* [PATCH v3 3/4] powerpc/ptdump: Reduce level numbers by 1 in note_page() and add p4d level
From: Christophe Leroy @ 2021-07-05 7:50 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <b864a92693ca8413ef0b19f0c12065c212899b6e.1625471053.git.christophe.leroy@csgroup.eu>
Do the same as commit f8f0d0b6fa20 ("mm: ptdump: reduce level numbers
by 1 in note_page()") and add missing p4d level.
This will align powerpc to the users of generic ptdump.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/mm/ptdump/8xx.c | 6 ++++--
arch/powerpc/mm/ptdump/book3s64.c | 6 ++++--
arch/powerpc/mm/ptdump/ptdump.c | 17 +++++++++--------
arch/powerpc/mm/ptdump/shared.c | 6 ++++--
4 files changed, 21 insertions(+), 14 deletions(-)
diff --git a/arch/powerpc/mm/ptdump/8xx.c b/arch/powerpc/mm/ptdump/8xx.c
index 86da2a669680..fac932eb8f9a 100644
--- a/arch/powerpc/mm/ptdump/8xx.c
+++ b/arch/powerpc/mm/ptdump/8xx.c
@@ -75,8 +75,10 @@ static const struct flag_info flag_array[] = {
};
struct pgtable_level pg_level[5] = {
- {
- }, { /* pgd */
+ { /* pgd */
+ .flag = flag_array,
+ .num = ARRAY_SIZE(flag_array),
+ }, { /* p4d */
.flag = flag_array,
.num = ARRAY_SIZE(flag_array),
}, { /* pud */
diff --git a/arch/powerpc/mm/ptdump/book3s64.c b/arch/powerpc/mm/ptdump/book3s64.c
index 14f73868db66..5ad92d9dc5d1 100644
--- a/arch/powerpc/mm/ptdump/book3s64.c
+++ b/arch/powerpc/mm/ptdump/book3s64.c
@@ -103,8 +103,10 @@ static const struct flag_info flag_array[] = {
};
struct pgtable_level pg_level[5] = {
- {
- }, { /* pgd */
+ { /* pgd */
+ .flag = flag_array,
+ .num = ARRAY_SIZE(flag_array),
+ }, { /* p4d */
.flag = flag_array,
.num = ARRAY_SIZE(flag_array),
}, { /* pud */
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index 3eb8732641da..fb531bc64fc5 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -58,7 +58,7 @@ struct pg_state {
const struct addr_marker *marker;
unsigned long start_address;
unsigned long start_pa;
- unsigned int level;
+ int level;
u64 current_flags;
bool check_wx;
unsigned long wx_pages;
@@ -188,10 +188,9 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr)
st->wx_pages += (addr - st->start_address) / PAGE_SIZE;
}
-static void note_page_update_state(struct pg_state *st, unsigned long addr,
- unsigned int level, u64 val)
+static void note_page_update_state(struct pg_state *st, unsigned long addr, int level, u64 val)
{
- u64 flag = val & pg_level[level].mask;
+ u64 flag = level >= 0 ? val & pg_level[level].mask : 0;
u64 pa = val & PTE_RPN_MASK;
st->level = level;
@@ -206,12 +205,12 @@ static void note_page_update_state(struct pg_state *st, unsigned long addr,
}
static void note_page(struct pg_state *st, unsigned long addr,
- unsigned int level, u64 val, unsigned long page_size)
+ int level, u64 val, unsigned long page_size)
{
- u64 flag = val & pg_level[level].mask;
+ u64 flag = level >= 0 ? val & pg_level[level].mask : 0;
/* At first no level is set */
- if (!st->level) {
+ if (st->level == -1) {
pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
note_page_update_state(st, addr, level, val);
/*
@@ -383,6 +382,7 @@ static int ptdump_show(struct seq_file *m, void *v)
struct pg_state st = {
.seq = m,
.marker = address_markers,
+ .level = -1,
.start_address = IS_ENABLED(CONFIG_PPC64) ? PAGE_OFFSET : TASK_SIZE,
};
@@ -393,7 +393,7 @@ static int ptdump_show(struct seq_file *m, void *v)
/* Traverse kernel page tables */
walk_pagetables(&st);
- note_page(&st, 0, 0, 0, 0);
+ note_page(&st, 0, -1, 0, 0);
return 0;
}
@@ -415,6 +415,7 @@ void ptdump_check_wx(void)
struct pg_state st = {
.seq = NULL,
.marker = address_markers,
+ .level = -1,
.check_wx = true,
.start_address = IS_ENABLED(CONFIG_PPC64) ? PAGE_OFFSET : TASK_SIZE,
};
diff --git a/arch/powerpc/mm/ptdump/shared.c b/arch/powerpc/mm/ptdump/shared.c
index c005fe041c18..03607ab90c66 100644
--- a/arch/powerpc/mm/ptdump/shared.c
+++ b/arch/powerpc/mm/ptdump/shared.c
@@ -68,8 +68,10 @@ static const struct flag_info flag_array[] = {
};
struct pgtable_level pg_level[5] = {
- {
- }, { /* pgd */
+ { /* pgd */
+ .flag = flag_array,
+ .num = ARRAY_SIZE(flag_array),
+ }, { /* p4d */
.flag = flag_array,
.num = ARRAY_SIZE(flag_array),
}, { /* pud */
--
2.25.0
^ permalink raw reply related
* [PATCH v3 2/4] powerpc/ptdump: Remove unused 'page_size' parameter
From: Christophe Leroy @ 2021-07-05 7:50 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <b864a92693ca8413ef0b19f0c12065c212899b6e.1625471053.git.christophe.leroy@csgroup.eu>
note_page_update_state() doesn't use page_size. Remove it.
Could also be removed to note_page() but as a following patch
will remove all current users of note_page(), just leave it as
is for now.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/mm/ptdump/ptdump.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index 349fd8fe173f..3eb8732641da 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -189,7 +189,7 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr)
}
static void note_page_update_state(struct pg_state *st, unsigned long addr,
- unsigned int level, u64 val, unsigned long page_size)
+ unsigned int level, u64 val)
{
u64 flag = val & pg_level[level].mask;
u64 pa = val & PTE_RPN_MASK;
@@ -213,7 +213,7 @@ static void note_page(struct pg_state *st, unsigned long addr,
/* At first no level is set */
if (!st->level) {
pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
- note_page_update_state(st, addr, level, val, page_size);
+ note_page_update_state(st, addr, level, val);
/*
* Dump the section of virtual memory when:
* - the PTE flags from one entry to the next differs.
@@ -242,7 +242,7 @@ static void note_page(struct pg_state *st, unsigned long addr,
* Address indicates we have passed the end of the
* current section of virtual memory
*/
- note_page_update_state(st, addr, level, val, page_size);
+ note_page_update_state(st, addr, level, val);
}
}
--
2.25.0
^ permalink raw reply related
* [PATCH v3 1/4] powerpc/ptdump: Use DEFINE_SHOW_ATTRIBUTE()
From: Christophe Leroy @ 2021-07-05 7:50 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
Use DEFINE_SHOW_ATTRIBUTE() instead of open coding
open() and fops.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v4: This series is following the partial merge of "Convert powerpc to GENERIC_PTDUMP".
Patches 1 2 and 3 of that series were merged in 5.13. This updated series is a
split of patch 4. The split helps reduce the size of the previous patch by only
keeping in it the actual conversion.
arch/powerpc/mm/ptdump/bats.c | 14 ++------------
arch/powerpc/mm/ptdump/hashpagetable.c | 12 +-----------
arch/powerpc/mm/ptdump/ptdump.c | 13 +------------
arch/powerpc/mm/ptdump/segment_regs.c | 12 +-----------
4 files changed, 5 insertions(+), 46 deletions(-)
diff --git a/arch/powerpc/mm/ptdump/bats.c b/arch/powerpc/mm/ptdump/bats.c
index c4c628b03cf8..4ed3418f07d9 100644
--- a/arch/powerpc/mm/ptdump/bats.c
+++ b/arch/powerpc/mm/ptdump/bats.c
@@ -57,7 +57,7 @@ static void bat_show_603(struct seq_file *m, int idx, u32 lower, u32 upper, bool
#define BAT_SHOW_603(_m, _n, _l, _u, _d) bat_show_603(_m, _n, mfspr(_l), mfspr(_u), _d)
-static int bats_show_603(struct seq_file *m, void *v)
+static int bats_show(struct seq_file *m, void *v)
{
seq_puts(m, "---[ Instruction Block Address Translation ]---\n");
@@ -88,17 +88,7 @@ static int bats_show_603(struct seq_file *m, void *v)
return 0;
}
-static int bats_open(struct inode *inode, struct file *file)
-{
- return single_open(file, bats_show_603, NULL);
-}
-
-static const struct file_operations bats_fops = {
- .open = bats_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(bats);
static int __init bats_init(void)
{
diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c
index ad6df9a2e7c8..c7f824d294b2 100644
--- a/arch/powerpc/mm/ptdump/hashpagetable.c
+++ b/arch/powerpc/mm/ptdump/hashpagetable.c
@@ -526,17 +526,7 @@ static int ptdump_show(struct seq_file *m, void *v)
return 0;
}
-static int ptdump_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ptdump_show, NULL);
-}
-
-static const struct file_operations ptdump_fops = {
- .open = ptdump_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(ptdump);
static int ptdump_init(void)
{
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index 5062c58b1e5b..349fd8fe173f 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -397,18 +397,7 @@ static int ptdump_show(struct seq_file *m, void *v)
return 0;
}
-
-static int ptdump_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ptdump_show, NULL);
-}
-
-static const struct file_operations ptdump_fops = {
- .open = ptdump_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(ptdump);
static void build_pgtable_complete_mask(void)
{
diff --git a/arch/powerpc/mm/ptdump/segment_regs.c b/arch/powerpc/mm/ptdump/segment_regs.c
index 565048a0c9be..3054944d3d7e 100644
--- a/arch/powerpc/mm/ptdump/segment_regs.c
+++ b/arch/powerpc/mm/ptdump/segment_regs.c
@@ -41,17 +41,7 @@ static int sr_show(struct seq_file *m, void *v)
return 0;
}
-static int sr_open(struct inode *inode, struct file *file)
-{
- return single_open(file, sr_show, NULL);
-}
-
-static const struct file_operations sr_fops = {
- .open = sr_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(sr);
static int __init sr_init(void)
{
--
2.25.0
^ permalink raw reply related
* Re: [PATCH v15 06/12] swiotlb: Use is_swiotlb_force_bounce for swiotlb data bouncing
From: Claire Chang @ 2021-07-05 7:29 UTC (permalink / raw)
To: Nathan Chancellor
Cc: heikki.krogerus, thomas.hellstrom, peterz, joonas.lahtinen,
dri-devel, chris, grant.likely, paulus, Frank Rowand, mingo,
Marek Szyprowski, Stefano Stabellini, Saravana Kannan,
xypron.glpk, Joerg Roedel, Rafael J . Wysocki, Christoph Hellwig,
Bartosz Golaszewski, bskeggs, linux-pci, xen-devel,
Thierry Reding, intel-gfx, matthew.auld, linux-devicetree,
Jianxiong Gao, Daniel Vetter, Will Deacon, Konrad Rzeszutek Wilk,
maarten.lankhorst, airlied, Dan Williams, linuxppc-dev,
jani.nikula, Rob Herring, rodrigo.vivi, Bjorn Helgaas,
boris.ostrovsky, Andy Shevchenko, jgross, Nicolas Boichat,
Greg KH, Randy Dunlap, Qian Cai, lkml, Tomasz Figa,
list@263.net:IOMMU DRIVERS, Jim Quinlan, Tom Lendacky,
Robin Murphy, bauerman
In-Reply-To: <YN/7xcxt/XGAKceZ@Ryzen-9-3900X.localdomain>
On Sat, Jul 3, 2021 at 1:55 PM Nathan Chancellor <nathan@kernel.org> wrote:
>
> Hi Will and Robin,
>
> On Fri, Jul 02, 2021 at 04:13:50PM +0100, Robin Murphy wrote:
> > On 2021-07-02 14:58, Will Deacon wrote:
> > > Hi Nathan,
> > >
> > > On Thu, Jul 01, 2021 at 12:52:20AM -0700, Nathan Chancellor wrote:
> > > > On 7/1/2021 12:40 AM, Will Deacon wrote:
> > > > > On Wed, Jun 30, 2021 at 08:56:51AM -0700, Nathan Chancellor wrote:
> > > > > > On Wed, Jun 30, 2021 at 12:43:48PM +0100, Will Deacon wrote:
> > > > > > > On Wed, Jun 30, 2021 at 05:17:27PM +0800, Claire Chang wrote:
> > > > > > > > `BUG: unable to handle page fault for address: 00000000003a8290` and
> > > > > > > > the fact it crashed at `_raw_spin_lock_irqsave` look like the memory
> > > > > > > > (maybe dev->dma_io_tlb_mem) was corrupted?
> > > > > > > > The dev->dma_io_tlb_mem should be set here
> > > > > > > > (https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git/tree/drivers/pci/probe.c#n2528)
> > > > > > > > through device_initialize.
> > > > > > >
> > > > > > > I'm less sure about this. 'dma_io_tlb_mem' should be pointing at
> > > > > > > 'io_tlb_default_mem', which is a page-aligned allocation from memblock.
