sizeof(unsigned int) * BPT_WORDS)
Otherwise this looks good and I think the offset calculations below are correct
so:
Reviewed-by: Alistair Popple
> +static unsigned int bpt_table[NBPTS * BPT_WORDS];
> +
> /* Prototypes */
> static int cmds(struct pt_regs *);
> static int mread(unsigned long, void *, int);
> @@ -854,15 +858,13 @@ static struct bpt *in_breakpoint_table(unsigned long
> nip, unsigned long *offp) {
> unsigned long off;
>
> - off = nip - (unsigned long) bpts;
> - if (off >= sizeof(bpts))
> + off = nip - (unsigned long) bpt_table;
> + if (off >= sizeof(bpt_table))
> return NULL;
> - off %= sizeof(struct bpt);
> - if (off != offsetof(struct bpt, instr[0])
> - && off != offsetof(struct bpt, instr[1]))
> + *offp = off % BPT_SIZE;
> + if (*offp != 0 && *offp != 4)
> return NULL;
> - *offp = off - offsetof(struct bpt, instr[0]);
> - return (struct bpt *) (nip - off);
> + return bpts + (off / BPT_SIZE);
> }
>
> static struct bpt *new_breakpoint(unsigned long a)
> @@ -877,7 +879,8 @@ static struct bpt *new_breakpoint(unsigned long a)
> for (bp = bpts; bp < [NBPTS]; ++bp) {
> if (!bp->enabled && atomic_read(>ref_count) == 0) {
> bp->address = a;
> - patch_instruction(>instr[1], bpinstr);
> + bp->instr = bpt_table + ((bp - bpts) * BPT_WORDS);
> + patch_instruction(bp->instr + 1, bpinstr);
> return bp;
> }
> }
Re: [PATCH V2 00/11] Subject: Remove duplicated kmap code
On Sun, May 03, 2020 at 10:04:47PM -0700, Ira Weiny wrote:
> Grepping for 'asm/highmem.h' and investigations don't reveal any issues...
> But
> you do have me worried. That said 0-day has been crunching on multiple
> versions of this series without issues such as this (save the mips issue
> above).
>
> I have to say it would be nice if the relation between linux/highmem.h and
> asm/highmem.h was more straightforward.
IIRC, the headache was due to asm/pgtable.h on several architectures and
asm/cacheflush.h on parisc.
|| IOW, there's one in linux/highmem.h (conditional on !CONFIG_HIGHMEM,
|| !ARCH_HAS_KMAP) and several per-architecture variants, usually declared in
|| their asm/highmem.h. In three of those (microblaze, parisc and powerpc)
these
|| are inlines (parisc one identical to linux/highmem.h, lives in
asm/cacheflush.h,
|| powerpc and microblaze ones calling kmap_atomic_prot() which is defined in
|| arch/$ARCH/mm/highmem.c).
||
|| parisc case is weird - essentially, they want to call
|| flush_kernel_dcache_page_addr() at the places where kunmap/kunmap_atomic
|| is done. And they do so despite not selecting HIGHMEM, with definitions
|| in usual place. They do have ARCH_HAS_KMAP defined, which prevents
|| getting buggered in linux/highmem.h. ARCH_HAS_KMAP is parisc-unique,
|| BTW, and checked only in linux/highmem.h.
||
|| All genuine arch-specific variants are defined in (or call functions
|| defined in) translation units that are only included CONFIG_HIGHMEM builds.
||
|| It would be tempting to consolidate those, e.g. by adding
__kmap_atomic()
|| and __kmap_atomic_prot() without that boilerplate, with universal
kmap_atomic()
|| and kmap_atomic_prot() in linux/highmem.h. Potential problem with that would
|| be something that pulls ash/highmem.h (or asm/cacheflush.h in case of parisc)
|| directly and uses kmap_atomic/kmap_atomic_prot. There's not a lot places
|| pulling asm/highmem.h, and many of them are not even in includes:
||
|| arch/arm/include/asm/efi.h:13:#include
|| arch/arm/mm/dma-mapping.c:31:#include
|| arch/arm/mm/flush.c:14:#include
|| arch/arm/mm/mmu.c:27:#include
|| arch/mips/include/asm/pgtable-32.h:22:#include
|| arch/mips/mm/cache.c:19:#include
|| arch/mips/mm/fault.c:28:#include /* For
VMALLOC_END */
|| arch/nds32/include/asm/pgtable.h:60:#include
|| arch/x86/kernel/setup_percpu.c:20:#include
|| include/linux/highmem.h:35:#include
||
|| Users of asm/cacheflush.h are rather more numerous; however, anything
|| outside of parisc-specific code has to pull linux/highmem.h, or it won't see
|| the definitions of kmap_atomic/kmap_atomic_prot at all. arch/parisc itself
|| has no callers of those.
||
|| Outside of arch/* there is a plenty of callers. However, the following is
|| true: all instances of kmap_atomic or kmap_atomic_prot outside of arch/*
|| are either inside the linux/highmem.h or are preceded by include of
|| linux/highmem.h on any build that sees them (there is a common include
|| chain that is conditional upon CONFIG_BLOCK, but it's only needed in
|| drivers that are BLOCK-dependent). It was not fun to verify, to put
|| it mildly...
||
|| So for parisc we have no problem - leaving
__kmap_atomic()/__kmap_atomic_prot()
|| in asm/cachefile.h and adding universal wrappers in linux/highmem.h will be
|| fine. For other architectures the things might be trickier.
||
|| * arc: all users in arch/arc/ are within arch/arc/mm/{cache,highmem}.c;
|| both pull linux/highmem.h. We are fine.
||
|| * arm: much, much worse. We have several files that pull linux/highmem.h:
|| arch/arm/mm/cache-feroceon-l2.c, arch/arm/mm/cache-xsc3l2.c,
|| arch/arm/mm/copypage-*.c, arch/arm/mm/dma-mapping.c, arch/arm/mm/flush.c,
|| arch/arm/mm/highmem.c, arch/arm/probes/uprobes/core.c,
|| arch/arm/include/asm/kvm_mmu.h (kmap_atomic_pfn()).
|| Those are fine, but we also have this:
|| arch/arm/include/asm/pgtable.h:200:#define __pte_map(pmd)
(pte_t *)kmap_atomic(pmd_page(*(pmd)))
|| arch/arm/include/asm/pgtable.h:208:#define pte_offset_map(pmd,addr)
(__pte_map(pmd) + pte_index(addr))
|| and sure as hell, asm/pgtable.h does *NOT* pull linux/highmem.h.
||
|| Fortunately, the users of pte_offset_map() (__pte_map() has no other users)
|| are few, both in arch/arm and outside of arch. All arm ones are pulling
|| linux/highmem (arch/arm/mm/{pgd,fault*}.c). Outside of arch we have several
|| that pull highmem.h (by way of rmap.h or pagemap.h, usually):
|| fs/userfaultfd.c, mm/gup.c, mm/hmm.c, mm/huge_memory.c,
|| mm/khugepaged.c, mm/memory-failure.c, mm/memory.c, mm/migrate.c,
|| mm/mremap.c, mm/page_vma_mapped.c, mm/swap_state.c, mm/swapfile.c,
|| mm/vmalloc.c
|| and then there are these in linux/mm.h:
||
|| #define pte_offset_map_lock(mm, pmd, address, ptlp) \
|| ({ \
|| spinlock_t *__ptl = pte_lockptr(mm,
Re: [PATCH] powerpc/powernv: Fix a warning message
Hello Christophe,
On Sat, May 02, 2020 at 01:59:49PM +0200, Christophe JAILLET wrote:
> Fix a cut'n'paste error in a warning message. This should be
> 'cpu-idle-state-residency-ns' to match the property searched in the
> previous 'of_property_read_u32_array()'
>
> Fixes: 9c7b185ab2fe ("powernv/cpuidle: Parse dt idle properties into global
> structure")
> Signed-off-by: Christophe JAILLET
Thanks for catching this.
Reviewed-by: Gautham R. Shenoy
> ---
> arch/powerpc/platforms/powernv/idle.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/arch/powerpc/platforms/powernv/idle.c
> b/arch/powerpc/platforms/powernv/idle.c
> index 78599bca66c2..2dd467383a88 100644
> --- a/arch/powerpc/platforms/powernv/idle.c
> +++ b/arch/powerpc/platforms/powernv/idle.c
> @@ -1270,7 +1270,7 @@ static int pnv_parse_cpuidle_dt(void)
> /* Read residencies */
> if (of_property_read_u32_array(np, "ibm,cpu-idle-state-residency-ns",
> temp_u32, nr_idle_states)) {
> - pr_warn("cpuidle-powernv: missing
> ibm,cpu-idle-state-latencies-ns in DT\n");
> + pr_warn("cpuidle-powernv: missing
> ibm,cpu-idle-state-residency-ns in DT\n");
> rc = -EINVAL;
> goto out;
> }
> --
> 2.25.1
>
Re: [PATCH V2 00/11] Subject: Remove duplicated kmap code
On Mon, May 04, 2020 at 02:35:09AM +0100, Al Viro wrote: > On Sun, May 03, 2020 at 06:09:01PM -0700, ira.we...@intel.com wrote: > > From: Ira Weiny > > > > The kmap infrastructure has been copied almost verbatim to every > > architecture. > > This series consolidates obvious duplicated code by defining core functions > > which call into the architectures only when needed. > > > > Some of the k[un]map_atomic() implementations have some similarities but the > > similarities were not sufficient to warrant further changes. > > > > In addition we remove a duplicate implementation of kmap() in DRM. > > > > Testing was done by 0day to cover all the architectures I can't readily > > build/test. > > OK... Looking through my old notes on kmap unification (this winter, never > went anywhere), > > * arch/mips/mm/cache.c ought to use linux/highmem.h, not asm/highmem.h > I suspect that your series doesn't build on some configs there. Hadn't > verified that, though. Yes patch 6 makes the change because kmap_atomic() was no longer declared in asm/highmem.h. I'm pretty sure 0-day caught that ... but I seem to remember noticing some oddness in that file and I did go through it by hand. > > * kmap_atomic_to_page() is dead, but not quite gone - csky and nds32 brought > the damn thing back (nds32 - only an extern). It needs killin'... Easy enough. Added as a follow on patch. > > * parisc is (arguably) abusing kunmap()/kunmap_atomic() for cache flushing. > Replace the bulk of its highmem.h with > #define ARCH_HAS_FLUSH_ON_KUNMAP > #define arch_before_kunmap flush_kernel_dcache_page_addr > and have default kunmap()/kunmap_atomic() do > #ifdef ARCH_HAS_FLUSH_ON_KUNMAP > arch_before_kunmap(page_address(page)); > #endif > and > #ifdef ARCH_HAS_FLUSH_ON_KUNMAP > arch_before_kunmap(addr); > #endif > resp. Kills ARCH_HAS_KMAP along with ifdefs on it, makes parisc use somewhat > less hacky. Agreed. Done in a follow on patch. > > I'd suggest checking various configs on mips - that's likely to cause > headache. > Said that, my analysis of include chains back then is pretty much worthless > by now - I really hate the amount of indirect include chains leading to that > sucker on some, but not all configs ;-/ IIRC, the proof that everything > using kmap*/kunmap* would pull linux/highmem.h regardless of config took > several > hours of digging, ran for several pages and had been hopelessly brittle. > arch/mips/mm/cache.c was the only exception caught by it, but these days > there might be more. Grepping for 'asm/highmem.h' and investigations don't reveal any issues... But you do have me worried. That said 0-day has been crunching on multiple versions of this series without issues such as this (save the mips issue above). I have to say it would be nice if the relation between linux/highmem.h and asm/highmem.h was more straightforward. Ira
[PATCH V18 2/2] mm/debug: Add tests validating architecture page table helpers
This adds tests which will validate architecture page table helpers and other accessors in their compliance with expected generic MM semantics. This will help various architectures in validating changes to existing page table helpers or addition of new ones. This test covers basic page table entry transformations including but not limited to old, young, dirty, clean, write, write protect etc at various level along with populating intermediate entries with next page table page and validating them. Test page table pages are allocated from system memory with required size and alignments. The mapped pfns at page table levels are derived from a real pfn representing a valid kernel text symbol. This test gets called via late_initcall(). This test gets built and run when CONFIG_DEBUG_VM_PGTABLE is selected. Any architecture, which is willing to subscribe this test will need to select ARCH_HAS_DEBUG_VM_PGTABLE. For now this is limited to arc, arm64, x86, s390 and powerpc platforms where the test is known to build and run successfully Going forward, other architectures too can subscribe the test after fixing any build or runtime problems with their page table helpers. Folks interested in making sure that a given platform's page table helpers conform to expected generic MM semantics should enable the above config which will just trigger this test during boot. Any non conformity here will be reported as an warning which would need to be fixed. This test will help catch any changes to the agreed upon semantics expected from generic MM and enable platforms to accommodate it thereafter. Cc: Andrew Morton Cc: Mike Rapoport Cc: Vineet Gupta Cc: Catalin Marinas Cc: Will Deacon Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Kirill A. Shutemov Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: linux-snps-...