> > > > > > > The spinlock is at offset 0x24 in that structure, and looking at the
> > > > > > > register dump from the crash:
> > > > > > >
> > > > > > > Jun 29 18:28:42 hp-4300G kernel: RSP: 0018:ffffadb4013db9e8 EFLAGS: 00010006
> > > > > > > Jun 29 18:28:42 hp-4300G kernel: RAX: 00000000003a8290 RBX: 0000000000000000 RCX: ffff8900572ad580
> > > > > > > Jun 29 18:28:42 hp-4300G kernel: RDX: ffff89005653f024 RSI: 00000000000c0000 RDI: 0000000000001d17
> > > > > > > Jun 29 18:28:42 hp-4300G kernel: RBP: 000000000a20d000 R08: 00000000000c0000 R09: 0000000000000000
> > > > > > > Jun 29 18:28:42 hp-4300G kernel: R10: 000000000a20d000 R11: ffff89005653f000 R12: 0000000000000212
> > > > > > > Jun 29 18:28:42 hp-4300G kernel: R13: 0000000000001000 R14: 0000000000000002 R15: 0000000000200000
> > > > > > > Jun 29 18:28:42 hp-4300G kernel: FS: 00007f1f8898ea40(0000) GS:ffff890057280000(0000) knlGS:0000000000000000
> > > > > > > Jun 29 18:28:42 hp-4300G kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> > > > > > > Jun 29 18:28:42 hp-4300G kernel: CR2: 00000000003a8290 CR3: 00000001020d0000 CR4: 0000000000350ee0
> > > > > > > Jun 29 18:28:42 hp-4300G kernel: Call Trace:
> > > > > > > Jun 29 18:28:42 hp-4300G kernel: _raw_spin_lock_irqsave+0x39/0x50
> > > > > > > Jun 29 18:28:42 hp-4300G kernel: swiotlb_tbl_map_single+0x12b/0x4c0
> > > > > > >
> > > > > > > Then that correlates with R11 holding the 'dma_io_tlb_mem' pointer and
> > > > > > > RDX pointing at the spinlock. Yet RAX is holding junk :/
> > > > > > >
> > > > > > > I agree that enabling KASAN would be a good idea, but I also think we
> > > > > > > probably need to get some more information out of swiotlb_tbl_map_single()
> > > > > > > to see see what exactly is going wrong in there.
> > > > > >
> > > > > > I can certainly enable KASAN and if there is any debug print I can add
> > > > > > or dump anything, let me know!
> > > > >
> > > > > I bit the bullet and took v5.13 with swiotlb/for-linus-5.14 merged in, built
> > > > > x86 defconfig and ran it on my laptop. However, it seems to work fine!
> > > > >
> > > > > Please can you share your .config?
> > > >
> > > > Sure thing, it is attached. It is just Arch Linux's config run through
> > > > olddefconfig. The original is below in case you need to diff it.
> > > >
> > > > https://raw.githubusercontent.com/archlinux/svntogit-packages/9045405dc835527164f3034b3ceb9a67c7a53cd4/trunk/config
> > > >
> > > > If there is anything more that I can provide, please let me know.
> > >
> > > I eventually got this booting (for some reason it was causing LD to SEGV
> > > trying to link it for a while...) and sadly it works fine on my laptop. Hmm.
>
> Seems like it might be something specific to the amdgpu module?
>
> > > Did you manage to try again with KASAN?
>
> Yes, it took a few times to reproduce the issue but I did manage to get
> a dmesg, please find it attached. I build from commit 7d31f1c65cc9 ("swiotlb:
> fix implicit debugfs declarations") in Konrad's tree.
Looking at the logs, the use-after-free bug looked somehow relevant
(and it's nvme again. Qian's crash is about nvme too):
[ 2.468288] BUG: KASAN: use-after-free in __iommu_dma_unmap_swiotlb+0x64/0xb0
[ 2.468288] Read of size 8 at addr ffff8881d7830000 by task swapper/0/0
[ 2.468288] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.12.0-rc3-debug #1
[ 2.468288] Hardware name: HP HP Desktop M01-F1xxx/87D6, BIOS F.12 12/17/2020
[ 2.468288] Call Trace:
[ 2.468288] <IRQ>
[ 2.479433] dump_stack+0x9c/0xcf
[ 2.479433] print_address_description.constprop.0+0x18/0x130
[ 2.479433] ? __iommu_dma_unmap_swiotlb+0x64/0xb0
[ 2.479433] kasan_report.cold+0x7f/0x111
[ 2.479433] ? __iommu_dma_unmap_swiotlb+0x64/0xb0
[ 2.479433] __iommu_dma_unmap_swiotlb+0x64/0xb0
[ 2.479433] nvme_pci_complete_rq+0x73/0x130
[ 2.479433] blk_complete_reqs+0x6f/0x80
[ 2.479433] __do_softirq+0xfc/0x3be
[ 2.479433] irq_exit_rcu+0xce/0x120
[ 2.479433] common_interrupt+0x80/0xa0
[ 2.479433] </IRQ>
[ 2.479433] asm_common_interrupt+0x1e/0x40
[ 2.479433] RIP: 0010:cpuidle_enter_state+0xf9/0x590
I wonder if this ended up unmapping something wrong and messing up the
dev->dma_io_tlb_mem (i.e. io_tlb_default_mem)?
Could you try this patch on top of 7d31f1c65cc9? This patch helps
check if we try to unmap the wrong address.
```
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index b7f76bca89bf..5ac08d50a394 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -613,6 +613,21 @@ void swiotlb_tbl_unmap_single(struct device *dev,
phys_addr_t tlb_addr,
size_t mapping_size, enum dma_data_direction dir,
unsigned long attrs)
{
+ struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
+ unsigned int offset = swiotlb_align_offset(dev, tlb_addr);
+ int index;
+
+ if (!is_swiotlb_buffer(dev, tlb_addr - offset)) {
+ dev_err(dev, "%s: attempt to unmap invalid address
(0x%llx, offset=%u)\n", __func__, tlb_addr, offset);
+ return;
+ }
+
+ index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT;
+ if (mem->slots[index].orig_addr == INVALID_PHYS_ADDR) {
+ dev_err(dev, "%s: memory is not mapped before (0x%llx,
offset=%u)\n", __func__, tlb_addr, offset);
+ return;
+ }
+
/*
* First, sync the memory before unmapping the entry
*/
```
It might be useful to have CONFIG_SLUB_DEBUG=y, CONFIG_SLUB_DEBUG_ON=y
and line numbers (scripts/decode_stacktrace.sh) too.
Thank you so much for helping!
>
> > > It might also be worth taking the IOMMU out of the equation, since that
> > > interfaces differently with SWIOTLB and I couldn't figure out the code path
> > > from the log you provided. What happens if you boot with "amd_iommu=off
> > > swiotlb=force"?
> >
> > Oh, now there's a thing... the chat from the IOMMU API in the boot log
> > implies that the IOMMU *should* be in the picture - we see that default
> > domains are IOMMU_DOMAIN_DMA default and the GPU 0000:0c:00.0 was added to a
> > group. That means dev->dma_ops should be set and DMA API calls should be
> > going through iommu-dma, yet the callstack in the crash says we've gone
> > straight from dma_map_page_attrs() to swiotlb_map(), implying the inline
> > dma_direct_map_page() path.
> >
> > If dev->dma_ops didn't look right in the first place, it's perhaps less
> > surprising that dev->dma_io_tlb_mem might be wild as well. It doesn't seem
> > plausible that we should have a race between initialising the device and
> > probing its driver, so maybe the whole dev pointer is getting trampled
> > earlier in the callchain (or is fundamentally wrong to begin with, but from
> > a quick skim of the amdgpu code it did look like adev->dev and adev->pdev
> > are appropriately set early on by amdgpu_pci_probe()).
> >
> > > (although word of warning here: i915 dies horribly on my laptop if I pass
> > > swiotlb=force, even with the distro 5.10 kernel)
> >
> > FWIW I'd imagine you probably need to massively increase the SWIOTLB buffer
> > size to have hope of that working.
>
> Is it worth trying this still then?
>
> Cheers,
> Nathan
^ permalink raw reply related
* Re: [RFC PATCH] powerpc: flexible register range save/restore macros
From: Christophe Leroy @ 2021-07-05 5:52 UTC (permalink / raw)
To: Nicholas Piggin, linuxppc-dev
In-Reply-To: <20210703091452.352816-1-npiggin@gmail.com>
Le 03/07/2021 à 11:14, Nicholas Piggin a écrit :
> Introduce macros that operate on a (start, end) range of registers,
> which reduces lines of code and need to do mental arithmetic while
> reading the code.
Looks like a nice patch.
Maybe you could split the patch in two parts, one part for GPRs and one patch for the FP/VR regs.
Christophe
>
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
> ---
> arch/powerpc/boot/crt0.S | 31 ++++---
> arch/powerpc/crypto/md5-asm.S | 10 +--
> arch/powerpc/crypto/sha1-powerpc-asm.S | 6 +-
> arch/powerpc/include/asm/ppc_asm.h | 81 +++++++++----------
> arch/powerpc/kernel/cpu_setup_6xx.S | 2 +-
> arch/powerpc/kernel/entry_32.S | 23 +++---
> arch/powerpc/kernel/exceptions-64e.S | 14 +---
> arch/powerpc/kernel/exceptions-64s.S | 6 +-
> arch/powerpc/kernel/fpu.S | 28 +++----
> arch/powerpc/kernel/head_32.h | 3 +-
> arch/powerpc/kernel/head_booke.h | 3 +-
> arch/powerpc/kernel/interrupt_64.S | 34 +++-----
> arch/powerpc/kernel/optprobes_head.S | 4 +-
> arch/powerpc/kernel/tm.S | 47 +++++------
> .../powerpc/kernel/trace/ftrace_64_mprofile.S | 14 ++--
> arch/powerpc/kernel/vector.S | 8 +-
> arch/powerpc/kvm/book3s_hv_rmhandlers.S | 5 +-
> .../lib/test_emulate_step_exec_instr.S | 8 +-
> 18 files changed, 140 insertions(+), 187 deletions(-)
>
> diff --git a/arch/powerpc/boot/crt0.S b/arch/powerpc/boot/crt0.S
> index 1d83966f5ef6..349279ba8ce7 100644
> --- a/arch/powerpc/boot/crt0.S
> +++ b/arch/powerpc/boot/crt0.S
> @@ -226,16 +226,19 @@ p_base: mflr r10 /* r10 now points to runtime addr of p_base */
> #ifdef __powerpc64__
>
> #define PROM_FRAME_SIZE 512
> -#define SAVE_GPR(n, base) std n,8*(n)(base)
> -#define REST_GPR(n, base) ld n,8*(n)(base)
> -#define SAVE_2GPRS(n, base) SAVE_GPR(n, base); SAVE_GPR(n+1, base)
> -#define SAVE_4GPRS(n, base) SAVE_2GPRS(n, base); SAVE_2GPRS(n+2, base)
> -#define SAVE_8GPRS(n, base) SAVE_4GPRS(n, base); SAVE_4GPRS(n+4, base)
> -#define SAVE_10GPRS(n, base) SAVE_8GPRS(n, base); SAVE_2GPRS(n+8, base)
> -#define REST_2GPRS(n, base) REST_GPR(n, base); REST_GPR(n+1, base)
> -#define REST_4GPRS(n, base) REST_2GPRS(n, base); REST_2GPRS(n+2, base)
> -#define REST_8GPRS(n, base) REST_4GPRS(n, base); REST_4GPRS(n+4, base)
> -#define REST_10GPRS(n, base) REST_8GPRS(n, base); REST_2GPRS(n+8, base)
> +
> +.macro OP_REGS op, width, start, end, base, offset
> + .Lreg=\start
> + .rept (\end - \start + 1)
> + \op .Lreg,\offset+\width*.Lreg(\base)
> + .Lreg=.Lreg+1
> + .endr
> +.endm
> +
> +#define SAVE_GPRS(start, end, base) OP_REGS std, 8, start, end, base, 0
> +#define SAVE_GPR(n, base) SAVE_GPRS(n, n, base)
> +#define REST_GPRS(start, end, base) OP_REGS ld, 8, start, end, base, 0
> +#define REST_GPR(n, base) REST_GPRS(n, n, base)
>
> /* prom handles the jump into and return from firmware. The prom args pointer
> is loaded in r3. */
> @@ -246,9 +249,7 @@ prom:
> stdu r1,-PROM_FRAME_SIZE(r1) /* Save SP and create stack space */
>
> SAVE_GPR(2, r1)
> - SAVE_GPR(13, r1)
> - SAVE_8GPRS(14, r1)
> - SAVE_10GPRS(22, r1)
> + SAVE_GPRS(13, 31, r1)
> mfcr r10
> std r10,8*32(r1)
> mfmsr r10
> @@ -283,9 +284,7 @@ prom:
>
> /* Restore other registers */
> REST_GPR(2, r1)
> - REST_GPR(13, r1)
> - REST_8GPRS(14, r1)
> - REST_10GPRS(22, r1)
> + REST_GPRS(13, 31, r1)
> ld r10,8*32(r1)
> mtcr r10
>
> diff --git a/arch/powerpc/crypto/md5-asm.S b/arch/powerpc/crypto/md5-asm.S
> index 948d100a2934..8f335a3f8430 100644
> --- a/arch/powerpc/crypto/md5-asm.S
> +++ b/arch/powerpc/crypto/md5-asm.S
> @@ -38,15 +38,11 @@
>
> #define INITIALIZE \
> PPC_STLU r1,-INT_FRAME_SIZE(r1); \
> - SAVE_8GPRS(14, r1); /* push registers onto stack */ \
> - SAVE_4GPRS(22, r1); \
> - SAVE_GPR(26, r1)
> + SAVE_GPRS(14, 26, r1) /* push registers onto stack */
>
> #define FINALIZE \
> - REST_8GPRS(14, r1); /* pop registers from stack */ \
> - REST_4GPRS(22, r1); \
> - REST_GPR(26, r1); \
> - addi r1,r1,INT_FRAME_SIZE;
> + REST_GPRS(14, 26, r1); /* pop registers from stack */
> + addi r1,r1,INT_FRAME_SIZE
>
> #ifdef __BIG_ENDIAN__
> #define LOAD_DATA(reg, off) \
> diff --git a/arch/powerpc/crypto/sha1-powerpc-asm.S b/arch/powerpc/crypto/sha1-powerpc-asm.S
> index 23e248beff71..f0d5ed557ab1 100644
> --- a/arch/powerpc/crypto/sha1-powerpc-asm.S
> +++ b/arch/powerpc/crypto/sha1-powerpc-asm.S
> @@ -125,8 +125,7 @@
>
> _GLOBAL(powerpc_sha_transform)
> PPC_STLU r1,-INT_FRAME_SIZE(r1)
> - SAVE_8GPRS(14, r1)
> - SAVE_10GPRS(22, r1)
> + SAVE_GPRS(14, 31, r1)
>
> /* Load up A - E */
> lwz RA(0),0(r3) /* A */
> @@ -184,7 +183,6 @@ _GLOBAL(powerpc_sha_transform)
> stw RD(0),12(r3)
> stw RE(0),16(r3)
>
> - REST_8GPRS(14, r1)
> - REST_10GPRS(22, r1)
> + REST_GPRS(14, 31, r1)
> addi r1,r1,INT_FRAME_SIZE
> blr
> diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
> index 116c1519728a..97fa10e13bd7 100644
> --- a/arch/powerpc/include/asm/ppc_asm.h
> +++ b/arch/powerpc/include/asm/ppc_asm.h
> @@ -15,56 +15,53 @@
>
> #define SZL (BITS_PER_LONG/8)
>
> +.macro OP_REGS op, width, start, end, base, offset
> + .Lreg=\start
> + .rept (\end - \start + 1)
> + \op .Lreg, \offset + \width * .Lreg(\base)
> + .Lreg=.Lreg+1
> + .endr
> +.endm
> +
> +.macro OP_REGS_IDX op, width, start, end, tmpreg, base
> + .Lreg=\start
> + .rept (\end - \start + 1)
> + li \tmpreg, \width * .Lreg
> + \op .Lreg, \tmpreg, \base
> + .Lreg=.Lreg+1
> + .endr
> +.endm
> +
> /*
> * Macros for storing registers into and loading registers from
> * exception frames.
> */
> #ifdef __powerpc64__
> -#define SAVE_GPR(n, base) std n,GPR0+8*(n)(base)
> -#define REST_GPR(n, base) ld n,GPR0+8*(n)(base)
> -#define SAVE_NVGPRS(base) SAVE_8GPRS(14, base); SAVE_10GPRS(22, base)
> -#define REST_NVGPRS(base) REST_8GPRS(14, base); REST_10GPRS(22, base)
> +#define SAVE_GPRS(start, end, base) OP_REGS std, 8, start, end, base, GPR0
> +#define SAVE_GPR(n, base) SAVE_GPRS(n, n, base)
> +#define REST_GPRS(start, end, base) OP_REGS ld, 8, start, end, base, GPR0
> +#define REST_GPR(n, base) REST_GPRS(n, n, base)
> +#define SAVE_NVGPRS(base) SAVE_GPRS(14, 31, base)
> +#define REST_NVGPRS(base) REST_GPRS(14, 31, base)
> #else
> -#define SAVE_GPR(n, base) stw n,GPR0+4*(n)(base)
> -#define REST_GPR(n, base) lwz n,GPR0+4*(n)(base)
> -#define SAVE_NVGPRS(base) stmw 13, GPR0+4*13(base)
> -#define REST_NVGPRS(base) lmw 13, GPR0+4*13(base)
> +#define SAVE_GPRS(start, end, base) OP_REGS stw, 4, start, end, base, GPR0
> +#define SAVE_GPR(n, base) SAVE_GPRS(n, n, base)
> +#define REST_GPRS(start, end, base) OP_REGS lwz, 4, start, end, base, GPR0
> +#define REST_GPR(n, base) REST_GPRS(n, n, base)
> +#define SAVE_NVGPRS(base) stmw 13, GPR0+4*13(base)
> +#define REST_NVGPRS(base) lmw 13, GPR0+4*13(base)
> #endif
>
> -#define SAVE_2GPRS(n, base) SAVE_GPR(n, base); SAVE_GPR(n+1, base)
> -#define SAVE_4GPRS(n, base) SAVE_2GPRS(n, base); SAVE_2GPRS(n+2, base)
> -#define SAVE_8GPRS(n, base) SAVE_4GPRS(n, base); SAVE_4GPRS(n+4, base)
> -#define SAVE_10GPRS(n, base) SAVE_8GPRS(n, base); SAVE_2GPRS(n+8, base)
> -#define REST_2GPRS(n, base) REST_GPR(n, base); REST_GPR(n+1, base)
> -#define REST_4GPRS(n, base) REST_2GPRS(n, base); REST_2GPRS(n+2, base)
> -#define REST_8GPRS(n, base) REST_4GPRS(n, base); REST_4GPRS(n+4, base)
> -#define REST_10GPRS(n, base) REST_8GPRS(n, base); REST_2GPRS(n+8, base)
> -
> -#define SAVE_FPR(n, base) stfd n,8*TS_FPRWIDTH*(n)(base)
> -#define SAVE_2FPRS(n, base) SAVE_FPR(n, base); SAVE_FPR(n+1, base)
> -#define SAVE_4FPRS(n, base) SAVE_2FPRS(n, base); SAVE_2FPRS(n+2, base)
> -#define SAVE_8FPRS(n, base) SAVE_4FPRS(n, base); SAVE_4FPRS(n+4, base)
> -#define SAVE_16FPRS(n, base) SAVE_8FPRS(n, base); SAVE_8FPRS(n+8, base)
> -#define SAVE_32FPRS(n, base) SAVE_16FPRS(n, base); SAVE_16FPRS(n+16, base)
> -#define REST_FPR(n, base) lfd n,8*TS_FPRWIDTH*(n)(base)
> -#define REST_2FPRS(n, base) REST_FPR(n, base); REST_FPR(n+1, base)
> -#define REST_4FPRS(n, base) REST_2FPRS(n, base); REST_2FPRS(n+2, base)
> -#define REST_8FPRS(n, base) REST_4FPRS(n, base); REST_4FPRS(n+4, base)
> -#define REST_16FPRS(n, base) REST_8FPRS(n, base); REST_8FPRS(n+8, base)
> -#define REST_32FPRS(n, base) REST_16FPRS(n, base); REST_16FPRS(n+16, base)
> -
> -#define SAVE_VR(n,b,base) li b,16*(n); stvx n,base,b
> -#define SAVE_2VRS(n,b,base) SAVE_VR(n,b,base); SAVE_VR(n+1,b,base)
> -#define SAVE_4VRS(n,b,base) SAVE_2VRS(n,b,base); SAVE_2VRS(n+2,b,base)
> -#define SAVE_8VRS(n,b,base) SAVE_4VRS(n,b,base); SAVE_4VRS(n+4,b,base)
> -#define SAVE_16VRS(n,b,base) SAVE_8VRS(n,b,base); SAVE_8VRS(n+8,b,base)
> -#define SAVE_32VRS(n,b,base) SAVE_16VRS(n,b,base); SAVE_16VRS(n+16,b,base)
> -#define REST_VR(n,b,base) li b,16*(n); lvx n,base,b
> -#define REST_2VRS(n,b,base) REST_VR(n,b,base); REST_VR(n+1,b,base)
> -#define REST_4VRS(n,b,base) REST_2VRS(n,b,base); REST_2VRS(n+2,b,base)
> -#define REST_8VRS(n,b,base) REST_4VRS(n,b,base); REST_4VRS(n+4,b,base)
> -#define REST_16VRS(n,b,base) REST_8VRS(n,b,base); REST_8VRS(n+8,b,base)
> -#define REST_32VRS(n,b,base) REST_16VRS(n,b,base); REST_16VRS(n+16,b,base)
> +#define SAVE_FPRS(start, end, base) OP_REGS stfd, 8*TS_FPRWIDTH, start, end, base, 0
> +#define SAVE_FPR(n, base) SAVE_FPRS(n, n, base)
> +
> +#define REST_FPRS(start, end, base) OP_REGS lfd, 8*TS_FPRWIDTH, start, end, base, 0
> +#define REST_FPR(n, base) REST_FPRS(n, n, base)
> +
> +#define SAVE_VRS(start, end, reg, base) OP_REGS_IDX stvx, 16, start, end, reg, base
> +#define SAVE_VR(n, reg, base) SAVE_VRS(n, n, reg, base)
> +#define REST_VRS(start, end, reg, base) OP_REGS_IDX lvx, 16, start, end, reg, base
> +#define REST_VR(n, reg, base) REST_VRS(n, n, reg, base)
>
> #ifdef __BIG_ENDIAN__
> #define STXVD2X_ROT(n,b,base) STXVD2X(n,b,base)
> diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
> index f8b5ff64b604..a77e7fb06278 100644
> --- a/arch/powerpc/kernel/cpu_setup_6xx.S
> +++ b/arch/powerpc/kernel/cpu_setup_6xx.S
> @@ -283,7 +283,7 @@ _GLOBAL(__init_fpu_registers)
> isync
> addis r9,r3,empty_zero_page@ha
> addi r9,r9,empty_zero_page@l
> - REST_32FPRS(0,r9)
> + REST_FPRS(0, 31, r9)
> sync
> mtmsr r10
> isync
> diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
> index 0273a1349006..299b50279882 100644
> --- a/arch/powerpc/kernel/entry_32.S
> +++ b/arch/powerpc/kernel/entry_32.S
> @@ -90,8 +90,7 @@ transfer_to_syscall:
> stw r12,8(r1)
> stw r2,_TRAP(r1)
> SAVE_GPR(0, r1)
> - SAVE_4GPRS(3, r1)
> - SAVE_2GPRS(7, r1)
> + SAVE_GPRS(3, 8, r1)
> addi r2,r10,-THREAD
> SAVE_NVGPRS(r1)
>
> @@ -139,7 +138,7 @@ syscall_exit_finish:
> mtxer r5
> lwz r0,GPR0(r1)
> lwz r3,GPR3(r1)
> - REST_8GPRS(4,r1)
> + REST_GPRS(4, 11, r1)
> lwz r12,GPR12(r1)
> b 1b
>
> @@ -232,9 +231,9 @@ fast_exception_return:
> beq 3f /* if not, we've got problems */
> #endif
>
> -2: REST_4GPRS(3, r11)
> +2: REST_GPRS(3, 6, r11)
> lwz r10,_CCR(r11)
> - REST_2GPRS(1, r11)
> + REST_GPRS(1, 2, r11)
> mtcr r10
> lwz r10,_LINK(r11)
> mtlr r10
> @@ -298,16 +297,14 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
> * the reliable stack unwinder later on. Clear it.
> */
> stw r0,8(r1)
> - REST_4GPRS(7, r1)
> - REST_2GPRS(11, r1)
> + REST_GPRS(7, 12, r1)
>
> mtcr r3
> mtlr r4
> mtctr r5
> mtspr SPRN_XER,r6
>
> - REST_4GPRS(2, r1)
> - REST_GPR(6, r1)
> + REST_GPRS(2, 6, r1)
> REST_GPR(0, r1)
> REST_GPR(1, r1)
> rfi
> @@ -341,8 +338,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
> lwz r6,_CCR(r1)
> li r0,0
>
> - REST_4GPRS(7, r1)
> - REST_2GPRS(11, r1)
> + REST_GPRS(7, 12, r1)
>
> mtlr r3
> mtctr r4
> @@ -354,7 +350,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
> */
> stw r0,8(r1)
>
> - REST_4GPRS(2, r1)
> + REST_GPRS(2, 5, r1)
>
> bne- cr1,1f /* emulate stack store */
> mtcr r6
> @@ -430,8 +426,7 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return)
> bne interrupt_return; \
> lwz r0,GPR0(r1); \
> lwz r2,GPR2(r1); \
> - REST_4GPRS(3, r1); \
> - REST_2GPRS(7, r1); \
> + REST_GPRS(3, 8, r1); \
> lwz r10,_XER(r1); \
> lwz r11,_CTR(r1); \
> mtspr SPRN_XER,r10; \
> diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
> index 1401787b0b93..947d4a83704b 100644
> --- a/arch/powerpc/kernel/exceptions-64e.S
> +++ b/arch/powerpc/kernel/exceptions-64e.S
> @@ -198,8 +198,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
>
> stdcx. r0,0,r1 /* to clear the reservation */
>
> - REST_4GPRS(2, r1)
> - REST_4GPRS(6, r1)
> + REST_GPRS(2, 9, r1)
>
> ld r10,_CTR(r1)
> ld r11,_XER(r1)
> @@ -375,9 +374,7 @@ ret_from_mc_except:
> exc_##n##_common: \
> std r0,GPR0(r1); /* save r0 in stackframe */ \
> std r2,GPR2(r1); /* save r2 in stackframe */ \
> - SAVE_4GPRS(3, r1); /* save r3 - r6 in stackframe */ \
> - SAVE_2GPRS(7, r1); /* save r7, r8 in stackframe */ \
> - std r9,GPR9(r1); /* save r9 in stackframe */ \
> + SAVE_GPRS(3, 9, r1); /* save r3 - r9 in stackframe */ \
> std r10,_NIP(r1); /* save SRR0 to stackframe */ \
> std r11,_MSR(r1); /* save SRR1 to stackframe */ \
> beq 2f; /* if from kernel mode */ \
> @@ -1061,9 +1058,7 @@ bad_stack_book3e:
> std r11,_DSISR(r1)
> std r0,GPR0(r1); /* save r0 in stackframe */ \
> std r2,GPR2(r1); /* save r2 in stackframe */ \
> - SAVE_4GPRS(3, r1); /* save r3 - r6 in stackframe */ \
> - SAVE_2GPRS(7, r1); /* save r7, r8 in stackframe */ \
> - std r9,GPR9(r1); /* save r9 in stackframe */ \
> + SAVE_GPRS(3, 9, r1); /* save r3 - r9 in stackframe */ \
> ld r3,PACA_EXGEN+EX_R10(r13);/* get back r10 */ \
> ld r4,PACA_EXGEN+EX_R11(r13);/* get back r11 */ \
> mfspr r5,SPRN_SPRG_GEN_SCRATCH;/* get back r13 XXX can be wrong */ \
> @@ -1077,8 +1072,7 @@ bad_stack_book3e:
> std r10,_LINK(r1)
> std r11,_CTR(r1)
> std r12,_XER(r1)
> - SAVE_10GPRS(14,r1)
> - SAVE_8GPRS(24,r1)
> + SAVE_GPRS(14, 31, r1)
> lhz r12,PACA_TRAP_SAVE(r13)
> std r12,_TRAP(r1)
> addi r11,r1,INT_FRAME_SIZE
> diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
> index 4aec59a77d4c..4084a049a8ed 100644
> --- a/arch/powerpc/kernel/exceptions-64s.S
> +++ b/arch/powerpc/kernel/exceptions-64s.S
> @@ -574,8 +574,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
> ld r10,IAREA+EX_CTR(r13)
> std r10,_CTR(r1)
> std r2,GPR2(r1) /* save r2 in stackframe */
> - SAVE_4GPRS(3, r1) /* save r3 - r6 in stackframe */
> - SAVE_2GPRS(7, r1) /* save r7, r8 in stackframe */
> + SAVE_GPRS(3, 8, r1) /* save r3 - r8 in stackframe */
> mflr r9 /* Get LR, later save to stack */
> ld r2,PACATOC(r13) /* get kernel TOC into r2 */
> std r9,_LINK(r1)
> @@ -693,8 +692,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
> mtlr r9
> ld r9,_CCR(r1)
> mtcr r9
> - REST_8GPRS(2, r1)
> - REST_4GPRS(10, r1)
> + REST_GPRS(2, 13, r1)
> REST_GPR(0, r1)
> /* restore original r1. */
> ld r1,GPR1(r1)
> diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
> index 6010adcee16e..79b01610dae2 100644
> --- a/arch/powerpc/kernel/fpu.S
> +++ b/arch/powerpc/kernel/fpu.S
> @@ -23,29 +23,29 @@
> #include <asm/feature-fixups.h>
>
> #ifdef CONFIG_VSX
> -#define __REST_32FPVSRS(n,c,base) \
> +#define __REST_32FPVSRS(c, base) \
> BEGIN_FTR_SECTION \
> b 2f; \
> END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
> - REST_32FPRS(n,base); \
> + REST_FPRS(0, 31, base); \
> b 3f; \
> -2: REST_32VSRS(n,c,base); \
> +2: REST_32VSRS(0, c, base); \
> 3:
>
> -#define __SAVE_32FPVSRS(n,c,base) \
> +#define __SAVE_32FPVSRS(c, base) \
> BEGIN_FTR_SECTION \
> b 2f; \
> END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
> - SAVE_32FPRS(n,base); \
> + SAVE_FPRS(0, 31, base); \
> b 3f; \
> -2: SAVE_32VSRS(n,c,base); \
> +2: SAVE_32VSRS(0, c, base); \
> 3:
> #else
> -#define __REST_32FPVSRS(n,b,base) REST_32FPRS(n, base)
> -#define __SAVE_32FPVSRS(n,b,base) SAVE_32FPRS(n, base)
> +#define __REST_32FPVSRS(c, base) REST_FPRS(0, 31, base)
> +#define __SAVE_32FPVSRS(c, base) SAVE_FPRS(0, 31, base)
> #endif
> -#define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base)
> -#define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base)
> +#define REST_32FPVSRS(c, base) __REST_32FPVSRS(__REG_##c, __REG_##base)
> +#define SAVE_32FPVSRS(c, base) __SAVE_32FPVSRS(__REG_##c, __REG_##base)
>
> /*
> * Load state from memory into FP registers including FPSCR.