@lists.infradead.org Cc: linux-arm-ker...@lists.infradead.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-s...@vger.kernel.org Cc: linux-ri...@lists.infradead.org Cc: x...@kernel.org Cc: linux-a...@vger.kernel.org Cc: linux-ker...@vger.kernel.org Suggested-by: Catalin Marinas Reviewed-by: Ingo Molnar Tested-by: Gerald Schaefer # s390 Tested-by: Christophe Leroy# ppc32 Signed-off-by: Qian Cai Signed-off-by: Andrew Morton Signed-off-by: Christophe Leroy Signed-off-by: Anshuman Khandual --- .../debug/debug-vm-pgtable/arch-support.txt | 34 ++ arch/arc/Kconfig | 1 + arch/arm64/Kconfig| 1 + arch/powerpc/Kconfig | 1 + arch/s390/Kconfig | 1 + arch/x86/Kconfig | 1 + lib/Kconfig.debug | 22 + mm/Makefile | 1 + mm/debug_vm_pgtable.c | 382 ++ 9 files changed, 444 insertions(+) create mode 100644 Documentation/features/debug/debug-vm-pgtable/arch-support.txt create mode 100644 mm/debug_vm_pgtable.c diff --git a/Documentation/features/debug/debug-vm-pgtable/arch-support.txt b/Documentation/features/debug/debug-vm-pgtable/arch-support.txt new file mode 100644 index ..c527d05c0459 --- /dev/null +++ b/Documentation/features/debug/debug-vm-pgtable/arch-support.txt @@ -0,0 +1,34 @@ +# +# Feature name: debug-vm-pgtable +# Kconfig: ARCH_HAS_DEBUG_VM_PGTABLE +# description: arch supports pgtable tests for semantics compliance +# +--- +| arch |status| +--- +| alpha: | TODO | +| arc: | ok | +| arm: | TODO | +| arm64: | ok | +| c6x: | TODO | +|csky: | TODO | +| h8300: | TODO | +| hexagon: | TODO | +|ia64: | TODO | +|m68k: | TODO | +| microblaze: | TODO | +|mips: | TODO | +| nds32: | TODO | +| nios2: | TODO | +|openrisc: | TODO | +| parisc: | TODO | +| powerpc: | ok | +| riscv: | TODO | +|s390: | ok | +| sh: | TODO | +| sparc: | TODO | +| um: | TODO | +| unicore32: | TODO | +| x86: | ok | +| xtensa: | TODO | +--- diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index ff306246d0f8..471ef22216c4 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -6,6 +6,7 @@ config ARC def_bool y select ARC_TIMERS + select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_DMA_PREP_COHERENT select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SETUP_DMA_OPS diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 40fb05d96c60..0efb46abaf3d 100644 --- a/arch/arm64/Kconfig +++
[PATCH V18 0/2] mm/debug: Add tests validating architecture page table helpers
This adds a test validation for architecture exported page table helpers. Patch adds basic transformation tests at various levels of the page table. This test was originally suggested by Catalin during arm64 THP migration RFC discussion earlier. Going forward it can include more specific tests with respect to various generic MM functions like THP, HugeTLB etc and platform specific tests. https://lore.kernel.org/linux-mm/20190628102003.ga56...@arrakis.emea.arm.com/ Needs to be applied on linux V5.7-rc4 Changes in V18: - Stopped enabling CONFIG_DEBUG_VM_PGTABLE via CONFIG_EXPERT - Dropped the exclude list (IA64 and ARM) as CONFIG_EXPERT route no longer available - Updated CONFIG_DEBUG_VM_PGTABLE's help section as required - Updated the commit message for [PATCH 2/2] as required Changes in V17: (https://patchwork.kernel.org/project/linux-mm/list/?series=274401) - debug_vm_pgtable() is now called from late_initcall() per Linus - Explicitly enable DEBUG_VM_PGTABLE when ARCH_HAS_DEBUG_VM_PGTABLE and DEBUG_VM - Added #ifdef documentation per Gerald - Dropped page table helper semantics documentation (will be added via later patches) - Split the X86 changes defining mm_p4d_folded() into a new prerequisite patch Changes in V16: (https://patchwork.kernel.org/patch/11431277/) - Replaced WRITE_ONCE() with set_pte_at() with a new barrier() in pte_clear_tests() per Qian - Enabled all powerpc platforms and updated the feature list Changes in V15: (https://patchwork.kernel.org/patch/11422803/) - Replaced __pa() with __pa_symbol() (https://patchwork.kernel.org/patch/11407715/) - Replaced pte_alloc_map() with pte_alloc_map_lock() per Qian - Replaced pte_unmap() with pte_unmap_unlock() per Qian - Added address to pte_clear_tests() and passed it down till pte_clear() per Qian Changes in V14: (https://patchwork.kernel.org/project/linux-mm/list/?series=242305) - Disabled DEBUG_VM_PGTABLE for IA64 and ARM (32 Bit) per Andrew and Christophe - Updated DEBUG_VM_PGTABLE documentation wrt EXPERT and disabled platforms - Updated RANDOM_[OR|NZ]VALUE open encodings with GENMASK() per Catalin - Updated s390 constraint bits from 12 to 4 (S390_MASK_BITS) per Gerald - Updated in-code documentation for RANDOM_ORVALUE per Gerald - Updated pxx_basic_tests() to use invert functions first per Catalin - Dropped ARCH_HAS_4LEVEL_HACK check from pud_basic_tests() - Replaced __ARCH_HAS_[4|5]LEVEL_HACK with __PAGETABLE_[PUD|P4D]_FOLDED per Catalin - Trimmed the CC list on the commit message per Catalin Changes in V13: (https://patchwork.kernel.org/project/linux-mm/list/?series=237125) - Subscribed s390 platform and updated debug-vm-pgtable/arch-support.txt per Gerald - Dropped keyword 'extern' from debug_vm_pgtable() declaration per Christophe - Moved debug_vm_pgtable() declarations to per Christophe - Moved debug_vm_pgtable() call site into kernel_init() per Christophe - Changed CONFIG_DEBUG_VM_PGTABLE rules per Christophe - Updated commit to include new supported platforms and changed config selection Changes in V12: (https://patchwork.kernel.org/project/linux-mm/list/?series=233905) - Replaced __mmdrop() with mmdrop() - Enable ARCH_HAS_DEBUG_VM_PGTABLE on X86 for non CONFIG_X86_PAE platforms as the test procedure interfere with pre-allocated PMDs attached to the PGD resulting in runtime failures with VM_BUG_ON() Changes in V11: (https://patchwork.kernel.org/project/linux-mm/list/?series=221135) - Rebased the patch on V5.4 Changes in V10: (https://patchwork.kernel.org/project/linux-mm/list/?series=205529) - Always enable DEBUG_VM_PGTABLE when DEBUG_VM is enabled per Ingo - Added tags from Ingo Changes in V9: (https://patchwork.kernel.org/project/linux-mm/list/?series=201429) - Changed feature support enumeration for powerpc platforms per Christophe - Changed config wrapper for basic_[pmd|pud]_tests() to enable ARC platform - Enabled the test on ARC platform Changes in V8: (https://patchwork.kernel.org/project/linux-mm/list/?series=194297) - Enabled ARCH_HAS_DEBUG_VM_PGTABLE on PPC32 platform per Christophe - Updated feature documentation as DEBUG_VM_PGTABLE is now enabled on PPC32 platform - Moved ARCH_HAS_DEBUG_VM_PGTABLE earlier to indent it with DEBUG_VM per Christophe - Added an information message in debug_vm_pgtable() per Christophe - Dropped random_vaddr boundary condition checks per Christophe and Qian - Replaced virt_addr_valid() check with pfn_valid() check in debug_vm_pgtable() - Slightly changed pr_fmt(fmt) information Changes in V7: (https://patchwork.kernel.org/project/linux-mm/list/?series=193051) - Memory allocation and free routines for mapped pages have been droped - Mapped pfns are derived from standard kernel text symbol per Matthew - Moved debug_vm_pgtaable() after page_alloc_init_late() per Michal and Qian - Updated the commit message per Michal - Updated W=1 GCC warning problem on x86 per Qian Cai - Addition of new alloc_contig_pages() helper has been submitted separately
Re: [PATCH v7 05/28] powerpc: Change calling convention for create_branch() et. al.
On Friday, 1 May 2020 1:41:57 PM AEST Jordan Niethe wrote:
> create_branch(), create_cond_branch() and translate_branch() return the
> instruction that they create, or return 0 to signal an error. Separate
> these concerns in preparation for an instruction type that is not just
> an unsigned int. Fill the created instruction to a pointer passed as
> the first parameter to the function and use a non-zero return value to
> signify an error.
We're not adding any new checks for error cases here, but this patch doesn't
change existing behaviour as far as I can tell and adding checks would be
difficult (and could introduce other bugs) so would be best done as a separate
series anyway if required at all.
> @@ -403,6 +407,7 @@ static void __init test_trampoline(void)
>
> static void __init test_branch_iform(void)
> {
> + int err;
> unsigned int instr;
> unsigned long addr;
>
> @@ -443,35 +448,35 @@ static void __init test_branch_iform(void)
> check(instr_is_branch_to_addr(, addr - 0x200));
>
> /* Branch to self, with link */
> - instr = create_branch(, addr, BRANCH_SET_LINK);
> + err = create_branch(, , addr, BRANCH_SET_LINK);
> check(instr_is_branch_to_addr(, addr));
The pointer alias above initially caught my eye, but it's ok because
create_branch() doesn't actually dereference the second instance. Arguably the
argument type could be changed to an unsigned long but then we'd just end up
with more casts so this is ok to me at least.
Reviewed-by: Alistair Popple
Re: [PATCH V2 00/11] Subject: Remove duplicated kmap code
On Sun, May 03, 2020 at 06:09:01PM -0700, ira.we...@intel.com wrote: > From: Ira Weiny > > The kmap infrastructure has been copied almost verbatim to every architecture. > This series consolidates obvious duplicated code by defining core functions > which call into the architectures only when needed. > > Some of the k[un]map_atomic() implementations have some similarities but the > similarities were not sufficient to warrant further changes. > > In addition we remove a duplicate implementation of kmap() in DRM. > > Testing was done by 0day to cover all the architectures I can't readily > build/test. OK... Looking through my old notes on kmap unification (this winter, never went anywhere), * arch/mips/mm/cache.c ought to use linux/highmem.h, not asm/highmem.h I suspect that your series doesn't build on some configs there. Hadn't verified that, though. * kmap_atomic_to_page() is dead, but not quite gone - csky and nds32 brought the damn thing back (nds32 - only an extern). It needs killin'... * parisc is (arguably) abusing kunmap()/kunmap_atomic() for cache flushing. Replace the bulk of its highmem.h with #define ARCH_HAS_FLUSH_ON_KUNMAP #define arch_before_kunmap flush_kernel_dcache_page_addr and have default kunmap()/kunmap_atomic() do #ifdef ARCH_HAS_FLUSH_ON_KUNMAP arch_before_kunmap(page_address(page)); #endif and #ifdef ARCH_HAS_FLUSH_ON_KUNMAP arch_before_kunmap(addr); #endif resp. Kills ARCH_HAS_KMAP along with ifdefs on it, makes parisc use somewhat less hacky. I'd suggest checking various configs on mips - that's likely to cause headache. Said that, my analysis of include chains back then is pretty much worthless by now - I really hate the amount of indirect include chains leading to that sucker on some, but not all configs ;-/ IIRC, the proof that everything using kmap*/kunmap* would pull linux/highmem.h regardless of config took several hours of digging, ran for several pages and had been hopelessly brittle. arch/mips/mm/cache.c was the only exception caught by it, but these days there might be more.
[PATCH V2 02/11] arch/xtensa: Move kmap build bug out of the way
From: Ira Weiny
Move the kmap() build bug to kmap_init() to facilitate patches to lift
kmap() to the core.
Reviewed-by: Christoph Hellwig
Signed-off-by: Ira Weiny
---
Changes from V1:
combine code onto 1 line.
---
arch/xtensa/include/asm/highmem.h | 5 -
arch/xtensa/mm/highmem.c | 4
2 files changed, 4 insertions(+), 5 deletions(-)
diff --git a/arch/xtensa/include/asm/highmem.h
b/arch/xtensa/include/asm/highmem.h
index 413848cc1e56..a9587c85be85 100644
--- a/arch/xtensa/include/asm/highmem.h
+++ b/arch/xtensa/include/asm/highmem.h
@@ -68,11 +68,6 @@ void kunmap_high(struct page *page);
static inline void *kmap(struct page *page)
{
- /* Check if this memory layout is broken because PKMAP overlaps
-* page table.
-*/
- BUILD_BUG_ON(PKMAP_BASE <
-TLBTEMP_BASE_1 + TLBTEMP_SIZE);
might_sleep();
if (!PageHighMem(page))
return page_address(page);
diff --git a/arch/xtensa/mm/highmem.c b/arch/xtensa/mm/highmem.c
index 184ceadccc1a..da734a2ed641 100644
--- a/arch/xtensa/mm/highmem.c
+++ b/arch/xtensa/mm/highmem.c
@@ -88,6 +88,10 @@ void __init kmap_init(void)
{
unsigned long kmap_vstart;
+ /* Check if this memory layout is broken because PKMAP overlaps
+* page table.
+*/
+ BUILD_BUG_ON(PKMAP_BASE < TLBTEMP_BASE_1 + TLBTEMP_SIZE);
/* cache the first kmap pte */
kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
kmap_pte = kmap_get_fixmap_pte(kmap_vstart);
--
2.25.1
[PATCH V2 09/11] arch/kmap: Don't hard code kmap_prot values
From: Ira Weiny To support kmap_atomic_prot() on all architectures each arch must support protections passed in to them. Change csky, mips, nds32 and xtensa to use their global constant kmap_prot rather than a hard coded value which was equal. Reviewed-by: Christoph Hellwig Signed-off-by: Ira Weiny --- changes from V1: Mention that kmap_prot is a constant in commit message --- arch/csky/mm/highmem.c | 2 +- arch/mips/mm/highmem.c | 2 +- arch/nds32/mm/highmem.c | 2 +- arch/xtensa/mm/highmem.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/csky/mm/highmem.c b/arch/csky/mm/highmem.c index 0aafbbbe651c..f4311669b5bb 100644 --- a/arch/csky/mm/highmem.c +++ b/arch/csky/mm/highmem.c @@ -32,7 +32,7 @@ void *kmap_atomic_high(struct page *page) #ifdef CONFIG_DEBUG_HIGHMEM BUG_ON(!pte_none(*(kmap_pte - idx))); #endif - set_pte(kmap_pte-idx, mk_pte(page, PAGE_KERNEL)); + set_pte(kmap_pte-idx, mk_pte(page, kmap_prot)); flush_tlb_one((unsigned long)vaddr); return (void *)vaddr; diff --git a/arch/mips/mm/highmem.c b/arch/mips/mm/highmem.c index 155fbb107b35..87023bd1a33c 100644 --- a/arch/mips/mm/highmem.c +++ b/arch/mips/mm/highmem.c @@ -29,7 +29,7 @@ void *kmap_atomic_high(struct page *page) #ifdef CONFIG_DEBUG_HIGHMEM BUG_ON(!pte_none(*(kmap_pte - idx))); #endif - set_pte(kmap_pte-idx, mk_pte(page, PAGE_KERNEL)); + set_pte(kmap_pte-idx, mk_pte(page, kmap_prot)); local_flush_tlb_one((unsigned long)vaddr); return (void*) vaddr; diff --git a/arch/nds32/mm/highmem.c b/arch/nds32/mm/highmem.c index f6e6915c0d31..809f8c830f06 100644 --- a/arch/nds32/mm/highmem.c +++ b/arch/nds32/mm/highmem.c @@ -21,7 +21,7 @@ void *kmap_atomic_high(struct page *page) idx = type + KM_TYPE_NR * smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); - pte = (page_to_pfn(page) << PAGE_SHIFT) | (PAGE_KERNEL); + pte = (page_to_pfn(page) << PAGE_SHIFT) | (kmap_prot); ptep = pte_offset_kernel(pmd_off_k(vaddr), vaddr); set_pte(ptep, pte); diff --git a/arch/xtensa/mm/highmem.c b/arch/xtensa/mm/highmem.c index 4de323e43682..50168b09510a 100644 --- a/arch/xtensa/mm/highmem.c +++ b/arch/xtensa/mm/highmem.c @@ -48,7 +48,7 @@ void *kmap_atomic_high(struct page *page) #ifdef CONFIG_DEBUG_HIGHMEM BUG_ON(!pte_none(*(kmap_pte + idx))); #endif - set_pte(kmap_pte + idx, mk_pte(page, PAGE_KERNEL_EXEC)); + set_pte(kmap_pte + idx, mk_pte(page, kmap_prot)); return (void *)vaddr; } -- 2.25.1
[PATCH V2 07/11] arch/kunmap_atomic: Consolidate duplicate code
From: Ira Weiny
Every single architecture (including !CONFIG_HIGHMEM) calls...
pagefault_enable();
preempt_enable();
... before returning from __kunmap_atomic(). Lift this code into the
kunmap_atomic() macro.
While we are at it rename __kunmap_atomic() to kunmap_atomic_high() to
be consistent.
Signed-off-by: Ira Weiny
---
Changes from V1:
Adjust to preserve bisect-ability
Remove uneeded kunmap_atomic_high() declarations
---
arch/arc/include/asm/highmem.h| 2 --
arch/arc/mm/highmem.c | 7 ++-
arch/arm/include/asm/highmem.h| 1 -
arch/arm/mm/highmem.c | 6 ++
arch/csky/include/asm/highmem.h | 1 -
arch/csky/mm/highmem.c| 9 +++--
arch/microblaze/include/asm/highmem.h | 1 -
arch/microblaze/mm/highmem.c | 6 ++
arch/mips/include/asm/highmem.h | 1 -
arch/mips/mm/cache.c | 4 ++--
arch/mips/mm/highmem.c| 6 ++
arch/nds32/include/asm/highmem.h | 1 -
arch/nds32/mm/highmem.c | 6 ++
arch/parisc/include/asm/cacheflush.h | 4 +---
arch/powerpc/include/asm/highmem.h| 1 -
arch/powerpc/mm/highmem.c | 6 ++
arch/sparc/include/asm/highmem.h | 2 --
arch/sparc/mm/highmem.c | 6 ++
arch/x86/include/asm/highmem.h| 1 -
arch/x86/mm/highmem_32.c | 7 ++-
arch/xtensa/include/asm/highmem.h | 2 --
arch/xtensa/mm/highmem.c | 7 ++-
include/linux/highmem.h | 11 +++
23 files changed, 31 insertions(+), 67 deletions(-)
diff --git a/arch/arc/include/asm/highmem.h b/arch/arc/include/asm/highmem.h
index db425cd38545..70900a73bfc8 100644
--- a/arch/arc/include/asm/highmem.h
+++ b/arch/arc/include/asm/highmem.h
@@ -30,8 +30,6 @@
#include
-extern void __kunmap_atomic(void *kvaddr);
-
extern void kmap_init(void);
static inline void flush_cache_kmaps(void)
diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c
index 0964b011c29f..5d3eab4ac0b0 100644
--- a/arch/arc/mm/highmem.c
+++ b/arch/arc/mm/highmem.c
@@ -65,7 +65,7 @@ void *kmap_atomic_high(struct page *page)
}
EXPORT_SYMBOL(kmap_atomic_high);
-void __kunmap_atomic(void *kv)
+void kunmap_atomic_high(void *kv)
{
unsigned long kvaddr = (unsigned long)kv;
@@ -87,11 +87,8 @@ void __kunmap_atomic(void *kv)
kmap_atomic_idx_pop();
}
-
- pagefault_enable();
- preempt_enable();
}
-EXPORT_SYMBOL(__kunmap_atomic);
+EXPORT_SYMBOL(kunmap_atomic_high);
static noinline pte_t * __init alloc_kmap_pgtable(unsigned long kvaddr)
{
diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h
index 8c80bfe18a34..b0d4bd8dc3c1 100644
--- a/arch/arm/include/asm/highmem.h
+++ b/arch/arm/include/asm/highmem.h
@@ -60,7 +60,6 @@ static inline void *kmap_high_get(struct page *page)
* when CONFIG_HIGHMEM is not set.
*/
#ifdef CONFIG_HIGHMEM
-extern void __kunmap_atomic(void *kvaddr);
extern void *kmap_atomic_pfn(unsigned long pfn);
#endif
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index 075fdc235091..ac8394655a6e 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -73,7 +73,7 @@ void *kmap_atomic_high(struct page *page)
}
EXPORT_SYMBOL(kmap_atomic_high);
-void __kunmap_atomic(void *kvaddr)
+void kunmap_atomic_high(void *kvaddr)
{
unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
int idx, type;
@@ -95,10 +95,8 @@ void __kunmap_atomic(void *kvaddr)
/* this address was obtained through kmap_high_get() */
kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)]));
}
- pagefault_enable();
- preempt_enable();
}
-EXPORT_SYMBOL(__kunmap_atomic);
+EXPORT_SYMBOL(kunmap_atomic_high);
void *kmap_atomic_pfn(unsigned long pfn)
{
diff --git a/arch/csky/include/asm/highmem.h b/arch/csky/include/asm/highmem.h
index 8ceee12f9bc1..263fbddcd0a3 100644
--- a/arch/csky/include/asm/highmem.h
+++ b/arch/csky/include/asm/highmem.h
@@ -32,7 +32,6 @@ extern pte_t *pkmap_page_table;
#define ARCH_HAS_KMAP_FLUSH_TLB
extern void kmap_flush_tlb(unsigned long addr);
-extern void __kunmap_atomic(void *kvaddr);
extern void *kmap_atomic_pfn(unsigned long pfn);
extern struct page *kmap_atomic_to_page(void *ptr);
diff --git a/arch/csky/mm/highmem.c b/arch/csky/mm/highmem.c
index 63d74b47eee6..0aafbbbe651c 100644
--- a/arch/csky/mm/highmem.c
+++ b/arch/csky/mm/highmem.c
@@ -39,13 +39,13 @@ void *kmap_atomic_high(struct page *page)
}
EXPORT_SYMBOL(kmap_atomic_high);
-void __kunmap_atomic(void *kvaddr)
+void kunmap_atomic_high(void *kvaddr)
{
unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
int idx;
if (vaddr < FIXADDR_START)
- goto out;
+ return;
#ifdef CONFIG_DEBUG_HIGHMEM
idx = KM_TYPE_NR*smp_processor_id() +
[PATCH V2 01/11] arch/kmap: Remove BUG_ON()
From: Ira Weiny
Replace the use of BUG_ON(in_interrupt()) in the kmap() and kunmap()
in favor of might_sleep().
Besides the benefits of might_sleep(), this normalizes the
implementations such that they can be made generic in subsequent
patches.
Reviewed-by: Dan Williams
Reviewed-by: Christoph Hellwig
Signed-off-by: Ira Weiny
---
arch/arc/include/asm/highmem.h| 2 +-
arch/arc/mm/highmem.c | 2 +-
arch/arm/mm/highmem.c | 2 +-
arch/csky/mm/highmem.c| 2 +-
arch/microblaze/include/asm/highmem.h | 2 +-
arch/mips/mm/highmem.c| 2 +-
arch/nds32/mm/highmem.c | 2 +-
arch/powerpc/include/asm/highmem.h| 2 +-
arch/sparc/include/asm/highmem.h | 4 ++--
arch/x86/mm/highmem_32.c | 3 +--
arch/xtensa/include/asm/highmem.h | 4 ++--
11 files changed, 13 insertions(+), 14 deletions(-)
diff --git a/arch/arc/include/asm/highmem.h b/arch/arc/include/asm/highmem.h
index 1af00accb37f..042e92921c4c 100644
--- a/arch/arc/include/asm/highmem.h
+++ b/arch/arc/include/asm/highmem.h
@@ -45,7 +45,7 @@ static inline void flush_cache_kmaps(void)
static inline void kunmap(struct page *page)
{
- BUG_ON(in_interrupt());
+ might_sleep();
if (!PageHighMem(page))
return;
kunmap_high(page);
diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c
index fc8849e4f72e..39ef7b9a3aa9 100644
--- a/arch/arc/mm/highmem.c
+++ b/arch/arc/mm/highmem.c
@@ -51,7 +51,7 @@ static pte_t * fixmap_page_table;
void *kmap(struct page *page)
{
- BUG_ON(in_interrupt());
+ might_sleep();
if (!PageHighMem(page))
return page_address(page);
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index a76f8ace9ce6..cc6eb79ef20c 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -42,7 +42,7 @@ EXPORT_SYMBOL(kmap);
void kunmap(struct page *page)
{
- BUG_ON(in_interrupt());
+ might_sleep();
if (!PageHighMem(page))
return;
kunmap_high(page);
diff --git a/arch/csky/mm/highmem.c b/arch/csky/mm/highmem.c
index 813129145f3d..690d678649d1 100644
--- a/arch/csky/mm/highmem.c
+++ b/arch/csky/mm/highmem.c
@@ -29,7 +29,7 @@ EXPORT_SYMBOL(kmap);
void kunmap(struct page *page)
{
- BUG_ON(in_interrupt());
+ might_sleep();
if (!PageHighMem(page))
return;
kunmap_high(page);
diff --git a/arch/microblaze/include/asm/highmem.h
b/arch/microblaze/include/asm/highmem.h
index 332c78e15198..99ced7278b5c 100644
--- a/arch/microblaze/include/asm/highmem.h
+++ b/arch/microblaze/include/asm/highmem.h
@@ -66,7 +66,7 @@ static inline void *kmap(struct page *page)
static inline void kunmap(struct page *page)
{
- BUG_ON(in_interrupt());
+ might_sleep();
if (!PageHighMem(page))
return;
kunmap_high(page);
diff --git a/arch/mips/mm/highmem.c b/arch/mips/mm/highmem.c
index d08e6d7d533b..edd889f6cede 100644
--- a/arch/mips/mm/highmem.c
+++ b/arch/mips/mm/highmem.c
@@ -28,7 +28,7 @@ EXPORT_SYMBOL(kmap);
void kunmap(struct page *page)
{
- BUG_ON(in_interrupt());
+ might_sleep();
if (!PageHighMem(page))
return;
kunmap_high(page);
diff --git a/arch/nds32/mm/highmem.c b/arch/nds32/mm/highmem.c
index 022779af6148..4c7c28e994ea 100644
--- a/arch/nds32/mm/highmem.c
+++ b/arch/nds32/mm/highmem.c
@@ -24,7 +24,7 @@ EXPORT_SYMBOL(kmap);
void kunmap(struct page *page)
{
- BUG_ON(in_interrupt());
+ might_sleep();
if (!PageHighMem(page))
return;
kunmap_high(page);
diff --git a/arch/powerpc/include/asm/highmem.h
b/arch/powerpc/include/asm/highmem.h
index a4b65b186ec6..529512f6d65a 100644
--- a/arch/powerpc/include/asm/highmem.h
+++ b/arch/powerpc/include/asm/highmem.h
@@ -74,7 +74,7 @@ static inline void *kmap(struct page *page)
static inline void kunmap(struct page *page)
{
- BUG_ON(in_interrupt());
+ might_sleep();
if (!PageHighMem(page))
return;
kunmap_high(page);
diff --git a/arch/sparc/include/asm/highmem.h b/arch/sparc/include/asm/highmem.h
index 18d776925c45..7dd2d4b3f980 100644
--- a/arch/sparc/include/asm/highmem.h
+++ b/arch/sparc/include/asm/highmem.h
@@ -55,7 +55,7 @@ void kunmap_high(struct page *page);
static inline void *kmap(struct page *page)
{
- BUG_ON(in_interrupt());
+ might_sleep();
if (!PageHighMem(page))
return page_address(page);
return kmap_high(page);
@@ -63,7 +63,7 @@ static inline void *kmap(struct page *page)
static inline void kunmap(struct page *page)
{
- BUG_ON(in_interrupt());
+ might_sleep();
if (!PageHighMem(page))
return;
kunmap_high(page);
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 0a1898b8552e..8af66382672b 100644
--- a/arch/x86/mm/highmem_32.c
+++
[PATCH V2 05/11] {x86,powerpc,microblaze}/kmap: Move preempt disable
From: Ira Weiny
During this kmap() conversion series we must maintain bisect-ability.