> @@ -54,7 +54,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
> _GLOBAL(load_fp_state)
> lfd fr0,FPSTATE_FPSCR(r3)
> MTFSF_L(fr0)
> - REST_32FPVSRS(0, R4, R3)
> + REST_32FPVSRS(R4, R3)
> blr
> EXPORT_SYMBOL(load_fp_state)
> _ASM_NOKPROBE_SYMBOL(load_fp_state); /* used by restore_math */
> @@ -64,7 +64,7 @@ _ASM_NOKPROBE_SYMBOL(load_fp_state); /* used by restore_math */
> * Assumes the caller has enabled FP in the MSR.
> */
> _GLOBAL(store_fp_state)
> - SAVE_32FPVSRS(0, R4, R3)
> + SAVE_32FPVSRS(R4, R3)
> mffs fr0
> stfd fr0,FPSTATE_FPSCR(r3)
> blr
> @@ -113,7 +113,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
> addi r10,r5,THREAD_FPSTATE
> lfd fr0,FPSTATE_FPSCR(r10)
> MTFSF_L(fr0)
> - REST_32FPVSRS(0, R4, R10)
> + REST_32FPVSRS(R4, R10)
> /* restore registers and return */
> /* we haven't used ctr or xer or lr */
> blr
> @@ -131,7 +131,7 @@ _GLOBAL(save_fpu)
> PPC_LCMPI 0,r6,0
> bne 2f
> addi r6,r3,THREAD_FPSTATE
> -2: SAVE_32FPVSRS(0, R4, R6)
> +2: SAVE_32FPVSRS(R4, R6)
> mffs fr0
> stfd fr0,FPSTATE_FPSCR(r6)
> blr
> diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
> index 6b1ec9e3541b..25887303651a 100644
> --- a/arch/powerpc/kernel/head_32.h
> +++ b/arch/powerpc/kernel/head_32.h
> @@ -115,8 +115,7 @@ _ASM_NOKPROBE_SYMBOL(\name\()_virt)
> stw r10,8(r1)
> li r10, \trapno
> stw r10,_TRAP(r1)
> - SAVE_4GPRS(3, r1)
> - SAVE_2GPRS(7, r1)
> + SAVE_GPRS(3, 8, r1)
> SAVE_NVGPRS(r1)
> stw r2,GPR2(r1)
> stw r12,_NIP(r1)
> diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
> index 87b806e8eded..5691e49d3368 100644
> --- a/arch/powerpc/kernel/head_booke.h
> +++ b/arch/powerpc/kernel/head_booke.h
> @@ -87,8 +87,7 @@ END_BTB_FLUSH_SECTION
> stw r10, 8(r1)
> li r10, \trapno
> stw r10,_TRAP(r1)
> - SAVE_4GPRS(3, r1)
> - SAVE_2GPRS(7, r1)
> + SAVE_GPRS(3, 8, r1)
> SAVE_NVGPRS(r1)
> stw r2,GPR2(r1)
> stw r12,_NIP(r1)
> diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S
> index 4063e8a3f704..03d053ff87c7 100644
> --- a/arch/powerpc/kernel/interrupt_64.S
> +++ b/arch/powerpc/kernel/interrupt_64.S
> @@ -169,10 +169,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
> * The value of AMR only matters while we're in the kernel.
> */
> mtcr r2
> - ld r2,GPR2(r1)
> - ld r3,GPR3(r1)
> - ld r13,GPR13(r1)
> - ld r1,GPR1(r1)
> + REST_GPRS(2, 3, r1)
> + REST_GPR(13, r1)
> + REST_GPR(1, r1)
> RFSCV_TO_USER
> b . /* prevent speculative execution */
>
> @@ -190,9 +189,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
> mtctr r3
> mtlr r4
> mtspr SPRN_XER,r5
> - REST_10GPRS(2, r1)
> - REST_2GPRS(12, r1)
> - ld r1,GPR1(r1)
> + REST_GPRS(2, 13, r1)
> + REST_GPR(1, r1)
> RFI_TO_USER
> .Lsyscall_vectored_\name\()_rst_end:
>
> @@ -383,10 +381,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
> * The value of AMR only matters while we're in the kernel.
> */
> mtcr r2
> - ld r2,GPR2(r1)
> - ld r3,GPR3(r1)
> - ld r13,GPR13(r1)
> - ld r1,GPR1(r1)
> + REST_GPRS(2, 3, r1)
> + REST_GPR(13, r1)
> + REST_GPR(1, r1)
> RFI_TO_USER
> b . /* prevent speculative execution */
>
> @@ -397,8 +394,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
> mtctr r3
> mtspr SPRN_XER,r4
> ld r0,GPR0(r1)
> - REST_8GPRS(4, r1)
> - ld r12,GPR12(r1)
> + REST_GPRS(4, 12, r1)
> b .Lsyscall_restore_regs_cont
> .Lsyscall_rst_end:
>
> @@ -555,17 +551,14 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
> ld r6,_XER(r1)
> li r0,0
>
> - REST_4GPRS(7, r1)
> - REST_2GPRS(11, r1)
> - REST_GPR(13, r1)
> + REST_GPRS(7, 13, r1)
>
> mtcr r3
> mtlr r4
> mtctr r5
> mtspr SPRN_XER,r6
>
> - REST_4GPRS(2, r1)
> - REST_GPR(6, r1)
> + REST_GPRS(2, 6, r1)
> REST_GPR(0, r1)
> REST_GPR(1, r1)
> .ifc \srr,srr
> @@ -662,8 +655,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
> ld r6,_CCR(r1)
> li r0,0
>
> - REST_4GPRS(7, r1)
> - REST_2GPRS(11, r1)
> + REST_GPRS(7, 12, r1)
>
> mtlr r3
> mtctr r4
> @@ -675,7 +667,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
> */
> std r0,STACK_FRAME_OVERHEAD-16(r1)
>
> - REST_4GPRS(2, r1)
> + REST_GPRS(2, 5, r1)
>
> bne- cr1,1f /* emulate stack store */
> mtcr r6
> diff --git a/arch/powerpc/kernel/optprobes_head.S b/arch/powerpc/kernel/optprobes_head.S
> index 19ea3312403c..5c7f0b4b784b 100644
> --- a/arch/powerpc/kernel/optprobes_head.S
> +++ b/arch/powerpc/kernel/optprobes_head.S
> @@ -10,8 +10,8 @@
> #include <asm/asm-offsets.h>
>
> #ifdef CONFIG_PPC64
> -#define SAVE_30GPRS(base) SAVE_10GPRS(2,base); SAVE_10GPRS(12,base); SAVE_10GPRS(22,base)
> -#define REST_30GPRS(base) REST_10GPRS(2,base); REST_10GPRS(12,base); REST_10GPRS(22,base)
> +#define SAVE_30GPRS(base) SAVE_GPRS(2, 31, base)
> +#define REST_30GPRS(base) REST_GPRS(2, 31, base)
> #define TEMPLATE_FOR_IMM_LOAD_INSNS nop; nop; nop; nop; nop
> #else
> #define SAVE_30GPRS(base) stmw r2, GPR2(base)
> diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
> index 2b91f233b05d..dd382ba5926a 100644
> --- a/arch/powerpc/kernel/tm.S
> +++ b/arch/powerpc/kernel/tm.S
> @@ -17,30 +17,30 @@
>
> #ifdef CONFIG_VSX
> /* See fpu.S, this is borrowed from there */
> -#define __SAVE_32FPRS_VSRS(n,c,base) \
> +#define __SAVE_32FPRS_VSRS(c, base) \
> BEGIN_FTR_SECTION \
> b 2f; \
> END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
> - SAVE_32FPRS(n,base); \
> + SAVE_FPRS(0, 31, base); \
> b 3f; \
> -2: SAVE_32VSRS(n,c,base); \
> +2: SAVE_32VSRS(0, c, base); \
> 3:
> -#define __REST_32FPRS_VSRS(n,c,base) \
> +#define __REST_32FPRS_VSRS(c, base) \
> BEGIN_FTR_SECTION \
> b 2f; \
> END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
> - REST_32FPRS(n,base); \
> + REST_FPRS(0, 31, base); \
> b 3f; \
> -2: REST_32VSRS(n,c,base); \
> +2: REST_32VSRS(0, c, base); \
> 3:
> #else
> -#define __SAVE_32FPRS_VSRS(n,c,base) SAVE_32FPRS(n, base)
> -#define __REST_32FPRS_VSRS(n,c,base) REST_32FPRS(n, base)
> +#define __SAVE_32FPRS_VSRS(c,base) SAVE_FPRS(0, 31, base)
> +#define __REST_32FPRS_VSRS(c,base) REST_FPRS(0, 31, base)
> #endif
> -#define SAVE_32FPRS_VSRS(n,c,base) \
> - __SAVE_32FPRS_VSRS(n,__REG_##c,__REG_##base)
> -#define REST_32FPRS_VSRS(n,c,base) \
> - __REST_32FPRS_VSRS(n,__REG_##c,__REG_##base)
> +#define SAVE_32FPRS_VSRS(c, base) \
> + __SAVE_32FPRS_VSRS(__REG_##c, __REG_##base)
> +#define REST_32FPRS_VSRS(c, base) \
> + __REST_32FPRS_VSRS(__REG_##c, __REG_##base)
>
> /* Stack frame offsets for local variables. */
> #define TM_FRAME_L0 TM_FRAME_SIZE-16
> @@ -226,11 +226,8 @@ _GLOBAL(tm_reclaim)
>
> /* Sync the userland GPRs 2-12, 14-31 to thread->regs: */
> SAVE_GPR(0, r7) /* user r0 */
> - SAVE_GPR(2, r7) /* user r2 */
> - SAVE_4GPRS(3, r7) /* user r3-r6 */
> - SAVE_GPR(8, r7) /* user r8 */
> - SAVE_GPR(9, r7) /* user r9 */
> - SAVE_GPR(10, r7) /* user r10 */
> + SAVE_GPRS(2, 6, r7) /* user r2-r6 */
> + SAVE_GPRS(8, 10, r7) /* user r8-r10 */
> ld r3, GPR1(r1) /* user r1 */
> ld r4, GPR7(r1) /* user r7 */
> ld r5, GPR11(r1) /* user r11 */
> @@ -290,7 +287,7 @@ _GLOBAL(tm_reclaim)
>
> /* Altivec (VEC/VMX/VR)*/
> addi r7, r3, THREAD_CKVRSTATE
> - SAVE_32VRS(0, r6, r7) /* r6 scratch, r7 ckvr_state */
> + SAVE_VRS(0, 31, r6, r7) /* r6 scratch, r7 ckvr_state */
> mfvscr v0
> li r6, VRSTATE_VSCR
> stvx v0, r7, r6
> @@ -301,7 +298,7 @@ _GLOBAL(tm_reclaim)
>
> /* Floating Point (FP) */
> addi r7, r3, THREAD_CKFPSTATE
> - SAVE_32FPRS_VSRS(0, R6, R7) /* r6 scratch, r7 ckfp_state */
> + SAVE_32FPRS_VSRS(R6, R7) /* r6 scratch, r7 ckfp_state */
> mffs fr0
> stfd fr0,FPSTATE_FPSCR(r7)
>
> @@ -409,7 +406,7 @@ _GLOBAL(__tm_recheckpoint)
> li r5, VRSTATE_VSCR
> lvx v0, r8, r5
> mtvscr v0
> - REST_32VRS(0, r5, r8) /* r5 scratch, r8 ptr */
> + REST_VRS(0, 31, r5, r8) /* r5 scratch, r8 ptr */
> ld r5, THREAD_CKVRSAVE(r3)
> mtspr SPRN_VRSAVE, r5
> #endif
> @@ -417,7 +414,7 @@ _GLOBAL(__tm_recheckpoint)
> addi r8, r3, THREAD_CKFPSTATE
> lfd fr0, FPSTATE_FPSCR(r8)
> MTFSF_L(fr0)
> - REST_32FPRS_VSRS(0, R4, R8)
> + REST_32FPRS_VSRS(R4, R8)
>
> mtmsr r6 /* FP/Vec off again! */
>
> @@ -445,12 +442,8 @@ restore_gprs:
> ld r6, THREAD_TM_PPR(r3)
>
> REST_GPR(0, r7) /* GPR0 */
> - REST_2GPRS(2, r7) /* GPR2-3 */
> - REST_GPR(4, r7) /* GPR4 */
> - REST_4GPRS(8, r7) /* GPR8-11 */
> - REST_2GPRS(12, r7) /* GPR12-13 */
> -
> - REST_NVGPRS(r7) /* GPR14-31 */
> + REST_GPRS(2, 4, r7) /* GPR2-4 */
> + REST_GPRS(8, 31, r7) /* GPR8-31 */
>
> /* Load up PPR and DSCR here so we don't run with user values for long */
> mtspr SPRN_DSCR, r5
> diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
> index f9fd5f743eba..dd5e720fe44b 100644
> --- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
> +++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
> @@ -41,15 +41,14 @@ _GLOBAL(ftrace_regs_caller)
>
> /* Save all gprs to pt_regs */
> SAVE_GPR(0, r1)
> - SAVE_10GPRS(2, r1)
> + SAVE_GPRS(2, 11, r1)
>
> /* Ok to continue? */
> lbz r3, PACA_FTRACE_ENABLED(r13)
> cmpdi r3, 0
> beq ftrace_no_trace
>
> - SAVE_10GPRS(12, r1)
> - SAVE_10GPRS(22, r1)
> + SAVE_GPRS(12, 31, r1)
>
> /* Save previous stack pointer (r1) */
> addi r8, r1, SWITCH_FRAME_SIZE
> @@ -108,10 +107,7 @@ ftrace_regs_call:
> #endif
>
> /* Restore gprs */
> - REST_GPR(0,r1)
> - REST_10GPRS(2,r1)
> - REST_10GPRS(12,r1)
> - REST_10GPRS(22,r1)
> + REST_GPRS(2, 31, r1)
>
> /* Restore possibly modified LR */
> ld r0, _LINK(r1)
> @@ -157,7 +153,7 @@ _GLOBAL(ftrace_caller)
> stdu r1, -SWITCH_FRAME_SIZE(r1)
>
> /* Save all gprs to pt_regs */
> - SAVE_8GPRS(3, r1)
> + SAVE_GPRS(3, 10, r1)
>
> lbz r3, PACA_FTRACE_ENABLED(r13)
> cmpdi r3, 0
> @@ -194,7 +190,7 @@ ftrace_call:
> mtctr r3
>
> /* Restore gprs */
> - REST_8GPRS(3,r1)
> + REST_GPRS(3, 10, r1)
>
> /* Restore callee's TOC */
> ld r2, 24(r1)
> diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
> index fc120fac1910..66071dc19452 100644
> --- a/arch/powerpc/kernel/vector.S
> +++ b/arch/powerpc/kernel/vector.S
> @@ -18,7 +18,7 @@ _GLOBAL(load_vr_state)
> li r4,VRSTATE_VSCR
> lvx v0,r4,r3
> mtvscr v0
> - REST_32VRS(0,r4,r3)
> + REST_VRS(0, 31, r4, r3)
> blr
> EXPORT_SYMBOL(load_vr_state)
> _ASM_NOKPROBE_SYMBOL(load_vr_state); /* used by restore_math */
> @@ -28,7 +28,7 @@ _ASM_NOKPROBE_SYMBOL(load_vr_state); /* used by restore_math */
> * Assumes the caller has enabled VMX in the MSR.
> */
> _GLOBAL(store_vr_state)
> - SAVE_32VRS(0, r4, r3)
> + SAVE_VRS(0, 31, r4, r3)
> mfvscr v0
> li r4, VRSTATE_VSCR
> stvx v0, r4, r3
> @@ -86,7 +86,7 @@ _GLOBAL(load_up_altivec)
> stw r4,THREAD_USED_VR(r5)
> lvx v0,r10,r6
> mtvscr v0
> - REST_32VRS(0,r4,r6)
> + REST_VRS(0, 31, r4, r6)
> /* restore registers and return */
> blr
> _ASM_NOKPROBE_SYMBOL(load_up_altivec)
> @@ -102,7 +102,7 @@ _GLOBAL(save_altivec)
> PPC_LCMPI 0,r7,0
> bne 2f
> addi r7,r3,THREAD_VRSTATE
> -2: SAVE_32VRS(0,r4,r7)
> +2: SAVE_VRS(0, 31, r4, r7)
> mfvscr v0
> li r4,VRSTATE_VSCR
> stvx v0,r4,r7
> diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
> index 8dd437d7a2c6..37ee440cc35e 100644
> --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
> +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
> @@ -2715,8 +2715,7 @@ kvmppc_bad_host_intr:
> std r0, GPR0(r1)
> std r9, GPR1(r1)
> std r2, GPR2(r1)
> - SAVE_4GPRS(3, r1)
> - SAVE_2GPRS(7, r1)
> + SAVE_GPRS(3, 8, r1)
> srdi r0, r12, 32
> clrldi r12, r12, 32
> std r0, _CCR(r1)
> @@ -2739,7 +2738,7 @@ kvmppc_bad_host_intr:
> ld r9, HSTATE_SCRATCH2(r13)
> ld r12, HSTATE_SCRATCH0(r13)
> GET_SCRATCH0(r0)
> - SAVE_4GPRS(9, r1)
> + SAVE_GPRS(9, 12, r1)
> std r0, GPR13(r1)
> SAVE_NVGPRS(r1)
> ld r5, HSTATE_CFAR(r13)
> diff --git a/arch/powerpc/lib/test_emulate_step_exec_instr.S b/arch/powerpc/lib/test_emulate_step_exec_instr.S
> index 9ef941d958d8..5473f9d03df3 100644
> --- a/arch/powerpc/lib/test_emulate_step_exec_instr.S
> +++ b/arch/powerpc/lib/test_emulate_step_exec_instr.S
> @@ -37,7 +37,7 @@ _GLOBAL(exec_instr)
> * The stack pointer (GPR1) and the thread pointer (GPR13) are not
> * saved as these should not be modified anyway.
> */
> - SAVE_2GPRS(2, r1)
> + SAVE_GPRS(2, 3, r1)
> SAVE_NVGPRS(r1)
>
> /*
> @@ -75,8 +75,7 @@ _GLOBAL(exec_instr)
>
> /* Load GPRs from pt_regs */
> REST_GPR(0, r31)
> - REST_10GPRS(2, r31)
> - REST_GPR(12, r31)
> + REST_GPRS(2, 12, r31)
> REST_NVGPRS(r31)
>
> /* Placeholder for the test instruction */
> @@ -99,8 +98,7 @@ _GLOBAL(exec_instr)
> subi r3, r3, GPR0
> SAVE_GPR(0, r3)
> SAVE_GPR(2, r3)
> - SAVE_8GPRS(4, r3)
> - SAVE_GPR(12, r3)
> + SAVE_GPRS(4, 12, r3)
> SAVE_NVGPRS(r3)
>
> /* Save resulting LR to pt_regs */
>
^ permalink raw reply
* Re: [PATCH v8 3/6] KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE
From: David Gibson @ 2021-07-05 4:42 UTC (permalink / raw)
To: Bharata B Rao; +Cc: farosas, aneesh.kumar, npiggin, kvm-ppc, linuxppc-dev
In-Reply-To: <20210621085003.904767-4-bharata@linux.ibm.com>
[-- Attachment #1: Type: text/plain, Size: 15932 bytes --]
On Mon, Jun 21, 2021 at 02:20:00PM +0530, Bharata B Rao wrote:
> H_RPT_INVALIDATE does two types of TLB invalidations:
>
> 1. Process-scoped invalidations for guests when LPCR[GTSE]=0.
> This is currently not used in KVM as GTSE is not usually
> disabled in KVM.
> 2. Partition-scoped invalidations that an L1 hypervisor does on
> behalf of an L2 guest. This is currently handled
> by H_TLB_INVALIDATE hcall and this new replaces the old that.
>
> This commit enables process-scoped invalidations for L1 guests.
> Support for process-scoped and partition-scoped invalidations
> from/for nested guests will be added separately.
>
> Process scoped tlbie invalidations from L1 and nested guests
> need RS register for TLBIE instruction to contain both PID and
> LPID. This patch introduces primitives that execute tlbie
> instruction with both PID and LPID set in prepartion for
> H_RPT_INVALIDATE hcall.
>
> A description of H_RPT_INVALIDATE follows:
>
> int64 /* H_Success: Return code on successful completion */
> /* H_Busy - repeat the call with the same */
> /* H_Parameter, H_P2, H_P3, H_P4, H_P5 : Invalid
> parameters */
> hcall(const uint64 H_RPT_INVALIDATE, /* Invalidate RPT
> translation
> lookaside information */
> uint64 id, /* PID/LPID to invalidate */
> uint64 target, /* Invalidation target */
> uint64 type, /* Type of lookaside information */
> uint64 pg_sizes, /* Page sizes */
> uint64 start, /* Start of Effective Address (EA)
> range (inclusive) */
> uint64 end) /* End of EA range (exclusive) */
>
> Invalidation targets (target)
> -----------------------------
> Core MMU 0x01 /* All virtual processors in the
> partition */
> Core local MMU 0x02 /* Current virtual processor */
> Nest MMU 0x04 /* All nest/accelerator agents
> in use by the partition */
>
> A combination of the above can be specified,
> except core and core local.
>
> Type of translation to invalidate (type)
> ---------------------------------------
> NESTED 0x0001 /* invalidate nested guest partition-scope */
> TLB 0x0002 /* Invalidate TLB */
> PWC 0x0004 /* Invalidate Page Walk Cache */
> PRT 0x0008 /* Invalidate caching of Process Table
> Entries if NESTED is clear */
> PAT 0x0008 /* Invalidate caching of Partition Table
> Entries if NESTED is set */
>
> A combination of the above can be specified.
>
> Page size mask (pages)
> ----------------------
> 4K 0x01
> 64K 0x02
> 2M 0x04
> 1G 0x08
> All sizes (-1UL)
>
> A combination of the above can be specified.
> All page sizes can be selected with -1.
>
> Semantics: Invalidate radix tree lookaside information
> matching the parameters given.
> * Return H_P2, H_P3 or H_P4 if target, type, or pageSizes parameters
> are different from the defined values.
> * Return H_PARAMETER if NESTED is set and pid is not a valid nested
> LPID allocated to this partition
> * Return H_P5 if (start, end) doesn't form a valid range. Start and
> end should be a valid Quadrant address and end > start.
> * Return H_NotSupported if the partition is not in running in radix
> translation mode.
> * May invalidate more translation information than requested.
> * If start = 0 and end = -1, set the range to cover all valid
> addresses. Else start and end should be aligned to 4kB (lower 11
> bits clear).
> * If NESTED is clear, then invalidate process scoped lookaside
> information. Else pid specifies a nested LPID, and the invalidation
> is performed on nested guest partition table and nested guest
> partition scope real addresses.
> * If pid = 0 and NESTED is clear, then valid addresses are quadrant 3
> and quadrant 0 spaces, Else valid addresses are quadrant 0.
> * Pages which are fully covered by the range are to be invalidated.
> Those which are partially covered are considered outside
> invalidation range, which allows a caller to optimally invalidate
> ranges that may contain mixed page sizes.
> * Return H_SUCCESS on success.
>
> Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
> ---
> arch/powerpc/include/asm/mmu_context.h | 9 ++
> arch/powerpc/kvm/book3s_hv.c | 36 ++++++
> arch/powerpc/mm/book3s64/radix_tlb.c | 172 +++++++++++++++++++++++++
> 3 files changed, 217 insertions(+)
>
> diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
> index 4bc45d3ed8b0..b44f291fc909 100644
> --- a/arch/powerpc/include/asm/mmu_context.h
> +++ b/arch/powerpc/include/asm/mmu_context.h
> @@ -124,8 +124,17 @@ static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea)
>
> #if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU)
> extern void radix_kvm_prefetch_workaround(struct mm_struct *mm);
> +void do_h_rpt_invalidate_prt(unsigned long pid, unsigned long lpid,
> + unsigned long type, unsigned long pg_sizes,
> + unsigned long start, unsigned long end);
> #else
> static inline void radix_kvm_prefetch_workaround(struct mm_struct *mm) { }
> +static inline void do_h_rpt_invalidate_prt(unsigned long pid,
> + unsigned long lpid,
> + unsigned long type,
> + unsigned long pg_sizes,
> + unsigned long start,
> + unsigned long end) { }
Since the only plausible caller is in KVM HV code, why do you need the
#else clause.