To do this, kmap_atomic_prot() in x86, powerpc, and microblaze need to
remain functional.
Create a temporary inline version of kmap_atomic_prot within these
architectures so we can rework their kmap_atomic() calls and then lift
kmap_atomic_prot() to the core.
Signed-off-by: Ira Weiny
---
Changes from V1:
New patch
---
arch/microblaze/include/asm/highmem.h | 11 ++-
arch/microblaze/mm/highmem.c | 10 ++
arch/powerpc/include/asm/highmem.h| 11 ++-
arch/powerpc/mm/highmem.c | 9 ++---
arch/x86/include/asm/highmem.h| 11 ++-
arch/x86/mm/highmem_32.c | 10 ++
6 files changed, 36 insertions(+), 26 deletions(-)
diff --git a/arch/microblaze/include/asm/highmem.h
b/arch/microblaze/include/asm/highmem.h
index 0c94046f2d58..ec9954b091e1 100644
--- a/arch/microblaze/include/asm/highmem.h
+++ b/arch/microblaze/include/asm/highmem.h
@@ -51,7 +51,16 @@ extern pte_t *pkmap_page_table;
#define PKMAP_NR(virt) ((virt - PKMAP_BASE) >> PAGE_SHIFT)
#define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT))
-extern void *kmap_atomic_prot(struct page *page, pgprot_t prot);
+extern void *kmap_atomic_high_prot(struct page *page, pgprot_t prot);
+void *kmap_atomic_prot(struct page *page, pgprot_t prot)
+{
+ preempt_disable();
+ pagefault_disable();
+ if (!PageHighMem(page))
+ return page_address(page);
+
+ return kmap_atomic_high_prot(page, prot);
+}
extern void __kunmap_atomic(void *kvaddr);
static inline void *kmap_atomic(struct page *page)
diff --git a/arch/microblaze/mm/highmem.c b/arch/microblaze/mm/highmem.c
index d7569f77fa15..0e3efaa8a004 100644
--- a/arch/microblaze/mm/highmem.c
+++ b/arch/microblaze/mm/highmem.c
@@ -32,18 +32,12 @@
*/
#include
-void *kmap_atomic_prot(struct page *page, pgprot_t prot)
+void *kmap_atomic_high_prot(struct page *page, pgprot_t prot)
{
unsigned long vaddr;
int idx, type;
- preempt_disable();
- pagefault_disable();
- if (!PageHighMem(page))
- return page_address(page);
-
-
type = kmap_atomic_idx_push();
idx = type + KM_TYPE_NR*smp_processor_id();
vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
@@ -55,7 +49,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
return (void *) vaddr;
}
-EXPORT_SYMBOL(kmap_atomic_prot);
+EXPORT_SYMBOL(kmap_atomic_high_prot);
void __kunmap_atomic(void *kvaddr)
{
diff --git a/arch/powerpc/include/asm/highmem.h
b/arch/powerpc/include/asm/highmem.h
index ba3371977d49..d049806a8354 100644
--- a/arch/powerpc/include/asm/highmem.h
+++ b/arch/powerpc/include/asm/highmem.h
@@ -59,7 +59,16 @@ extern pte_t *pkmap_page_table;
#define PKMAP_NR(virt) ((virt-PKMAP_BASE) >> PAGE_SHIFT)
#define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT))
-extern void *kmap_atomic_prot(struct page *page, pgprot_t prot);
+extern void *kmap_atomic_high_prot(struct page *page, pgprot_t prot);
+static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
+{
+ preempt_disable();
+ pagefault_disable();
+ if (!PageHighMem(page))
+ return page_address(page);
+
+ return kmap_atomic_high_prot(page, prot);
+}
extern void __kunmap_atomic(void *kvaddr);
static inline void *kmap_atomic(struct page *page)
diff --git a/arch/powerpc/mm/highmem.c b/arch/powerpc/mm/highmem.c
index 320c1672b2ae..f075cef6d663 100644
--- a/arch/powerpc/mm/highmem.c
+++ b/arch/powerpc/mm/highmem.c
@@ -30,16 +30,11 @@
* be used in IRQ contexts, so in some (very limited) cases we need
* it.
*/
-void *kmap_atomic_prot(struct page *page, pgprot_t prot)
+void *kmap_atomic_high_prot(struct page *page, pgprot_t prot)
{
unsigned long vaddr;
int idx, type;
- preempt_disable();
- pagefault_disable();
- if (!PageHighMem(page))
- return page_address(page);
-
type = kmap_atomic_idx_push();
idx = type + KM_TYPE_NR*smp_processor_id();
vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
@@ -49,7 +44,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
return (void*) vaddr;
}
-EXPORT_SYMBOL(kmap_atomic_prot);
+EXPORT_SYMBOL(kmap_atomic_high_prot);
void __kunmap_atomic(void *kvaddr)
{
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index 90b96594d6c5..61f47fef40e5 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -58,7 +58,16 @@ extern unsigned long highstart_pfn, highend_pfn;
#define PKMAP_NR(virt) ((virt-PKMAP_BASE) >> PAGE_SHIFT)
#define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT))
-void *kmap_atomic_prot(struct page *page, pgprot_t prot);
+extern void *kmap_atomic_high_prot(struct page *page, pgprot_t prot);
+static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
[PATCH V2 00/11] Subject: Remove duplicated kmap code
From: Ira Weiny
The kmap infrastructure has been copied almost verbatim to every architecture.
This series consolidates obvious duplicated code by defining core functions
which call into the architectures only when needed.
Some of the k[un]map_atomic() implementations have some similarities but the
similarities were not sufficient to warrant further changes.
In addition we remove a duplicate implementation of kmap() in DRM.
Testing was done by 0day to cover all the architectures I can't readily
build/test.
---
Changes from V1:
Fix bisect-ability
Update commit message and fix line lengths
Remove unneded kunmap_atomic_high() declarations
Remove unneded kmap_atomic_high() declarations
collect reviews
rebase to 5.7-rc4
Changes from V0:
Define kmap_flush_tlb() and make kmap() truely arch independent.
Redefine the k[un]map_atomic_* code to call into the architectures for
high mem pages
Ensure all architectures define kmap_prot, use it appropriately, and
define kmap_atomic_prot()
Remove drm implementation of kmap_atomic()
Ira Weiny (11):
arch/kmap: Remove BUG_ON()
arch/xtensa: Move kmap build bug out of the way
arch/kmap: Remove redundant arch specific kmaps
arch/kunmap: Remove duplicate kunmap implementations
{x86,powerpc,microblaze}/kmap: Move preempt disable
arch/kmap_atomic: Consolidate duplicate code
arch/kunmap_atomic: Consolidate duplicate code
arch/kmap: Ensure kmap_prot visibility
arch/kmap: Don't hard code kmap_prot values
arch/kmap: Define kmap_atomic_prot() for all arch's
drm: Remove drm specific kmap_atomic code
arch/arc/include/asm/highmem.h| 15 ---
arch/arc/mm/highmem.c | 28 +++-
arch/arm/include/asm/highmem.h| 7 ---
arch/arm/mm/highmem.c | 35 +++
arch/csky/include/asm/highmem.h | 9 +---
arch/csky/mm/highmem.c| 43 +--
arch/microblaze/include/asm/highmem.h | 28 +---
arch/microblaze/mm/highmem.c | 16 ++-
arch/microblaze/mm/init.c | 3 --
arch/mips/include/asm/highmem.h | 9 +---
arch/mips/mm/cache.c | 6 +--
arch/mips/mm/highmem.c| 49 -
arch/nds32/include/asm/highmem.h | 7 ---
arch/nds32/mm/highmem.c | 39 +++--
arch/parisc/include/asm/cacheflush.h | 4 +-
arch/powerpc/include/asm/highmem.h| 29 +
arch/powerpc/mm/highmem.c | 21 ++---
arch/powerpc/mm/mem.c | 3 --
arch/sparc/include/asm/highmem.h | 22 --
arch/sparc/mm/highmem.c | 18 +++-
arch/x86/include/asm/highmem.h| 9
arch/x86/mm/highmem_32.c | 50 ++---
arch/xtensa/include/asm/highmem.h | 27
arch/xtensa/mm/highmem.c | 22 --
drivers/gpu/drm/ttm/ttm_bo_util.c | 56 ++--
drivers/gpu/drm/vmwgfx/vmwgfx_blit.c | 16 +++
include/drm/ttm/ttm_bo_api.h | 4 --
include/linux/highmem.h | 62 +--
28 files changed, 140 insertions(+), 497 deletions(-)
--
2.25.1
[PATCH V2 11/11] drm: Remove drm specific kmap_atomic code
From: Ira Weiny
kmap_atomic_prot() is now exported by all architectures. Use this
function rather than open coding a driver specific kmap_atomic.
Reviewed-by: Christian König
Reviewed-by: Christoph Hellwig
Signed-off-by: Ira Weiny
---
drivers/gpu/drm/ttm/ttm_bo_util.c| 56 ++--
drivers/gpu/drm/vmwgfx/vmwgfx_blit.c | 16
include/drm/ttm/ttm_bo_api.h | 4 --
3 files changed, 12 insertions(+), 64 deletions(-)
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c
b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 52d2b71f1588..f09b096ba4fd 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -257,54 +257,6 @@ static int ttm_copy_io_page(void *dst, void *src, unsigned
long page)
return 0;
}
-#ifdef CONFIG_X86
-#define __ttm_kmap_atomic_prot(__page, __prot) kmap_atomic_prot(__page, __prot)
-#define __ttm_kunmap_atomic(__addr) kunmap_atomic(__addr)
-#else
-#define __ttm_kmap_atomic_prot(__page, __prot) vmap(&__page, 1, 0, __prot)
-#define __ttm_kunmap_atomic(__addr) vunmap(__addr)
-#endif
-
-
-/**
- * ttm_kmap_atomic_prot - Efficient kernel map of a single page with
- * specified page protection.
- *
- * @page: The page to map.
- * @prot: The page protection.
- *
- * This function maps a TTM page using the kmap_atomic api if available,
- * otherwise falls back to vmap. The user must make sure that the
- * specified page does not have an aliased mapping with a different caching
- * policy unless the architecture explicitly allows it. Also mapping and
- * unmapping using this api must be correctly nested. Unmapping should
- * occur in the reverse order of mapping.
- */
-void *ttm_kmap_atomic_prot(struct page *page, pgprot_t prot)
-{
- if (pgprot_val(prot) == pgprot_val(PAGE_KERNEL))
- return kmap_atomic(page);
- else
- return __ttm_kmap_atomic_prot(page, prot);
-}
-EXPORT_SYMBOL(ttm_kmap_atomic_prot);
-
-/**
- * ttm_kunmap_atomic_prot - Unmap a page that was mapped using
- * ttm_kmap_atomic_prot.
- *
- * @addr: The virtual address from the map.
- * @prot: The page protection.