> #endif
>
> extern void switch_cop(struct mm_struct *next);
> diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
> index bc0813644666..7e6da4687d88 100644
> --- a/arch/powerpc/kvm/book3s_hv.c
> +++ b/arch/powerpc/kvm/book3s_hv.c
> @@ -76,6 +76,7 @@
> #include <asm/kvm_book3s_uvmem.h>
> #include <asm/ultravisor.h>
> #include <asm/dtl.h>
> +#include <asm/plpar_wrappers.h>
>
> #include "book3s.h"
>
> @@ -924,6 +925,32 @@ static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu)
> return yield_count;
> }
>
> +static long kvmppc_h_rpt_invalidate(struct kvm_vcpu *vcpu,
> + unsigned long id, unsigned long target,
> + unsigned long type, unsigned long pg_sizes,
> + unsigned long start, unsigned long end)
> +{
> + if (!kvm_is_radix(vcpu->kvm))
> + return H_UNSUPPORTED;
> +
> + if (end < start)
> + return H_P5;
> +
> + /*
> + * Partition-scoped invalidation for nested guests.
> + * Not yet supported
> + */
> + if (type & H_RPTI_TYPE_NESTED)
> + return H_P3;
> +
> + /*
> + * Process-scoped invalidation for L1 guests.
> + */
> + do_h_rpt_invalidate_prt(id, vcpu->kvm->arch.lpid,
> + type, pg_sizes, start, end);
> + return H_SUCCESS;
> +}
> +
> int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
> {
> unsigned long req = kvmppc_get_gpr(vcpu, 3);
> @@ -1132,6 +1159,14 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
> */
> ret = kvmppc_h_svm_init_abort(vcpu->kvm);
> break;
> + case H_RPT_INVALIDATE:
> + ret = kvmppc_h_rpt_invalidate(vcpu, kvmppc_get_gpr(vcpu, 4),
> + kvmppc_get_gpr(vcpu, 5),
> + kvmppc_get_gpr(vcpu, 6),
> + kvmppc_get_gpr(vcpu, 7),
> + kvmppc_get_gpr(vcpu, 8),
> + kvmppc_get_gpr(vcpu, 9));
> + break;
>
> default:
> return RESUME_HOST;
> @@ -1178,6 +1213,7 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)
> case H_XIRR_X:
> #endif
> case H_PAGE_INIT:
> + case H_RPT_INVALIDATE:
> return 1;
> }
>
> diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
> index 409e61210789..cdd98b9e7b15 100644
> --- a/arch/powerpc/mm/book3s64/radix_tlb.c
> +++ b/arch/powerpc/mm/book3s64/radix_tlb.c
> @@ -130,6 +130,21 @@ static __always_inline void __tlbie_pid(unsigned long pid, unsigned long ric)
> trace_tlbie(0, 0, rb, rs, ric, prs, r);
> }
>
> +static __always_inline void __tlbie_pid_lpid(unsigned long pid,
> + unsigned long lpid,
> + unsigned long ric)
> +{
> + unsigned long rb, rs, prs, r;
> +
> + rb = PPC_BIT(53); /* IS = 1 */
> + rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
> + prs = 1; /* process scoped */
> + r = 1; /* radix format */
> +
> + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
> + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
> + trace_tlbie(0, 0, rb, rs, ric, prs, r);
> +}
> static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric)
> {
> unsigned long rb,rs,prs,r;
> @@ -190,6 +205,23 @@ static __always_inline void __tlbie_va(unsigned long va, unsigned long pid,
> trace_tlbie(0, 0, rb, rs, ric, prs, r);
> }
>
> +static __always_inline void __tlbie_va_lpid(unsigned long va, unsigned long pid,
> + unsigned long lpid,
> + unsigned long ap, unsigned long ric)
> +{
> + unsigned long rb, rs, prs, r;
> +
> + rb = va & ~(PPC_BITMASK(52, 63));
> + rb |= ap << PPC_BITLSHIFT(58);
> + rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
> + prs = 1; /* process scoped */
> + r = 1; /* radix format */
> +
> + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
> + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
> + trace_tlbie(0, 0, rb, rs, ric, prs, r);
> +}
> +
> static __always_inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid,
> unsigned long ap, unsigned long ric)
> {
> @@ -235,6 +267,22 @@ static inline void fixup_tlbie_va_range(unsigned long va, unsigned long pid,
> }
> }
>
> +static inline void fixup_tlbie_va_range_lpid(unsigned long va,
> + unsigned long pid,
> + unsigned long lpid,
> + unsigned long ap)
> +{
> + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
> + asm volatile("ptesync" : : : "memory");
> + __tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
> + }
> +
> + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
> + asm volatile("ptesync" : : : "memory");
> + __tlbie_va_lpid(va, pid, lpid, ap, RIC_FLUSH_TLB);
> + }
> +}
> +
> static inline void fixup_tlbie_pid(unsigned long pid)
> {
> /*
> @@ -254,6 +302,25 @@ static inline void fixup_tlbie_pid(unsigned long pid)
> }
> }
>
> +static inline void fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid)
> +{
> + /*
> + * We can use any address for the invalidation, pick one which is
> + * probably unused as an optimisation.
> + */
> + unsigned long va = ((1UL << 52) - 1);
> +
> + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
> + asm volatile("ptesync" : : : "memory");
> + __tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
> + }
> +
> + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
> + asm volatile("ptesync" : : : "memory");
> + __tlbie_va_lpid(va, pid, lpid, mmu_get_ap(MMU_PAGE_64K),
> + RIC_FLUSH_TLB);
> + }
> +}
>
> static inline void fixup_tlbie_lpid_va(unsigned long va, unsigned long lpid,
> unsigned long ap)
> @@ -344,6 +411,31 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
> asm volatile("eieio; tlbsync; ptesync": : :"memory");
> }
>
> +static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid,
> + unsigned long ric)
> +{
> + asm volatile("ptesync" : : : "memory");
> +
> + /*
> + * Workaround the fact that the "ric" argument to __tlbie_pid
> + * must be a compile-time contraint to match the "i" constraint
> + * in the asm statement.
> + */
> + switch (ric) {
> + case RIC_FLUSH_TLB:
> + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
> + fixup_tlbie_pid_lpid(pid, lpid);
> + break;
> + case RIC_FLUSH_PWC:
> + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
> + break;
> + case RIC_FLUSH_ALL:
> + default:
> + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL);
> + fixup_tlbie_pid_lpid(pid, lpid);
> + }
> + asm volatile("eieio; tlbsync; ptesync" : : : "memory");
> +}
> struct tlbiel_pid {
> unsigned long pid;
> unsigned long ric;
> @@ -469,6 +561,20 @@ static inline void __tlbie_va_range(unsigned long start, unsigned long end,
> fixup_tlbie_va_range(addr - page_size, pid, ap);
> }
>
> +static inline void __tlbie_va_range_lpid(unsigned long start, unsigned long end,
> + unsigned long pid, unsigned long lpid,
> + unsigned long page_size,
> + unsigned long psize)
> +{
> + unsigned long addr;
> + unsigned long ap = mmu_get_ap(psize);
> +
> + for (addr = start; addr < end; addr += page_size)
> + __tlbie_va_lpid(addr, pid, lpid, ap, RIC_FLUSH_TLB);
> +
> + fixup_tlbie_va_range_lpid(addr - page_size, pid, lpid, ap);
> +}
> +
> static __always_inline void _tlbie_va(unsigned long va, unsigned long pid,
> unsigned long psize, unsigned long ric)
> {
> @@ -549,6 +655,18 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end,
> asm volatile("eieio; tlbsync; ptesync": : :"memory");
> }
>
> +static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end,
> + unsigned long pid, unsigned long lpid,
> + unsigned long page_size,
> + unsigned long psize, bool also_pwc)
> +{
> + asm volatile("ptesync" : : : "memory");
> + if (also_pwc)
> + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
> + __tlbie_va_range_lpid(start, end, pid, lpid, page_size, psize);
> + asm volatile("eieio; tlbsync; ptesync" : : : "memory");
> +}
> +
> static inline void _tlbiel_va_range_multicast(struct mm_struct *mm,
> unsigned long start, unsigned long end,
> unsigned long pid, unsigned long page_size,
> @@ -1381,4 +1499,58 @@ extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
> }
> }
> EXPORT_SYMBOL_GPL(radix_kvm_prefetch_workaround);
> +
> +/*
> + * Performs process-scoped invalidations for a given LPID
> + * as part of H_RPT_INVALIDATE hcall.
> + */
> +void do_h_rpt_invalidate_prt(unsigned long pid, unsigned long lpid,
> + unsigned long type, unsigned long pg_sizes,
> + unsigned long start, unsigned long end)
> +{
> + unsigned long psize, nr_pages;
> + struct mmu_psize_def *def;
> + bool flush_pid;
> +
> + /*
> + * A H_RPTI_TYPE_ALL request implies RIC=3, hence
> + * do a single IS=1 based flush.
> + */
> + if ((type & H_RPTI_TYPE_ALL) == H_RPTI_TYPE_ALL) {
> + _tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL);
> + return;
> + }
> +
> + if (type & H_RPTI_TYPE_PWC)
> + _tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
> +
> + /* Full PID flush */
> + if (start == 0 && end == -1)
> + return _tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
> +
> + /* Do range invalidation for all the valid page sizes */
> + for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
> + def = &mmu_psize_defs[psize];
> + if (!(pg_sizes & def->h_rpt_pgsize))
> + continue;
> +
> + nr_pages = (end - start) >> def->shift;
> + flush_pid = nr_pages > tlb_single_page_flush_ceiling;
> +
> + /*
> + * If the number of pages spanning the range is above
> + * the ceiling, convert the request into a full PID flush.
> + * And since PID flush takes out all the page sizes, there
> + * is no need to consider remaining page sizes.
> + */
> + if (flush_pid) {
> + _tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
> + return;
> + }
> + _tlbie_va_range_lpid(start, end, pid, lpid,
> + (1UL << def->shift), psize, false);
> + }
> +}
> +EXPORT_SYMBOL_GPL(do_h_rpt_invalidate_prt);
> +
> #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply
* Re: [powerpc][5.13.0-next-20210701] Kernel crash while running ltp(chdir01) tests
From: Zhang Yi @ 2021-07-05 2:17 UTC (permalink / raw)
To: Theodore Ts'o
Cc: Sachin Sant, Jan Kara, Guoqing Jiang,
linux-fsdevel@vger.kernel.org, Ext4 Developers List, linuxppc-dev
In-Reply-To: <YOG/5ZY1AL05jumi@mit.edu>
On 2021/7/4 22:04, Theodore Ts'o wrote:
> On Sat, Jul 03, 2021 at 12:55:09PM +0800, Zhang Yi wrote:
>> Yeah, it sounds good to me. Do you want me to send the fix patch, or you
>> modify your commit 8f9e16badb8fd in another email directly?
>
> I've gone ahead and made the changes; what do you think?
>
> I like how it also removes 40 lines of code. :-)
>
Thanks for the fix, this patch looks good to me besides one error
handling below.
>
>>From ef3130d1b0b8ca769252d6a722a2e59a00141383 Mon Sep 17 00:00:00 2001
> From: Theodore Ts'o <tytso@mit.edu>
> Date: Fri, 2 Jul 2021 18:05:03 -0400
> Subject: [PATCH] ext4: inline jbd2_journal_[un]register_shrinker()
>
> The function jbd2_journal_unregister_shrinker() was getting called
> twice when the file system was getting unmounted. On Power and ARM
> platforms this was causing kernel crash when unmounting the file
> system, when a percpu_counter was destroyed twice.
>
> Fix this by removing jbd2_journal_[un]register_shrinker() functions,
> and inlining the shrinker setup and teardown into
> journal_init_common() and jbd2_journal_destroy(). This means that
> ext4 and ocfs2 now no longer need to know about registering and
> unregistering jbd2's shrinker.
>
> Also, while we're at it, rename the percpu counter from
> j_jh_shrink_count to j_checkpoint_jh_count, since this makes it
> clearer what this counter is intended to track.
>
> Fixes: 4ba3fcdde7e3 ("jbd2,ext4: add a shrinker to release checkpointed buffers")
> Reported-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
> Reported-by: Jon Hunter <jonathanh@nvidia.com>
> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
> ---
> fs/ext4/super.c | 8 ---
> fs/jbd2/checkpoint.c | 4 +-
> fs/jbd2/journal.c | 148 +++++++++++++++++--------------------------
> include/linux/jbd2.h | 6 +-
> 4 files changed, 63 insertions(+), 103 deletions(-)
>
[..]
> diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
> index 152880c298ca..8a9c94dd3599 100644
> --- a/fs/jbd2/journal.c
> +++ b/fs/jbd2/journal.c
[..]
> /*
> * Management for journal control blocks: functions to create and
> * destroy journal_t structures, and to initialise and read existing
> @@ -1361,6 +1403,19 @@ static journal_t *journal_init_common(struct block_device *bdev,
> journal->j_sb_buffer = bh;
> journal->j_superblock = (journal_superblock_t *)bh->b_data;
>
> + journal->j_shrink_transaction = NULL;
> + journal->j_shrinker.scan_objects = jbd2_journal_shrink_scan;
> + journal->j_shrinker.count_objects = jbd2_journal_shrink_count;
> + journal->j_shrinker.seeks = DEFAULT_SEEKS;
> + journal->j_shrinker.batch = journal->j_max_transaction_buffers;
> +
> + if (percpu_counter_init(&journal->j_checkpoint_jh_count, 0, GFP_KERNEL))
> + goto err_cleanup;
> +
> + if (register_shrinker(&journal->j_shrinker)) {
> + percpu_counter_destroy(&journal->j_checkpoint_jh_count);
> + goto err_cleanup;
> + }
Need to release j_sb_buffer in above two error path.
Thanks,
Yi.