- */
-void ttm_kunmap_atomic_prot(void *addr, pgprot_t prot)
-{
- if (pgprot_val(prot) == pgprot_val(PAGE_KERNEL))
- kunmap_atomic(addr);
- else
- __ttm_kunmap_atomic(addr);
-}
-EXPORT_SYMBOL(ttm_kunmap_atomic_prot);
-
static int ttm_copy_io_ttm_page(struct ttm_tt *ttm, void *src,
unsigned long page,
pgprot_t prot)
@@ -316,13 +268,13 @@ static int ttm_copy_io_ttm_page(struct ttm_tt *ttm, void
*src,
return -ENOMEM;
src = (void *)((unsigned long)src + (page << PAGE_SHIFT));
- dst = ttm_kmap_atomic_prot(d, prot);
+ dst = kmap_atomic_prot(d, prot);
if (!dst)
return -ENOMEM;
memcpy_fromio(dst, src, PAGE_SIZE);
- ttm_kunmap_atomic_prot(dst, prot);
+ kunmap_atomic(dst);
return 0;
}
@@ -338,13 +290,13 @@ static int ttm_copy_ttm_io_page(struct ttm_tt *ttm, void
*dst,
return -ENOMEM;
dst = (void *)((unsigned long)dst + (page << PAGE_SHIFT));
- src = ttm_kmap_atomic_prot(s, prot);
+ src = kmap_atomic_prot(s, prot);
if (!src)
return -ENOMEM;
memcpy_toio(dst, src, PAGE_SIZE);
- ttm_kunmap_atomic_prot(src, prot);
+ kunmap_atomic(src);
return 0;
}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
index bb46ca0c458f..94d456a1d1a9 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
@@ -374,12 +374,12 @@ static int vmw_bo_cpu_blit_line(struct
vmw_bo_blit_line_data *d,
copy_size = min_t(u32, copy_size, PAGE_SIZE - src_page_offset);
if (unmap_src) {
- ttm_kunmap_atomic_prot(d->src_addr, d->src_prot);
+ kunmap_atomic(d->src_addr);
d->src_addr = NULL;
}
if (unmap_dst) {
- ttm_kunmap_atomic_prot(d->dst_addr, d->dst_prot);
+ kunmap_atomic(d->dst_addr);
d->dst_addr = NULL;
}
@@ -388,8 +388,8 @@ static int vmw_bo_cpu_blit_line(struct
vmw_bo_blit_line_data *d,
return -EINVAL;
d->dst_addr =
- ttm_kmap_atomic_prot(d->dst_pages[dst_page],
-d->dst_prot);
+ kmap_atomic_prot(d->dst_pages[dst_page],
+d->dst_prot);
if (!d->dst_addr)
return -ENOMEM;
@@ -401,8 +401,8 @@ static int vmw_bo_cpu_blit_line(struct
vmw_bo_blit_line_data *d,
return -EINVAL;
[PATCH V2 03/11] arch/kmap: Remove redundant arch specific kmaps
From: Ira Weiny
The kmap code for all the architectures is almost 100% identical.
Lift the common code to the core. Use ARCH_HAS_KMAP_FLUSH_TLB to
indicate if an arch defines kmap_flush_tlb() and call if if needed.
This also has the benefit of changing kmap() on a number of
architectures to be an inline call rather than an actual function.
Reviewed-by: Christoph Hellwig
Signed-off-by: Ira Weiny
---
arch/arc/include/asm/highmem.h| 2 --
arch/arc/mm/highmem.c | 10 --
arch/arm/include/asm/highmem.h| 2 --
arch/arm/mm/highmem.c | 9 -
arch/csky/include/asm/highmem.h | 4 ++--
arch/csky/mm/highmem.c| 14 --
arch/microblaze/include/asm/highmem.h | 9 -
arch/mips/include/asm/highmem.h | 4 ++--
arch/mips/mm/highmem.c| 14 +++---
arch/nds32/include/asm/highmem.h | 2 --
arch/nds32/mm/highmem.c | 12
arch/powerpc/include/asm/highmem.h| 9 -
arch/sparc/include/asm/highmem.h | 9 -
arch/x86/include/asm/highmem.h| 2 --
arch/x86/mm/highmem_32.c | 9 -
arch/xtensa/include/asm/highmem.h | 9 -
include/linux/highmem.h | 18 ++
17 files changed, 29 insertions(+), 109 deletions(-)
diff --git a/arch/arc/include/asm/highmem.h b/arch/arc/include/asm/highmem.h
index 042e92921c4c..96eb67c86961 100644
--- a/arch/arc/include/asm/highmem.h
+++ b/arch/arc/include/asm/highmem.h
@@ -30,8 +30,6 @@
#include
-extern void *kmap(struct page *page);
-extern void *kmap_high(struct page *page);
extern void *kmap_atomic(struct page *page);
extern void __kunmap_atomic(void *kvaddr);
extern void kunmap_high(struct page *page);
diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c
index 39ef7b9a3aa9..4db13a6b9f3b 100644
--- a/arch/arc/mm/highmem.c
+++ b/arch/arc/mm/highmem.c
@@ -49,16 +49,6 @@
extern pte_t * pkmap_page_table;
static pte_t * fixmap_page_table;
-void *kmap(struct page *page)
-{
- might_sleep();
- if (!PageHighMem(page))
- return page_address(page);
-
- return kmap_high(page);
-}
-EXPORT_SYMBOL(kmap);
-
void *kmap_atomic(struct page *page)
{
int idx, cpu_idx;
diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h
index eb4e4207cd3c..c917522541de 100644
--- a/arch/arm/include/asm/highmem.h
+++ b/arch/arm/include/asm/highmem.h
@@ -20,7 +20,6 @@
extern pte_t *pkmap_page_table;
-extern void *kmap_high(struct page *page);
extern void kunmap_high(struct page *page);
/*
@@ -63,7 +62,6 @@ static inline void *kmap_high_get(struct page *page)
* when CONFIG_HIGHMEM is not set.
*/
#ifdef CONFIG_HIGHMEM
-extern void *kmap(struct page *page);
extern void kunmap(struct page *page);
extern void *kmap_atomic(struct page *page);
extern void __kunmap_atomic(void *kvaddr);
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index cc6eb79ef20c..e8ba37c36590 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -31,15 +31,6 @@ static inline pte_t get_fixmap_pte(unsigned long vaddr)
return *ptep;
}
-void *kmap(struct page *page)
-{
- might_sleep();
- if (!PageHighMem(page))
- return page_address(page);
- return kmap_high(page);
-}
-EXPORT_SYMBOL(kmap);
-
void kunmap(struct page *page)
{
might_sleep();
diff --git a/arch/csky/include/asm/highmem.h b/arch/csky/include/asm/highmem.h
index a345a2f2c22e..9d0516e38110 100644
--- a/arch/csky/include/asm/highmem.h
+++ b/arch/csky/include/asm/highmem.h
@@ -30,10 +30,10 @@ extern pte_t *pkmap_page_table;
#define PKMAP_NR(virt) ((virt-PKMAP_BASE) >> PAGE_SHIFT)
#define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT))
-extern void *kmap_high(struct page *page);
extern void kunmap_high(struct page *page);
-extern void *kmap(struct page *page);
+#define ARCH_HAS_KMAP_FLUSH_TLB
+extern void kmap_flush_tlb(unsigned long addr);
extern void kunmap(struct page *page);
extern void *kmap_atomic(struct page *page);
extern void __kunmap_atomic(void *kvaddr);
diff --git a/arch/csky/mm/highmem.c b/arch/csky/mm/highmem.c
index 690d678649d1..4a3c273bc8b9 100644
--- a/arch/csky/mm/highmem.c
+++ b/arch/csky/mm/highmem.c
@@ -13,18 +13,12 @@ static pte_t *kmap_pte;
unsigned long highstart_pfn, highend_pfn;
-void *kmap(struct page *page)
+void kmap_flush_tlb(unsigned long addr)
{
- void *addr;
-
- might_sleep();
- if (!PageHighMem(page))
- return page_address(page);
- addr = kmap_high(page);
- flush_tlb_one((unsigned long)addr);
-
- return addr;
+ flush_tlb_one(addr);
}
+EXPORT_SYMBOL(kmap_flush_tlb);
+
EXPORT_SYMBOL(kmap);
void kunmap(struct page *page)
diff --git a/arch/microblaze/include/asm/highmem.h
b/arch/microblaze/include/asm/highmem.h
index 99ced7278b5c..8c5bfd228bd8 100644
---
[PATCH V2 10/11] arch/kmap: Define kmap_atomic_prot() for all arch's
From: Ira Weiny
To support kmap_atomic_prot(), all architectures need to support
protections passed to their kmap_atomic_high() function. Pass
protections into kmap_atomic_high() and change the name to
kmap_atomic_high_prot() to match.
Then define kmap_atomic_prot() as a core function which calls
kmap_atomic_high_prot() when needed.
Finally, redefine kmap_atomic() as a wrapper of kmap_atomic_prot() with
the default kmap_prot exported by the architectures.
Signed-off-by: Ira Weiny
---
Changes from V1:
Adjust for bisect-ability
Adjust for removing kunmap_atomic_high
Remove kmap_atomic_high_prot declarations
---
arch/arc/mm/highmem.c | 6 +++---
arch/arm/mm/highmem.c | 6 +++---
arch/csky/mm/highmem.c| 6 +++---
arch/microblaze/include/asm/highmem.h | 16
arch/mips/mm/highmem.c| 6 +++---
arch/nds32/mm/highmem.c | 6 +++---
arch/powerpc/include/asm/highmem.h| 17 -
arch/sparc/mm/highmem.c | 6 +++---
arch/x86/include/asm/highmem.h| 14 --
arch/xtensa/mm/highmem.c | 6 +++---
include/linux/highmem.h | 7 ---
11 files changed, 25 insertions(+), 71 deletions(-)
diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c
index 5d3eab4ac0b0..479b0d72d3cf 100644
--- a/arch/arc/mm/highmem.c
+++ b/arch/arc/mm/highmem.c
@@ -49,7 +49,7 @@
extern pte_t * pkmap_page_table;
static pte_t * fixmap_page_table;
-void *kmap_atomic_high(struct page *page)
+void *kmap_atomic_high_prot(struct page *page, pgprot_t prot)
{
int idx, cpu_idx;
unsigned long vaddr;
@@ -59,11 +59,11 @@ void *kmap_atomic_high(struct page *page)
vaddr = FIXMAP_ADDR(idx);
set_pte_at(_mm, vaddr, fixmap_page_table + idx,
- mk_pte(page, kmap_prot));
+ mk_pte(page, prot));
return (void *)vaddr;
}
-EXPORT_SYMBOL(kmap_atomic_high);
+EXPORT_SYMBOL(kmap_atomic_high_prot);
void kunmap_atomic_high(void *kv)
{
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index ac8394655a6e..e013f6b81328 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -31,7 +31,7 @@ static inline pte_t get_fixmap_pte(unsigned long vaddr)
return *ptep;
}
-void *kmap_atomic_high(struct page *page)
+void *kmap_atomic_high_prot(struct page *page, pgprot_t prot)
{
unsigned int idx;
unsigned long vaddr;
@@ -67,11 +67,11 @@ void *kmap_atomic_high(struct page *page)
* in place, so the contained TLB flush ensures the TLB is updated
* with the new mapping.
*/
- set_fixmap_pte(idx, mk_pte(page, kmap_prot));
+ set_fixmap_pte(idx, mk_pte(page, prot));
return (void *)vaddr;
}
-EXPORT_SYMBOL(kmap_atomic_high);
+EXPORT_SYMBOL(kmap_atomic_high_prot);
void kunmap_atomic_high(void *kvaddr)
{
diff --git a/arch/csky/mm/highmem.c b/arch/csky/mm/highmem.c
index f4311669b5bb..3ae5c8cd7619 100644
--- a/arch/csky/mm/highmem.c
+++ b/arch/csky/mm/highmem.c
@@ -21,7 +21,7 @@ EXPORT_SYMBOL(kmap_flush_tlb);
EXPORT_SYMBOL(kmap);
-void *kmap_atomic_high(struct page *page)
+void *kmap_atomic_high_prot(struct page *page, pgprot_t prot)
{
unsigned long vaddr;
int idx, type;
@@ -32,12 +32,12 @@ void *kmap_atomic_high(struct page *page)
#ifdef CONFIG_DEBUG_HIGHMEM
BUG_ON(!pte_none(*(kmap_pte - idx)));
#endif
- set_pte(kmap_pte-idx, mk_pte(page, kmap_prot));
+ set_pte(kmap_pte-idx, mk_pte(page, prot));
flush_tlb_one((unsigned long)vaddr);
return (void *)vaddr;
}
-EXPORT_SYMBOL(kmap_atomic_high);
+EXPORT_SYMBOL(kmap_atomic_high_prot);
void kunmap_atomic_high(void *kvaddr)
{
diff --git a/arch/microblaze/include/asm/highmem.h
b/arch/microblaze/include/asm/highmem.h
index 033ac5b5c2da..d7c55cfd27bd 100644
--- a/arch/microblaze/include/asm/highmem.h
+++ b/arch/microblaze/include/asm/highmem.h
@@ -51,22 +51,6 @@ extern pte_t *pkmap_page_table;
#define PKMAP_NR(virt) ((virt - PKMAP_BASE) >> PAGE_SHIFT)
#define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT))
-extern void *kmap_atomic_high_prot(struct page *page, pgprot_t prot);
-void *kmap_atomic_prot(struct page *page, pgprot_t prot)
-{
- preempt_disable();
- pagefault_disable();
- if (!PageHighMem(page))
- return page_address(page);
-
- return kmap_atomic_high_prot(page, prot);
-}
-
-static inline void *kmap_atomic_high(struct page *page)
-{
- return kmap_atomic_high_prot(page, kmap_prot);
-}
-
#define flush_cache_kmaps(){ flush_icache(); flush_dcache(); }
#endif /* __KERNEL__ */
diff --git a/arch/mips/mm/highmem.c b/arch/mips/mm/highmem.c
index 87023bd1a33c..37e244cdb14e 100644
--- a/arch/mips/mm/highmem.c
+++ b/arch/mips/mm/highmem.c
@@ -18,7 +18,7 @@ void kmap_flush_tlb(unsigned long addr)
}
EXPORT_SYMBOL(kmap_flush_tlb);
-void
[PATCH V2 06/11] arch/kmap_atomic: Consolidate duplicate code
From: Ira Weiny
Every arch has the same code to ensure atomic operations and a check for
!HIGHMEM page.
Remove the duplicate code by defining a core kmap_atomic() which only
calls the arch specific kmap_atomic_high() when the page is high memory.
Signed-off-by: Ira Weiny
---
Changes from V1:
Adjust to preserve bisect-ability
Remove unneeded kmap_atomic_high declarations
---
arch/arc/include/asm/highmem.h| 1 -
arch/arc/mm/highmem.c | 9 ++---
arch/arm/include/asm/highmem.h| 1 -
arch/arm/mm/highmem.c | 9 ++---
arch/csky/include/asm/highmem.h | 1 -
arch/csky/mm/highmem.c| 9 ++---
arch/microblaze/include/asm/highmem.h | 4 ++--
arch/mips/include/asm/highmem.h | 1 -
arch/mips/mm/cache.c | 2 +-
arch/mips/mm/highmem.c| 18 ++
arch/nds32/include/asm/highmem.h | 1 -
arch/nds32/mm/highmem.c | 9 ++---
arch/powerpc/include/asm/highmem.h| 4 ++--
arch/powerpc/mm/highmem.c | 6 --
arch/sparc/include/asm/highmem.h | 1 -
arch/sparc/mm/highmem.c | 9 ++---
arch/x86/include/asm/highmem.h| 5 -
arch/x86/mm/highmem_32.c | 14 --
arch/xtensa/include/asm/highmem.h | 1 -
arch/xtensa/mm/highmem.c | 9 ++---
include/linux/highmem.h | 23 +++
21 files changed, 46 insertions(+), 91 deletions(-)
diff --git a/arch/arc/include/asm/highmem.h b/arch/arc/include/asm/highmem.h
index 8387a5596a91..db425cd38545 100644
--- a/arch/arc/include/asm/highmem.h
+++ b/arch/arc/include/asm/highmem.h
@@ -30,7 +30,6 @@
#include
-extern void *kmap_atomic(struct page *page);
extern void __kunmap_atomic(void *kvaddr);
extern void kmap_init(void);
diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c
index 4db13a6b9f3b..0964b011c29f 100644
--- a/arch/arc/mm/highmem.c
+++ b/arch/arc/mm/highmem.c
@@ -49,16 +49,11 @@
extern pte_t * pkmap_page_table;
static pte_t * fixmap_page_table;
-void *kmap_atomic(struct page *page)
+void *kmap_atomic_high(struct page *page)
{
int idx, cpu_idx;
unsigned long vaddr;
- preempt_disable();
- pagefault_disable();
- if (!PageHighMem(page))
- return page_address(page);
-
cpu_idx = kmap_atomic_idx_push();
idx = cpu_idx + KM_TYPE_NR * smp_processor_id();
vaddr = FIXMAP_ADDR(idx);
@@ -68,7 +63,7 @@ void *kmap_atomic(struct page *page)
return (void *)vaddr;
}
-EXPORT_SYMBOL(kmap_atomic);
+EXPORT_SYMBOL(kmap_atomic_high);
void __kunmap_atomic(void *kv)
{
diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h
index 736f65283e7b..8c80bfe18a34 100644
--- a/arch/arm/include/asm/highmem.h
+++ b/arch/arm/include/asm/highmem.h
@@ -60,7 +60,6 @@ static inline void *kmap_high_get(struct page *page)
* when CONFIG_HIGHMEM is not set.
*/
#ifdef CONFIG_HIGHMEM
-extern void *kmap_atomic(struct page *page);
extern void __kunmap_atomic(void *kvaddr);
extern void *kmap_atomic_pfn(unsigned long pfn);
#endif
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index c700b32350ee..075fdc235091 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -31,18 +31,13 @@ static inline pte_t get_fixmap_pte(unsigned long vaddr)
return *ptep;
}
-void *kmap_atomic(struct page *page)
+void *kmap_atomic_high(struct page *page)
{
unsigned int idx;
unsigned long vaddr;
void *kmap;
int type;
- preempt_disable();
- pagefault_disable();
- if (!PageHighMem(page))
- return page_address(page);
-
#ifdef CONFIG_DEBUG_HIGHMEM
/*
* There is no cache coherency issue when non VIVT, so force the
@@ -76,7 +71,7 @@ void *kmap_atomic(struct page *page)
return (void *)vaddr;
}
-EXPORT_SYMBOL(kmap_atomic);
+EXPORT_SYMBOL(kmap_atomic_high);
void __kunmap_atomic(void *kvaddr)
{
diff --git a/arch/csky/include/asm/highmem.h b/arch/csky/include/asm/highmem.h
index be11c5b67122..8ceee12f9bc1 100644
--- a/arch/csky/include/asm/highmem.h
+++ b/arch/csky/include/asm/highmem.h
@@ -32,7 +32,6 @@ extern pte_t *pkmap_page_table;
#define ARCH_HAS_KMAP_FLUSH_TLB
extern void kmap_flush_tlb(unsigned long addr);
-extern void *kmap_atomic(struct page *page);
extern void __kunmap_atomic(void *kvaddr);
extern void *kmap_atomic_pfn(unsigned long pfn);
extern struct page *kmap_atomic_to_page(void *ptr);
diff --git a/arch/csky/mm/highmem.c b/arch/csky/mm/highmem.c
index e9952211264b..63d74b47eee6 100644
--- a/arch/csky/mm/highmem.c
+++ b/arch/csky/mm/highmem.c
@@ -21,16 +21,11 @@ EXPORT_SYMBOL(kmap_flush_tlb);
EXPORT_SYMBOL(kmap);
-void *kmap_atomic(struct page *page)
+void *kmap_atomic_high(struct page *page)
{
unsigned long vaddr;
int idx, type;
- preempt_disable();
[PATCH V2 04/11] arch/kunmap: Remove duplicate kunmap implementations
From: Ira Weiny
All architectures do exactly the same thing for kunmap(); remove all the
duplicate definitions and lift the call to the core.
This also has the benefit of changing kmap_unmap() on a number of
architectures to be an inline call rather than an actual function.
Reviewed-by: Christoph Hellwig
Signed-off-by: Ira Weiny
---
arch/arc/include/asm/highmem.h| 10 --
arch/arm/include/asm/highmem.h| 3 ---
arch/arm/mm/highmem.c | 9 -
arch/csky/include/asm/highmem.h | 3 ---
arch/csky/mm/highmem.c| 9 -
arch/microblaze/include/asm/highmem.h | 9 -
arch/mips/include/asm/highmem.h | 3 ---
arch/mips/mm/highmem.c| 9 -
arch/nds32/include/asm/highmem.h | 3 ---
arch/nds32/mm/highmem.c | 10 --
arch/powerpc/include/asm/highmem.h| 9 -
arch/sparc/include/asm/highmem.h | 10 --
arch/x86/include/asm/highmem.h| 4
arch/x86/mm/highmem_32.c | 9 -
arch/xtensa/include/asm/highmem.h | 10 --
include/linux/highmem.h | 9 +
16 files changed, 9 insertions(+), 110 deletions(-)
diff --git a/arch/arc/include/asm/highmem.h b/arch/arc/include/asm/highmem.h
index 96eb67c86961..8387a5596a91 100644
--- a/arch/arc/include/asm/highmem.h
+++ b/arch/arc/include/asm/highmem.h
@@ -32,7 +32,6 @@
extern void *kmap_atomic(struct page *page);
extern void __kunmap_atomic(void *kvaddr);
-extern void kunmap_high(struct page *page);
extern void kmap_init(void);
@@ -41,15 +40,6 @@ static inline void flush_cache_kmaps(void)
flush_cache_all();
}
-static inline void kunmap(struct page *page)
-{
- might_sleep();
- if (!PageHighMem(page))
- return;
- kunmap_high(page);
-}
-
-
#endif
#endif
diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h
index c917522541de..736f65283e7b 100644
--- a/arch/arm/include/asm/highmem.h
+++ b/arch/arm/include/asm/highmem.h
@@ -20,8 +20,6 @@
extern pte_t *pkmap_page_table;
-extern void kunmap_high(struct page *page);
-
/*
* The reason for kmap_high_get() is to ensure that the currently kmap'd
* page usage count does not decrease to zero while we're using its
@@ -62,7 +60,6 @@ static inline void *kmap_high_get(struct page *page)
* when CONFIG_HIGHMEM is not set.
*/
#ifdef CONFIG_HIGHMEM
-extern void kunmap(struct page *page);
extern void *kmap_atomic(struct page *page);
extern void __kunmap_atomic(void *kvaddr);
extern void *kmap_atomic_pfn(unsigned long pfn);
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index e8ba37c36590..c700b32350ee 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -31,15 +31,6 @@ static inline pte_t get_fixmap_pte(unsigned long vaddr)
return *ptep;
}
-void kunmap(struct page *page)
-{
- might_sleep();
- if (!PageHighMem(page))
- return;
- kunmap_high(page);
-}
-EXPORT_SYMBOL(kunmap);
-
void *kmap_atomic(struct page *page)
{
unsigned int idx;
diff --git a/arch/csky/include/asm/highmem.h b/arch/csky/include/asm/highmem.h
index 9d0516e38110..be11c5b67122 100644
--- a/arch/csky/include/asm/highmem.h
+++ b/arch/csky/include/asm/highmem.h
@@ -30,11 +30,8 @@ extern pte_t *pkmap_page_table;
#define PKMAP_NR(virt) ((virt-PKMAP_BASE) >> PAGE_SHIFT)
#define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT))
-extern void kunmap_high(struct page *page);
-
#define ARCH_HAS_KMAP_FLUSH_TLB
extern void kmap_flush_tlb(unsigned long addr);
-extern void kunmap(struct page *page);
extern void *kmap_atomic(struct page *page);
extern void __kunmap_atomic(void *kvaddr);
extern void *kmap_atomic_pfn(unsigned long pfn);
diff --git a/arch/csky/mm/highmem.c b/arch/csky/mm/highmem.c
index 4a3c273bc8b9..e9952211264b 100644
--- a/arch/csky/mm/highmem.c
+++ b/arch/csky/mm/highmem.c
@@ -21,15 +21,6 @@ EXPORT_SYMBOL(kmap_flush_tlb);
EXPORT_SYMBOL(kmap);
-void kunmap(struct page *page)
-{
- might_sleep();
- if (!PageHighMem(page))
- return;
- kunmap_high(page);
-}
-EXPORT_SYMBOL(kunmap);
-
void *kmap_atomic(struct page *page)
{
unsigned long vaddr;
diff --git a/arch/microblaze/include/asm/highmem.h
b/arch/microblaze/include/asm/highmem.h
index 8c5bfd228bd8..0c94046f2d58 100644
--- a/arch/microblaze/include/asm/highmem.h
+++ b/arch/microblaze/include/asm/highmem.h
@@ -51,18 +51,9 @@ extern pte_t *pkmap_page_table;
#define PKMAP_NR(virt) ((virt - PKMAP_BASE) >> PAGE_SHIFT)
#define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT))
-extern void kunmap_high(struct page *page);
extern void *kmap_atomic_prot(struct page *page, pgprot_t prot);
extern void __kunmap_atomic(void *kvaddr);
-static inline void kunmap(struct page *page)
-{
- might_sleep();
- if (!PageHighMem(page))
- return;
- kunmap_high(page);
-}
[PATCH V2 08/11] arch/kmap: Ensure kmap_prot visibility
From: Ira Weiny
We want to support kmap_atomic_prot() on all architectures and it makes
sense to define kmap_atomic() to use the default kmap_prot.
So we ensure all arch's have a globally available kmap_prot either as a
define or exported symbol.