^ permalink raw reply
* [PATCH AUTOSEL 4.4 03/15] crypto: nx - add missing MODULE_DEVICE_TABLE
From: Sasha Levin @ 2021-07-04 23:12 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Herbert Xu, Hulk Robot, Bixuan Cui, linux-crypto,
linuxppc-dev
In-Reply-To: <20210704231222.1492037-1-sashal@kernel.org>
From: Bixuan Cui <cuibixuan@huawei.com>
[ Upstream commit 06676aa1f455c74e3ad1624cea3acb9ed2ef71ae ]
This patch adds missing MODULE_DEVICE_TABLE definition which generates
correct modalias for automatic loading of this driver when it is built
as an external module.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Bixuan Cui <cuibixuan@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/crypto/nx/nx-842-pseries.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/crypto/nx/nx-842-pseries.c b/drivers/crypto/nx/nx-842-pseries.c
index cddc6d8b55d9..2e5b4004f0ee 100644
--- a/drivers/crypto/nx/nx-842-pseries.c
+++ b/drivers/crypto/nx/nx-842-pseries.c
@@ -1086,6 +1086,7 @@ static struct vio_device_id nx842_vio_driver_ids[] = {
{"ibm,compression-v1", "ibm,compression"},
{"", ""},
};
+MODULE_DEVICE_TABLE(vio, nx842_vio_driver_ids);
static struct vio_driver nx842_vio_driver = {
.name = KBUILD_MODNAME,
--
2.30.2
^ permalink raw reply related
* [PATCH AUTOSEL 4.9 04/20] crypto: nx - add missing MODULE_DEVICE_TABLE
From: Sasha Levin @ 2021-07-04 23:11 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Herbert Xu, Hulk Robot, Bixuan Cui, linux-crypto,
linuxppc-dev
In-Reply-To: <20210704231155.1491795-1-sashal@kernel.org>
From: Bixuan Cui <cuibixuan@huawei.com>
[ Upstream commit 06676aa1f455c74e3ad1624cea3acb9ed2ef71ae ]
This patch adds missing MODULE_DEVICE_TABLE definition which generates
correct modalias for automatic loading of this driver when it is built
as an external module.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Bixuan Cui <cuibixuan@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/crypto/nx/nx-842-pseries.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/crypto/nx/nx-842-pseries.c b/drivers/crypto/nx/nx-842-pseries.c
index cddc6d8b55d9..2e5b4004f0ee 100644
--- a/drivers/crypto/nx/nx-842-pseries.c
+++ b/drivers/crypto/nx/nx-842-pseries.c
@@ -1086,6 +1086,7 @@ static struct vio_device_id nx842_vio_driver_ids[] = {
{"ibm,compression-v1", "ibm,compression"},
{"", ""},
};
+MODULE_DEVICE_TABLE(vio, nx842_vio_driver_ids);
static struct vio_driver nx842_vio_driver = {
.name = KBUILD_MODNAME,
--
2.30.2
^ permalink raw reply related
* [PATCH AUTOSEL 4.14 06/25] crypto: nx - add missing MODULE_DEVICE_TABLE
From: Sasha Levin @ 2021-07-04 23:11 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Herbert Xu, Hulk Robot, Bixuan Cui, linux-crypto,
linuxppc-dev
In-Reply-To: <20210704231123.1491517-1-sashal@kernel.org>
From: Bixuan Cui <cuibixuan@huawei.com>
[ Upstream commit 06676aa1f455c74e3ad1624cea3acb9ed2ef71ae ]
This patch adds missing MODULE_DEVICE_TABLE definition which generates
correct modalias for automatic loading of this driver when it is built
as an external module.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Bixuan Cui <cuibixuan@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/crypto/nx/nx-842-pseries.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/crypto/nx/nx-842-pseries.c b/drivers/crypto/nx/nx-842-pseries.c
index cddc6d8b55d9..2e5b4004f0ee 100644
--- a/drivers/crypto/nx/nx-842-pseries.c
+++ b/drivers/crypto/nx/nx-842-pseries.c
@@ -1086,6 +1086,7 @@ static struct vio_device_id nx842_vio_driver_ids[] = {
{"ibm,compression-v1", "ibm,compression"},
{"", ""},
};
+MODULE_DEVICE_TABLE(vio, nx842_vio_driver_ids);
static struct vio_driver nx842_vio_driver = {
.name = KBUILD_MODNAME,
--
2.30.2
^ permalink raw reply related
* [PATCH AUTOSEL 4.19 09/31] crypto: nx - add missing MODULE_DEVICE_TABLE
From: Sasha Levin @ 2021-07-04 23:10 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Herbert Xu, Hulk Robot, Bixuan Cui, linux-crypto,
linuxppc-dev
In-Reply-To: <20210704231043.1491209-1-sashal@kernel.org>
From: Bixuan Cui <cuibixuan@huawei.com>
[ Upstream commit 06676aa1f455c74e3ad1624cea3acb9ed2ef71ae ]
This patch adds missing MODULE_DEVICE_TABLE definition which generates
correct modalias for automatic loading of this driver when it is built
as an external module.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Bixuan Cui <cuibixuan@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/crypto/nx/nx-842-pseries.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/crypto/nx/nx-842-pseries.c b/drivers/crypto/nx/nx-842-pseries.c
index 66869976cfa2..fa40edae231e 100644
--- a/drivers/crypto/nx/nx-842-pseries.c
+++ b/drivers/crypto/nx/nx-842-pseries.c
@@ -1086,6 +1086,7 @@ static const struct vio_device_id nx842_vio_driver_ids[] = {
{"ibm,compression-v1", "ibm,compression"},
{"", ""},
};
+MODULE_DEVICE_TABLE(vio, nx842_vio_driver_ids);
static struct vio_driver nx842_vio_driver = {
.name = KBUILD_MODNAME,
--
2.30.2
^ permalink raw reply related
* [PATCH AUTOSEL 5.4 39/50] KVM: PPC: Book3S HV: Fix TLB management on SMT8 POWER9 and POWER10 processors
From: Sasha Levin @ 2021-07-04 23:09 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Fabiano Rosas, Nicholas Piggin, kvm-ppc,
Suraj Jitindar Singh, linuxppc-dev
In-Reply-To: <20210704230938.1490742-1-sashal@kernel.org>
From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
[ Upstream commit 77bbbc0cf84834ed130838f7ac1988567f4d0288 ]
The POWER9 vCPU TLB management code assumes all threads in a core share
a TLB, and that TLBIEL execued by one thread will invalidate TLBs for
all threads. This is not the case for SMT8 capable POWER9 and POWER10
(big core) processors, where the TLB is split between groups of threads.
This results in TLB multi-hits, random data corruption, etc.
Fix this by introducing cpu_first_tlb_thread_sibling etc., to determine
which siblings share TLBs, and use that in the guest TLB flushing code.
[npiggin@gmail.com: add changelog and comment]
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210602040441.3984352-1-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
arch/powerpc/include/asm/cputhreads.h | 30 +++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv.c | 13 ++++++------
arch/powerpc/kvm/book3s_hv_builtin.c | 2 +-
arch/powerpc/kvm/book3s_hv_rm_mmu.c | 2 +-
4 files changed, 39 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index deb99fd6e060..51f533b6ece0 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -99,6 +99,36 @@ static inline int cpu_last_thread_sibling(int cpu)
return cpu | (threads_per_core - 1);
}
+/*
+ * tlb_thread_siblings are siblings which share a TLB. This is not
+ * architected, is not something a hypervisor could emulate and a future
+ * CPU may change behaviour even in compat mode, so this should only be
+ * used on PowerNV, and only with care.
+ */
+static inline int cpu_first_tlb_thread_sibling(int cpu)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+ return cpu & ~0x6; /* Big Core */
+ else
+ return cpu_first_thread_sibling(cpu);
+}
+
+static inline int cpu_last_tlb_thread_sibling(int cpu)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+ return cpu | 0x6; /* Big Core */
+ else
+ return cpu_last_thread_sibling(cpu);
+}
+
+static inline int cpu_tlb_thread_sibling_step(void)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+ return 2; /* Big Core */
+ else
+ return 1;
+}
+
static inline u32 get_tensr(void)
{
#ifdef CONFIG_BOOKE
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 6938b793a015..9011857c0434 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2536,7 +2536,7 @@ static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
cpumask_t *cpu_in_guest;
int i;
- cpu = cpu_first_thread_sibling(cpu);
+ cpu = cpu_first_tlb_thread_sibling(cpu);
if (nested) {
cpumask_set_cpu(cpu, &nested->need_tlb_flush);
cpu_in_guest = &nested->cpu_in_guest;
@@ -2550,9 +2550,10 @@ static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
* the other side is the first smp_mb() in kvmppc_run_core().
*/
smp_mb();
- for (i = 0; i < threads_per_core; ++i)
- if (cpumask_test_cpu(cpu + i, cpu_in_guest))
- smp_call_function_single(cpu + i, do_nothing, NULL, 1);
+ for (i = cpu; i <= cpu_last_tlb_thread_sibling(cpu);
+ i += cpu_tlb_thread_sibling_step())
+ if (cpumask_test_cpu(i, cpu_in_guest))
+ smp_call_function_single(i, do_nothing, NULL, 1);
}
static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu)
@@ -2583,8 +2584,8 @@ static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu)
*/
if (prev_cpu != pcpu) {
if (prev_cpu >= 0 &&
- cpu_first_thread_sibling(prev_cpu) !=
- cpu_first_thread_sibling(pcpu))
+ cpu_first_tlb_thread_sibling(prev_cpu) !=
+ cpu_first_tlb_thread_sibling(pcpu))
radix_flush_cpu(kvm, prev_cpu, vcpu);
if (nested)
nested->prev_cpu[vcpu->arch.nested_vcpu_id] = pcpu;
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 7c1909657b55..4a91b543a854 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -847,7 +847,7 @@ void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu,
* Thus we make all 4 threads use the same bit.
*/
if (cpu_has_feature(CPU_FTR_ARCH_300))
- pcpu = cpu_first_thread_sibling(pcpu);
+ pcpu = cpu_first_tlb_thread_sibling(pcpu);
if (nested)
need_tlb_flush = &nested->need_tlb_flush;
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 220305454c23..9bf3be438ac5 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -67,7 +67,7 @@ static int global_invalidates(struct kvm *kvm)
* so use the bit for the first thread to represent the core.
*/
if (cpu_has_feature(CPU_FTR_ARCH_300))
- cpu = cpu_first_thread_sibling(cpu);
+ cpu = cpu_first_tlb_thread_sibling(cpu);
cpumask_clear_cpu(cpu, &kvm->arch.need_tlb_flush);
}
--
2.30.2
^ permalink raw reply related
* [PATCH AUTOSEL 5.4 14/50] crypto: nx - add missing MODULE_DEVICE_TABLE
From: Sasha Levin @ 2021-07-04 23:09 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Herbert Xu, Hulk Robot, Bixuan Cui, linux-crypto,
linuxppc-dev
In-Reply-To: <20210704230938.1490742-1-sashal@kernel.org>
From: Bixuan Cui <cuibixuan@huawei.com>
[ Upstream commit 06676aa1f455c74e3ad1624cea3acb9ed2ef71ae ]
This patch adds missing MODULE_DEVICE_TABLE definition which generates
correct modalias for automatic loading of this driver when it is built
as an external module.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Bixuan Cui <cuibixuan@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/crypto/nx/nx-842-pseries.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/crypto/nx/nx-842-pseries.c b/drivers/crypto/nx/nx-842-pseries.c
index 2de5e3672e42..258c5e38a551 100644
--- a/drivers/crypto/nx/nx-842-pseries.c
+++ b/drivers/crypto/nx/nx-842-pseries.c
@@ -1071,6 +1071,7 @@ static const struct vio_device_id nx842_vio_driver_ids[] = {
{"ibm,compression-v1", "ibm,compression"},
{"", ""},
};
+MODULE_DEVICE_TABLE(vio, nx842_vio_driver_ids);
static struct vio_driver nx842_vio_driver = {
.name = KBUILD_MODNAME,
--
2.30.2
^ permalink raw reply related
* [PATCH AUTOSEL 5.10 57/70] KVM: PPC: Book3S HV: Fix TLB management on SMT8 POWER9 and POWER10 processors
From: Sasha Levin @ 2021-07-04 23:07 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Fabiano Rosas, Nicholas Piggin, kvm-ppc,
Suraj Jitindar Singh, linuxppc-dev
In-Reply-To: <20210704230804.1490078-1-sashal@kernel.org>
From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
[ Upstream commit 77bbbc0cf84834ed130838f7ac1988567f4d0288 ]
The POWER9 vCPU TLB management code assumes all threads in a core share
a TLB, and that TLBIEL execued by one thread will invalidate TLBs for
all threads. This is not the case for SMT8 capable POWER9 and POWER10
(big core) processors, where the TLB is split between groups of threads.
This results in TLB multi-hits, random data corruption, etc.
Fix this by introducing cpu_first_tlb_thread_sibling etc., to determine
which siblings share TLBs, and use that in the guest TLB flushing code.
[npiggin@gmail.com: add changelog and comment]
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210602040441.3984352-1-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
arch/powerpc/include/asm/cputhreads.h | 30 +++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv.c | 13 ++++++------
arch/powerpc/kvm/book3s_hv_builtin.c | 2 +-
arch/powerpc/kvm/book3s_hv_rm_mmu.c | 2 +-
4 files changed, 39 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index 98c8bd155bf9..b167186aaee4 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -98,6 +98,36 @@ static inline int cpu_last_thread_sibling(int cpu)
return cpu | (threads_per_core - 1);
}
+/*
+ * tlb_thread_siblings are siblings which share a TLB. This is not
+ * architected, is not something a hypervisor could emulate and a future
+ * CPU may change behaviour even in compat mode, so this should only be
+ * used on PowerNV, and only with care.
+ */
+static inline int cpu_first_tlb_thread_sibling(int cpu)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+ return cpu & ~0x6; /* Big Core */
+ else
+ return cpu_first_thread_sibling(cpu);
+}
+
+static inline int cpu_last_tlb_thread_sibling(int cpu)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+ return cpu | 0x6; /* Big Core */
+ else
+ return cpu_last_thread_sibling(cpu);
+}
+
+static inline int cpu_tlb_thread_sibling_step(void)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+ return 2; /* Big Core */
+ else
+ return 1;
+}
+
static inline u32 get_tensr(void)
{
#ifdef CONFIG_BOOKE
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 280f7992ae99..18ecffbad9ae 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2578,7 +2578,7 @@ static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
cpumask_t *cpu_in_guest;
int i;
- cpu = cpu_first_thread_sibling(cpu);
+ cpu = cpu_first_tlb_thread_sibling(cpu);
if (nested) {
cpumask_set_cpu(cpu, &nested->need_tlb_flush);
cpu_in_guest = &nested->cpu_in_guest;
@@ -2592,9 +2592,10 @@ static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
* the other side is the first smp_mb() in kvmppc_run_core().