Signed-off-by: Ira Weiny
---
arch/microblaze/include/asm/highmem.h | 2 +-
arch/microblaze/mm/init.c | 3 ---
arch/powerpc/include/asm/highmem.h| 2 +-
arch/powerpc/mm/mem.c | 3 ---
arch/sparc/mm/highmem.c | 1 +
5 files changed, 3 insertions(+), 8 deletions(-)
diff --git a/arch/microblaze/include/asm/highmem.h
b/arch/microblaze/include/asm/highmem.h
index 1b8a3c5102bd..033ac5b5c2da 100644
--- a/arch/microblaze/include/asm/highmem.h
+++ b/arch/microblaze/include/asm/highmem.h
@@ -25,8 +25,8 @@
#include
#include
+#define kmap_prot PAGE_KERNEL
extern pte_t *kmap_pte;
-extern pgprot_t kmap_prot;
extern pte_t *pkmap_page_table;
/*
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 1ffbfa96b9b8..a467686c13af 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -49,8 +49,6 @@ unsigned long lowmem_size;
#ifdef CONFIG_HIGHMEM
pte_t *kmap_pte;
EXPORT_SYMBOL(kmap_pte);
-pgprot_t kmap_prot;
-EXPORT_SYMBOL(kmap_prot);
static inline pte_t *virt_to_kpte(unsigned long vaddr)
{
@@ -68,7 +66,6 @@ static void __init highmem_init(void)
pkmap_page_table = virt_to_kpte(PKMAP_BASE);
kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN));
- kmap_prot = PAGE_KERNEL;
}
static void highmem_setup(void)
diff --git a/arch/powerpc/include/asm/highmem.h
b/arch/powerpc/include/asm/highmem.h
index 373a470df205..ee5de974c5ef 100644
--- a/arch/powerpc/include/asm/highmem.h
+++ b/arch/powerpc/include/asm/highmem.h
@@ -29,8 +29,8 @@
#include
#include
+#define kmap_prot PAGE_KERNEL
extern pte_t *kmap_pte;
-extern pgprot_t kmap_prot;
extern pte_t *pkmap_page_table;
/*
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 041ed7cfd341..3f642b058731 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -64,8 +64,6 @@ bool init_mem_is_free;
#ifdef CONFIG_HIGHMEM
pte_t *kmap_pte;
EXPORT_SYMBOL(kmap_pte);
-pgprot_t kmap_prot;
-EXPORT_SYMBOL(kmap_prot);
#endif
pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
@@ -245,7 +243,6 @@ void __init paging_init(void)
pkmap_page_table = virt_to_kpte(PKMAP_BASE);
kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN));
- kmap_prot = PAGE_KERNEL;
#endif /* CONFIG_HIGHMEM */
printk(KERN_DEBUG "Top of RAM: 0x%llx, Total RAM: 0x%llx\n",
diff --git a/arch/sparc/mm/highmem.c b/arch/sparc/mm/highmem.c
index 469786bc430f..9f06d75e88e1 100644
--- a/arch/sparc/mm/highmem.c
+++ b/arch/sparc/mm/highmem.c
@@ -33,6 +33,7 @@
#include
pgprot_t kmap_prot;
+EXPORT_SYMBOL(kmap_prot);
static pte_t *kmap_pte;
--
2.25.1
Re: [PATCH v2 17/20] mm: free_area_init: allow defining max_zone_pfn in descending order
On Sun, May 03, 2020 at 10:41:38AM -0700, Guenter Roeck wrote: > Hi, > > On Wed, Apr 29, 2020 at 03:11:23PM +0300, Mike Rapoport wrote: > > From: Mike Rapoport > > > > Some architectures (e.g. ARC) have the ZONE_HIGHMEM zone below the > > ZONE_NORMAL. Allowing free_area_init() parse max_zone_pfn array even it is > > sorted in descending order allows using free_area_init() on such > > architectures. > > > > Add top -> down traversal of max_zone_pfn array in free_area_init() and use > > the latter in ARC node/zone initialization. > > > > Signed-off-by: Mike Rapoport > > This patch causes my microblazeel qemu boot test in linux-next to fail. > Reverting it fixes the problem. > The same problem is seen with s390 emulations. Guenter > qemu command line: > > qemu-system-microblazeel -M petalogix-ml605 -m 256 \ > -kernel arch/microblaze/boot/linux.bin -no-reboot \ > -initrd rootfs.cpio \ > -append 'panic=-1 slub_debug=FZPUA rdinit=/sbin/init > console=ttyS0,115200' \ > -monitor none -serial stdio -nographic > > initrd: > > https://github.com/groeck/linux-build-test/blob/master/rootfs/microblazeel/rootfs.cpio.gz > configuration: > > https://github.com/groeck/linux-build-test/blob/master/rootfs/microblazeel/qemu_microblazeel_ml605_defconfig > > Bisect log is below. > > Guenter > > --- > # bad: [fb9d670f57e3f6478602328bbbf71138be06ca4f] Add linux-next specific > files for 20200501 > # good: [6a8b55ed4056ea5559ebe4f6a4b247f627870d4c] Linux 5.7-rc3 > git bisect start 'HEAD' 'v5.7-rc3' > # good: [068b80b68a670f0b17288c8a3d1ee751f35162ab] Merge remote-tracking > branch 'drm/drm-next' > git bisect good 068b80b68a670f0b17288c8a3d1ee751f35162ab > # good: [46c70fc6a3ac35cd72ddad248dcbe4eee716d2a5] Merge remote-tracking > branch 'drivers-x86/for-next' > git bisect good 46c70fc6a3ac35cd72ddad248dcbe4eee716d2a5 > # good: [f39c4ad479a2f005f972a2b941b40efa6b9c9349] Merge remote-tracking > branch 'rpmsg/for-next' > git bisect good f39c4ad479a2f005f972a2b941b40efa6b9c9349 > # bad: [165d3ee0162fe28efc2c8180176633e33515df15] > ipc-convert-ipcs_idr-to-xarray-update > git bisect bad 165d3ee0162fe28efc2c8180176633e33515df15 > # good: [001f1d211ed2ed0f005838dc4390993930bbbd69] mm: remove > early_pfn_in_nid() and CONFIG_NODES_SPAN_OTHER_NODES > git bisect good 001f1d211ed2ed0f005838dc4390993930bbbd69 > # bad: [aaad7401bd32f10c1d591dd886b3a9b9595c6d77] mm/vmsan: fix some typos in > comment > git bisect bad aaad7401bd32f10c1d591dd886b3a9b9595c6d77 > # bad: [09f9d0ab1fbed85623b283995aa7a7d78daa1611] khugepaged: allow to > collapse PTE-mapped compound pages > git bisect bad 09f9d0ab1fbed85623b283995aa7a7d78daa1611 > # bad: [c942fc8a3e5088407bc32d94f554bab205175f8a] mm/vmstat.c: do not show > lowmem reserve protection information of empty zone > git bisect bad c942fc8a3e5088407bc32d94f554bab205175f8a > # bad: [b29358d269ace3826d8521bea842fc2984cfc11b] mm/page_alloc.c: rename > free_pages_check() to check_free_page() > git bisect bad b29358d269ace3826d8521bea842fc2984cfc11b > # bad: [be0fb591a1f1df20a00c8f023f9ca4891f177b0d] mm: simplify > find_min_pfn_with_active_regions() > git bisect bad be0fb591a1f1df20a00c8f023f9ca4891f177b0d > # bad: [c17422a008d36dcf3e9f51469758c5762716cb0a] mm: rename > free_area_init_node() to free_area_init_memoryless_node() > git bisect bad c17422a008d36dcf3e9f51469758c5762716cb0a > # bad: [51a2f644fd020d5f090044825c388444d11029d5] mm: free_area_init: allow > defining max_zone_pfn in descending order > git bisect bad 51a2f644fd020d5f090044825c388444d11029d5 > # first bad commit: [51a2f644fd020d5f090044825c388444d11029d5] mm: > free_area_init: allow defining max_zone_pfn in descending order
Re: [PATCH v2 17/20] mm: free_area_init: allow defining max_zone_pfn in descending order
Hi, On Wed, Apr 29, 2020 at 03:11:23PM +0300, Mike Rapoport wrote: > From: Mike Rapoport > > Some architectures (e.g. ARC) have the ZONE_HIGHMEM zone below the > ZONE_NORMAL. Allowing free_area_init() parse max_zone_pfn array even it is > sorted in descending order allows using free_area_init() on such > architectures. > > Add top -> down traversal of max_zone_pfn array in free_area_init() and use > the latter in ARC node/zone initialization. > > Signed-off-by: Mike Rapoport This patch causes my microblazeel qemu boot test in linux-next to fail. Reverting it fixes the problem. qemu command line: qemu-system-microblazeel -M petalogix-ml605 -m 256 \ -kernel arch/microblaze/boot/linux.bin -no-reboot \ -initrd rootfs.cpio \ -append 'panic=-1 slub_debug=FZPUA rdinit=/sbin/init console=ttyS0,115200' \ -monitor none -serial stdio -nographic initrd: https://github.com/groeck/linux-build-test/blob/master/rootfs/microblazeel/rootfs.cpio.gz configuration: https://github.com/groeck/linux-build-test/blob/master/rootfs/microblazeel/qemu_microblazeel_ml605_defconfig Bisect log is below. Guenter --- # bad: [fb9d670f57e3f6478602328bbbf71138be06ca4f] Add linux-next specific files for 20200501 # good: [6a8b55ed4056ea5559ebe4f6a4b247f627870d4c] Linux 5.7-rc3 git bisect start 'HEAD' 'v5.7-rc3' # good: [068b80b68a670f0b17288c8a3d1ee751f35162ab] Merge remote-tracking branch 'drm/drm-next' git bisect good 068b80b68a670f0b17288c8a3d1ee751f35162ab # good: [46c70fc6a3ac35cd72ddad248dcbe4eee716d2a5] Merge remote-tracking branch 'drivers-x86/for-next' git bisect good 46c70fc6a3ac35cd72ddad248dcbe4eee716d2a5 # good: [f39c4ad479a2f005f972a2b941b40efa6b9c9349] Merge remote-tracking branch 'rpmsg/for-next' git bisect good f39c4ad479a2f005f972a2b941b40efa6b9c9349 # bad: [165d3ee0162fe28efc2c8180176633e33515df15] ipc-convert-ipcs_idr-to-xarray-update git bisect bad 165d3ee0162fe28efc2c8180176633e33515df15 # good: [001f1d211ed2ed0f005838dc4390993930bbbd69] mm: remove early_pfn_in_nid() and CONFIG_NODES_SPAN_OTHER_NODES git bisect good 001f1d211ed2ed0f005838dc4390993930bbbd69 # bad: [aaad7401bd32f10c1d591dd886b3a9b9595c6d77] mm/vmsan: fix some typos in comment git bisect bad aaad7401bd32f10c1d591dd886b3a9b9595c6d77 # bad: [09f9d0ab1fbed85623b283995aa7a7d78daa1611] khugepaged: allow to collapse PTE-mapped compound pages git bisect bad 09f9d0ab1fbed85623b283995aa7a7d78daa1611 # bad: [c942fc8a3e5088407bc32d94f554bab205175f8a] mm/vmstat.c: do not show lowmem reserve protection information of empty zone git bisect bad c942fc8a3e5088407bc32d94f554bab205175f8a # bad: [b29358d269ace3826d8521bea842fc2984cfc11b] mm/page_alloc.c: rename free_pages_check() to check_free_page() git bisect bad b29358d269ace3826d8521bea842fc2984cfc11b # bad: [be0fb591a1f1df20a00c8f023f9ca4891f177b0d] mm: simplify find_min_pfn_with_active_regions() git bisect bad be0fb591a1f1df20a00c8f023f9ca4891f177b0d # bad: [c17422a008d36dcf3e9f51469758c5762716cb0a] mm: rename free_area_init_node() to free_area_init_memoryless_node() git bisect bad c17422a008d36dcf3e9f51469758c5762716cb0a # bad: [51a2f644fd020d5f090044825c388444d11029d5] mm: free_area_init: allow defining max_zone_pfn in descending order git bisect bad 51a2f644fd020d5f090044825c388444d11029d5 # first bad commit: [51a2f644fd020d5f090044825c388444d11029d5] mm: free_area_init: allow defining max_zone_pfn in descending order
Re: [PATCH 0/7] sha1 library cleanup
On Sat, May 02, 2020 at 03:05:46PM -0600, Jason A. Donenfeld wrote:
> Thanks for this series. I like the general idea. I think it might make
> sense, though, to separate things out into sha1.h and sha256.h. That
> will be nice preparation work for when we eventually move obsolete
> primitives into some subdirectory.
That's basically what I suggested in the cover letter:
"As future work, we should split sha.h into sha1.h and sha2.h and try to
remove the remaining uses of SHA-1. For example, the remaining use in
drivers/char/random.c is probably one that can be gotten rid of."
("sha2.h" rather than "sha256.h", since it would include SHA-512 too.
Also, we already have sha3.h, so having sha{1,2,3}.h would be logical.)
But there are 108 files that include , all of which would need to
be updated, which risks merge conflicts. So this series seemed like a good
stopping point to get these initial changes in for 5.8. Then in the next
release we can split up sha.h (and debate whether sha1.h should really be
"" or whatever).
There are 3 files where I added an include of sha.h, where we could go directly
to sha1.h if we did it now. But that's not much compared to the 108 files.
- Eric
Re: [PATCH 0/7] sha1 library cleanup
On Sat, 2 May 2020 at 20:28, Eric Biggers wrote: > > sounds very generic and important, like it's the > header to include if you're doing cryptographic hashing in the kernel. > But actually it only includes the library implementation of the SHA-1 > compression function (not even the full SHA-1). This should basically > never be used anymore; SHA-1 is no longer considered secure, and there > are much better ways to do cryptographic hashing in the kernel. > > Also the function is named just "sha_transform()", which makes it > unclear which version of SHA is meant. > > Therefore, this series cleans things up by moving these SHA-1 > declarations into where they better belong, and changing > the names to say SHA-1 rather than just SHA. > > As future work, we should split sha.h into sha1.h and sha2.h and try to > remove the remaining uses of SHA-1. For example, the remaining use in > drivers/char/random.c is probably one that can be gotten rid of. > > This patch series applies to cryptodev/master. > > Eric Biggers (7): > mptcp: use SHA256_BLOCK_SIZE, not SHA_MESSAGE_BYTES > crypto: powerpc/sha1 - remove unused temporary workspace > crypto: powerpc/sha1 - prefix the "sha1_" functions > crypto: s390/sha1 - prefix the "sha1_" functions > crypto: lib/sha1 - rename "sha" to "sha1" > crypto: lib/sha1 - remove unnecessary includes of linux/cryptohash.h > crypto: lib/sha1 - fold linux/cryptohash.h into crypto/sha.h > For the series, Acked-by: Ard Biesheuvel > Documentation/security/siphash.rst | 2 +- > arch/arm/crypto/sha1_glue.c | 1 - > arch/arm/crypto/sha1_neon_glue.c| 1 - > arch/arm/crypto/sha256_glue.c | 1 - > arch/arm/crypto/sha256_neon_glue.c | 1 - > arch/arm/kernel/armksyms.c | 1 - > arch/arm64/crypto/sha256-glue.c | 1 - > arch/arm64/crypto/sha512-glue.c | 1 - > arch/microblaze/kernel/microblaze_ksyms.c | 1 - > arch/mips/cavium-octeon/crypto/octeon-md5.c | 1 - > arch/powerpc/crypto/md5-glue.c | 1 - > arch/powerpc/crypto/sha1-spe-glue.c | 1 - > arch/powerpc/crypto/sha1.c | 33 ++--- > arch/powerpc/crypto/sha256-spe-glue.c | 1 - > arch/s390/crypto/sha1_s390.c| 12 > arch/sparc/crypto/md5_glue.c| 1 - > arch/sparc/crypto/sha1_glue.c | 1 - > arch/sparc/crypto/sha256_glue.c | 1 - > arch/sparc/crypto/sha512_glue.c | 1 - > arch/unicore32/kernel/ksyms.c | 1 - > arch/x86/crypto/sha1_ssse3_glue.c | 1 - > arch/x86/crypto/sha256_ssse3_glue.c | 1 - > arch/x86/crypto/sha512_ssse3_glue.c | 1 - > crypto/sha1_generic.c | 5 ++-- > drivers/char/random.c | 8 ++--- > drivers/crypto/atmel-sha.c | 1 - > drivers/crypto/chelsio/chcr_algo.c | 1 - > drivers/crypto/chelsio/chcr_ipsec.c | 1 - > drivers/crypto/omap-sham.c | 1 - > fs/f2fs/hash.c | 1 - > include/crypto/sha.h| 10 +++ > include/linux/cryptohash.h | 14 - > include/linux/filter.h | 4 +-- > include/net/tcp.h | 1 - > kernel/bpf/core.c | 18 +-- > lib/crypto/chacha.c | 1 - > lib/sha1.c | 24 --- > net/core/secure_seq.c | 1 - > net/ipv6/addrconf.c | 10 +++ > net/ipv6/seg6_hmac.c| 1 - > net/mptcp/crypto.c | 4 +-- > 41 files changed, 69 insertions(+), 104 deletions(-) > delete mode 100644 include/linux/cryptohash.h > > > base-commit: 12b3cf9093542d9f752a4968815ece836159013f > -- > 2.26.2 >
[PATCH 2/2] powerpc/64s/hash: add torture_hpt kernel boot option to increase hash faults
This option increases the number of hash misses by limiting the number of
kernel HPT entries. This helps stress test difficult to hit paths in the
kernel.
Signed-off-by: Nicholas Piggin
---
.../admin-guide/kernel-parameters.txt | 9 +++
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 10 +++
arch/powerpc/mm/book3s64/hash_4k.c| 3 +
arch/powerpc/mm/book3s64/hash_64k.c | 8 +++
arch/powerpc/mm/book3s64/hash_utils.c | 66 ++-
5 files changed, 95 insertions(+), 1 deletion(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt
b/Documentation/admin-guide/kernel-parameters.txt
index 5a34b7dd9ebe..1ec6a32a717a 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -876,6 +876,15 @@
them frequently to increase the rate of SLB faults
on kernel addresses.
+ torture_hpt [PPC]
+ Limits the number of kernel HPT entries in the hash
+ page table to increase the rate of hash page table
+ faults on kernel addresses.
+
+ This may hang when run on processors / emulators which
+ do not have a TLB, or flush it more often than
+ required, QEMU seems to have problems.
+
disable=[IPV6]
See Documentation/networking/ipv6.txt.
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 758de1e0f676..539e3d91eac4 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -324,6 +324,16 @@ static inline bool torture_slb(void)
return static_branch_unlikely(_slb_key);
}
+extern bool torture_hpt_enabled;
+DECLARE_STATIC_KEY_FALSE(torture_hpt_key);
+static inline bool torture_hpt(void)
+{
+ return static_branch_unlikely(_hpt_key);
+}
+
+void hpt_do_torture(unsigned long ea, unsigned long access,
+ unsigned long rflags, unsigned long hpte_group);
+
/*
* This computes the AVPN and B fields of the first dword of a HPTE,
* for use when we want to match an existing PTE. The bottom 7 bits
diff --git a/arch/powerpc/mm/book3s64/hash_4k.c
b/arch/powerpc/mm/book3s64/hash_4k.c
index 22e787123cdf..54e4ff8c558d 100644
--- a/arch/powerpc/mm/book3s64/hash_4k.c
+++ b/arch/powerpc/mm/book3s64/hash_4k.c
@@ -118,6 +118,9 @@ int __hash_page_4K(unsigned long ea, unsigned long access,
unsigned long vsid,
}
new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE;
new_pte |= pte_set_hidx(ptep, rpte, 0, slot, PTRS_PER_PTE);
+
+ if (torture_hpt())
+ hpt_do_torture(ea, access, rflags, hpte_group);
}
*ptep = __pte(new_pte & ~H_PAGE_BUSY);
return 0;
diff --git a/arch/powerpc/mm/book3s64/hash_64k.c
b/arch/powerpc/mm/book3s64/hash_64k.c
index 7084ce2951e6..19ea0fc145a9 100644
--- a/arch/powerpc/mm/book3s64/hash_64k.c
+++ b/arch/powerpc/mm/book3s64/hash_64k.c
@@ -216,6 +216,9 @@ int __hash_page_4K(unsigned long ea, unsigned long access,
unsigned long vsid,
new_pte |= pte_set_hidx(ptep, rpte, subpg_index, slot, PTRS_PER_PTE);
new_pte |= H_PAGE_HASHPTE;
+ if (torture_hpt())
+ hpt_do_torture(ea, access, rflags, hpte_group);
+
*ptep = __pte(new_pte & ~H_PAGE_BUSY);
return 0;
}
@@ -327,7 +330,12 @@ int __hash_page_64K(unsigned long ea, unsigned long access,
new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE;
new_pte |= pte_set_hidx(ptep, rpte, 0, slot, PTRS_PER_PTE);
+
+ if (torture_hpt())
+ hpt_do_torture(ea, access, rflags, hpte_group);
}
+
*ptep = __pte(new_pte & ~H_PAGE_BUSY);
+
return 0;
}
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c
b/arch/powerpc/mm/book3s64/hash_utils.c
index 9c487b5782ef..e9bdf825f897 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -353,8 +353,12 @@ int htab_remove_mapping(unsigned long vstart, unsigned
long vend,
return ret;
}
-static bool disable_1tb_segments = false;
+static bool disable_1tb_segments __read_mostly = false;
bool torture_slb_enabled __read_mostly = false;
+bool torture_hpt_enabled __read_mostly = false;
+
+/* per-CPU array allocated if we enable torture_hpt. */
+static unsigned long *torture_hpt_last_group;
static int __init parse_disable_1tb_segments(char *p)
{
@@ -370,6 +374,13 @@ static int __init parse_torture_slb(char *p)
}
early_param("torture_slb", parse_torture_slb);
+static int __init parse_torture_hpt(char *p)
+{
+ torture_hpt_enabled = true;
+ return 0;
+}
+early_param("torture_hpt", parse_torture_hpt);
+
static int __init htab_dt_scan_seg_sizes(unsigned long
[PATCH 1/2] powerpc/64s/hash: add torture_slb kernel boot option to increase SLB faults
This option increases the number of SLB misses by limiting the number of
kernel SLB entries, and increased flushing of cached lookaside information.
This helps stress test difficult to hit paths in the kernel.
Signed-off-by: Nicholas Piggin
---
.../admin-guide/kernel-parameters.txt | 5 +
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 7 +
arch/powerpc/mm/book3s64/hash_utils.c | 13 ++
arch/powerpc/mm/book3s64/slb.c| 145 --
4 files changed, 125 insertions(+), 45 deletions(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt
b/Documentation/admin-guide/kernel-parameters.txt
index f2a93c8679e8..5a34b7dd9ebe 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -871,6 +871,11 @@
can be useful when debugging issues that require an SLB
miss to occur.
+ torture_slb [PPC]
+ Limits the number of kernel SLB entries, and flushes
+ them frequently to increase the rate of SLB faults
+ on kernel addresses.
+
disable=[IPV6]
See Documentation/networking/ipv6.txt.
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 3fa1b962dc27..758de1e0f676 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -317,6 +317,13 @@ extern unsigned long tce_alloc_start, tce_alloc_end;
*/
extern int mmu_ci_restrictions;
+extern bool torture_slb_enabled;
+DECLARE_STATIC_KEY_FALSE(torture_slb_key);
+static inline bool torture_slb(void)
+{
+ return static_branch_unlikely(_slb_key);
+}
+
/*
* This computes the AVPN and B fields of the first dword of a HPTE,
* for use when we want to match an existing PTE. The bottom 7 bits
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c
b/arch/powerpc/mm/book3s64/hash_utils.c
index 8ed2411c3f39..9c487b5782ef 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -354,6 +354,7 @@ int htab_remove_mapping(unsigned long vstart, unsigned long
vend,
}
static bool disable_1tb_segments = false;
+bool torture_slb_enabled __read_mostly = false;
static int __init parse_disable_1tb_segments(char *p)
{
@@ -362,6 +363,13 @@ static int __init parse_disable_1tb_segments(char *p)
}
early_param("disable_1tb_segments", parse_disable_1tb_segments);
+static int __init parse_torture_slb(char *p)
+{
+ torture_slb_enabled = true;
+ return 0;
+}
+early_param("torture_slb", parse_torture_slb);
+
static int __init htab_dt_scan_seg_sizes(unsigned long node,
const char *uname, int depth,
void *data)
@@ -854,6 +862,8 @@ static void __init hash_init_partition_table(phys_addr_t
hash_table,
pr_info("Partition table %p\n", partition_tb);
}
+DEFINE_STATIC_KEY_FALSE(torture_slb_key);
+
static void __init htab_initialize(void)
{
unsigned long table;
@@ -870,6 +880,9 @@ static void __init htab_initialize(void)
printk(KERN_INFO "Using 1TB segments\n");
}
+ if (torture_slb_enabled)
+ static_branch_enable(_slb_key);
+
/*
* Calculate the required size of the htab. We want the number of
* PTEGs to equal one half the number of real pages.
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index 716204aee3da..37e9f6c096e3 100644
--- a/arch/powerpc/mm/book3s64/slb.c
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -68,7 +68,7 @@ static void assert_slb_presence(bool present, unsigned long
ea)
* slbfee. requires bit 24 (PPC bit 39) be clear in RB. Hardware
* ignores all other bits from 0-27, so just clear them all.
*/
- ea &= ~((1UL << 28) - 1);
+ ea &= ~((1UL << SID_SHIFT) - 1);
asm volatile(__PPC_SLBFEE_DOT(%0, %1) : "=r"(tmp) : "r"(ea) : "cr0");
WARN_ON(present == (tmp == 0));
@@ -153,14 +153,28 @@ void slb_flush_all_realmode(void)
asm volatile("slbmte %0,%0; slbia" : : "r" (0));
}
+static __always_inline void __slb_flush_and_restore_bolted(u32 ih)
+{
+ struct slb_shadow *p = get_slb_shadow();
+ unsigned long ksp_esid_data, ksp_vsid_data;
+
+ ksp_esid_data = be64_to_cpu(p->save_area[KSTACK_INDEX].esid);
+ ksp_vsid_data = be64_to_cpu(p->save_area[KSTACK_INDEX].vsid);
+
+ asm volatile(PPC_SLBIA(%0)" \n"
+"slbmte%1, %2 \n"
+:: "i" (ih),
+ "r" (ksp_vsid_data),
+ "r" (ksp_esid_data)
+: "memory");
+}
+
/*
* This flushes non-bolted entries, it can be run in virtual mode. Must
* be called with interrupts disabled.
*/
void