*/
smp_mb();
- for (i = 0; i < threads_per_core; ++i)
- if (cpumask_test_cpu(cpu + i, cpu_in_guest))
- smp_call_function_single(cpu + i, do_nothing, NULL, 1);
+ for (i = cpu; i <= cpu_last_tlb_thread_sibling(cpu);
+ i += cpu_tlb_thread_sibling_step())
+ if (cpumask_test_cpu(i, cpu_in_guest))
+ smp_call_function_single(i, do_nothing, NULL, 1);
}
static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu)
@@ -2625,8 +2626,8 @@ static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu)
*/
if (prev_cpu != pcpu) {
if (prev_cpu >= 0 &&
- cpu_first_thread_sibling(prev_cpu) !=
- cpu_first_thread_sibling(pcpu))
+ cpu_first_tlb_thread_sibling(prev_cpu) !=
+ cpu_first_tlb_thread_sibling(pcpu))
radix_flush_cpu(kvm, prev_cpu, vcpu);
if (nested)
nested->prev_cpu[vcpu->arch.nested_vcpu_id] = pcpu;
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 8f58dd20b362..4621905bdd9e 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -893,7 +893,7 @@ void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu,
* Thus we make all 4 threads use the same bit.
*/
if (cpu_has_feature(CPU_FTR_ARCH_300))
- pcpu = cpu_first_thread_sibling(pcpu);
+ pcpu = cpu_first_tlb_thread_sibling(pcpu);
if (nested)
need_tlb_flush = &nested->need_tlb_flush;
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 88da2764c1bb..3ddc83d2e849 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -67,7 +67,7 @@ static int global_invalidates(struct kvm *kvm)
* so use the bit for the first thread to represent the core.
*/
if (cpu_has_feature(CPU_FTR_ARCH_300))
- cpu = cpu_first_thread_sibling(cpu);
+ cpu = cpu_first_tlb_thread_sibling(cpu);
cpumask_clear_cpu(cpu, &kvm->arch.need_tlb_flush);
}
--
2.30.2
^ permalink raw reply related
* [PATCH AUTOSEL 5.10 21/70] crypto: nx - add missing MODULE_DEVICE_TABLE
From: Sasha Levin @ 2021-07-04 23:07 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Herbert Xu, Hulk Robot, Bixuan Cui, linux-crypto,
linuxppc-dev
In-Reply-To: <20210704230804.1490078-1-sashal@kernel.org>
From: Bixuan Cui <cuibixuan@huawei.com>
[ Upstream commit 06676aa1f455c74e3ad1624cea3acb9ed2ef71ae ]
This patch adds missing MODULE_DEVICE_TABLE definition which generates
correct modalias for automatic loading of this driver when it is built
as an external module.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Bixuan Cui <cuibixuan@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/crypto/nx/nx-842-pseries.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/crypto/nx/nx-842-pseries.c b/drivers/crypto/nx/nx-842-pseries.c
index 2de5e3672e42..258c5e38a551 100644
--- a/drivers/crypto/nx/nx-842-pseries.c
+++ b/drivers/crypto/nx/nx-842-pseries.c
@@ -1071,6 +1071,7 @@ static const struct vio_device_id nx842_vio_driver_ids[] = {
{"ibm,compression-v1", "ibm,compression"},
{"", ""},
};
+MODULE_DEVICE_TABLE(vio, nx842_vio_driver_ids);
static struct vio_driver nx842_vio_driver = {
.name = KBUILD_MODNAME,
--
2.30.2
^ permalink raw reply related
* [PATCH AUTOSEL 5.10 19/70] sched/core: Initialize the idle task with preemption disabled
From: Sasha Levin @ 2021-07-04 23:07 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, linux-s390, linux-arch, linux-ia64, linux-parisc,
linux-sh, Peter Zijlstra, linux-xtensa, linux-mips, linux-csky,
Ingo Molnar, openrisc, linux-alpha, sparclinux, linux-riscv,
linux-snps-arc, linuxppc-dev, Valentin Schneider,
linux-arm-kernel
In-Reply-To: <20210704230804.1490078-1-sashal@kernel.org>
From: Valentin Schneider <valentin.schneider@arm.com>
[ Upstream commit f1a0a376ca0c4ef1fc3d24e3e502acbb5b795674 ]
As pointed out by commit
de9b8f5dcbd9 ("sched: Fix crash trying to dequeue/enqueue the idle thread")
init_idle() can and will be invoked more than once on the same idle
task. At boot time, it is invoked for the boot CPU thread by
sched_init(). Then smp_init() creates the threads for all the secondary
CPUs and invokes init_idle() on them.
As the hotplug machinery brings the secondaries to life, it will issue
calls to idle_thread_get(), which itself invokes init_idle() yet again.
In this case it's invoked twice more per secondary: at _cpu_up(), and at
bringup_cpu().
Given smp_init() already initializes the idle tasks for all *possible*
CPUs, no further initialization should be required. Now, removing
init_idle() from idle_thread_get() exposes some interesting expectations
with regards to the idle task's preempt_count: the secondary startup always
issues a preempt_disable(), requiring some reset of the preempt count to 0
between hot-unplug and hotplug, which is currently served by
idle_thread_get() -> idle_init().
Given the idle task is supposed to have preemption disabled once and never
see it re-enabled, it seems that what we actually want is to initialize its
preempt_count to PREEMPT_DISABLED and leave it there. Do that, and remove
init_idle() from idle_thread_get().
Secondary startups were patched via coccinelle:
@begone@
@@
-preempt_disable();
...
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210512094636.2958515-1-valentin.schneider@arm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
arch/alpha/kernel/smp.c | 1 -
arch/arc/kernel/smp.c | 1 -
arch/arm/kernel/smp.c | 1 -
arch/arm64/include/asm/preempt.h | 2 +-
arch/arm64/kernel/smp.c | 1 -
arch/csky/kernel/smp.c | 1 -
arch/ia64/kernel/smpboot.c | 1 -
arch/mips/kernel/smp.c | 1 -
arch/openrisc/kernel/smp.c | 2 --
arch/parisc/kernel/smp.c | 1 -
arch/powerpc/kernel/smp.c | 1 -
arch/riscv/kernel/smpboot.c | 1 -
arch/s390/include/asm/preempt.h | 4 ++--
arch/s390/kernel/smp.c | 1 -
arch/sh/kernel/smp.c | 2 --
arch/sparc/kernel/smp_32.c | 1 -
arch/sparc/kernel/smp_64.c | 3 ---
arch/x86/include/asm/preempt.h | 2 +-
arch/x86/kernel/smpboot.c | 1 -
arch/xtensa/kernel/smp.c | 1 -
include/asm-generic/preempt.h | 2 +-
init/main.c | 6 +-----
kernel/fork.c | 2 +-
kernel/sched/core.c | 2 +-
kernel/smpboot.c | 1 -
25 files changed, 8 insertions(+), 34 deletions(-)
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index f4dd9f3f3001..4b2575f936d4 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -166,7 +166,6 @@ smp_callin(void)
DBGS(("smp_callin: commencing CPU %d current %p active_mm %p\n",
cpuid, current, current->active_mm));
- preempt_disable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index 52906d314537..db0e104d6835 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -189,7 +189,6 @@ void start_kernel_secondary(void)
pr_info("## CPU%u LIVE ##: Executing Code...\n", cpu);
local_irq_enable();
- preempt_disable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 48099c6e1e4a..8aa7fa949c23 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -432,7 +432,6 @@ asmlinkage void secondary_start_kernel(void)
#endif
pr_debug("CPU%u: Booted secondary processor\n", cpu);
- preempt_disable();
trace_hardirqs_off();
/*
diff --git a/arch/arm64/include/asm/preempt.h b/arch/arm64/include/asm/preempt.h
index 80e946b2abee..e83f0982b99c 100644
--- a/arch/arm64/include/asm/preempt.h
+++ b/arch/arm64/include/asm/preempt.h
@@ -23,7 +23,7 @@ static inline void preempt_count_set(u64 pc)
} while (0)
#define init_idle_preempt_count(p, cpu) do { \
- task_thread_info(p)->preempt_count = PREEMPT_ENABLED; \
+ task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
} while (0)
static inline void set_preempt_need_resched(void)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 18e9727d3f64..feee5a3cd128 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -223,7 +223,6 @@ asmlinkage notrace void secondary_start_kernel(void)
init_gic_priority_masking();
rcu_cpu_starting(cpu);
- preempt_disable();
trace_hardirqs_off();
/*
diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c
index 041d0de6a1b6..1a8d7eaf1ff7 100644
--- a/arch/csky/kernel/smp.c
+++ b/arch/csky/kernel/smp.c
@@ -282,7 +282,6 @@ void csky_start_secondary(void)
pr_info("CPU%u Online: %s...\n", cpu, __func__);
local_irq_enable();
- preempt_disable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 093040f7e626..0cad990385c0 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -440,7 +440,6 @@ start_secondary (void *unused)
#endif
efi_map_pal_code();
cpu_init();
- preempt_disable();
smp_callin();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 48d84d5fcc36..ff25926c5458 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -348,7 +348,6 @@ asmlinkage void start_secondary(void)
*/
calibrate_delay();
- preempt_disable();
cpu = smp_processor_id();
cpu_data[cpu].udelay_val = loops_per_jiffy;
diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c
index 29c82ef2e207..e4dad76066ae 100644
--- a/arch/openrisc/kernel/smp.c
+++ b/arch/openrisc/kernel/smp.c
@@ -134,8 +134,6 @@ asmlinkage __init void secondary_start_kernel(void)
set_cpu_online(cpu, true);
local_irq_enable();
-
- preempt_disable();
/*
* OK, it's off to the idle thread for us
*/
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 10227f667c8a..1405b603b91b 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -302,7 +302,6 @@ void __init smp_callin(unsigned long pdce_proc)
#endif
smp_cpu_init(slave_id);
- preempt_disable();
flush_cache_all_local(); /* start with known state */
flush_tlb_all_local(NULL);
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index db7ac77bea3a..0760230be56f 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1426,7 +1426,6 @@ void start_secondary(void *unused)
smp_store_cpu_info(cpu);
set_dec(tb_ticks_per_jiffy);
rcu_cpu_starting(cpu);
- preempt_disable();
cpu_callin_map[cpu] = 1;
if (smp_ops->setup_cpu)
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 96167d55ed98..0b04e0eae3ab 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -166,7 +166,6 @@ asmlinkage __visible void smp_callin(void)
* Disable preemption before enabling interrupts, so we don't try to
* schedule a CPU that hasn't actually started yet.
*/
- preempt_disable();
local_irq_enable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
diff --git a/arch/s390/include/asm/preempt.h b/arch/s390/include/asm/preempt.h
index 6ede29907fbf..e38480eb58fa 100644
--- a/arch/s390/include/asm/preempt.h
+++ b/arch/s390/include/asm/preempt.h
@@ -32,7 +32,7 @@ static inline void preempt_count_set(int pc)
#define init_task_preempt_count(p) do { } while (0)
#define init_idle_preempt_count(p, cpu) do { \
- S390_lowcore.preempt_count = PREEMPT_ENABLED; \
+ S390_lowcore.preempt_count = PREEMPT_DISABLED; \
} while (0)
static inline void set_preempt_need_resched(void)
@@ -91,7 +91,7 @@ static inline void preempt_count_set(int pc)
#define init_task_preempt_count(p) do { } while (0)
#define init_idle_preempt_count(p, cpu) do { \
- S390_lowcore.preempt_count = PREEMPT_ENABLED; \
+ S390_lowcore.preempt_count = PREEMPT_DISABLED; \
} while (0)
static inline void set_preempt_need_resched(void)
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 791bc373418b..7db5460553b7 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -863,7 +863,6 @@ static void smp_init_secondary(void)
set_cpu_flag(CIF_ASCE_SECONDARY);
cpu_init();
rcu_cpu_starting(cpu);
- preempt_disable();
init_cpu_timer();
vtime_init();
pfault_init();
diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c
index 372acdc9033e..65924d9ec245 100644
--- a/arch/sh/kernel/smp.c
+++ b/arch/sh/kernel/smp.c
@@ -186,8 +186,6 @@ asmlinkage void start_secondary(void)
per_cpu_trap_init();
- preempt_disable();
-
notify_cpu_starting(cpu);
local_irq_enable();
diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c
index 50c127ab46d5..22b148e5a5f8 100644
--- a/arch/sparc/kernel/smp_32.c
+++ b/arch/sparc/kernel/smp_32.c
@@ -348,7 +348,6 @@ static void sparc_start_secondary(void *arg)
*/
arch_cpu_pre_starting(arg);
- preempt_disable();
cpu = smp_processor_id();
notify_cpu_starting(cpu);
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index e38d8bf454e8..ae5faa1d989d 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -138,9 +138,6 @@ void smp_callin(void)
set_cpu_online(cpuid, true);
- /* idle thread is expected to have preempt disabled */
- preempt_disable();
-
local_irq_enable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 69485ca13665..a334dd0d7c42 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -43,7 +43,7 @@ static __always_inline void preempt_count_set(int pc)
#define init_task_preempt_count(p) do { } while (0)
#define init_idle_preempt_count(p, cpu) do { \
- per_cpu(__preempt_count, (cpu)) = PREEMPT_ENABLED; \
+ per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \
} while (0)
/*
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 582387fc939f..8baff500914e 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -230,7 +230,6 @@ static void notrace start_secondary(void *unused)
cpu_init_exception_handling();
cpu_init();
x86_cpuinit.early_percpu_clock_init();
- preempt_disable();
smp_callin();
enable_start_cpu0 = 0;
diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c
index cd85a7a2722b..1254da07ead1 100644
--- a/arch/xtensa/kernel/smp.c
+++ b/arch/xtensa/kernel/smp.c
@@ -145,7 +145,6 @@ void secondary_start_kernel(void)
cpumask_set_cpu(cpu, mm_cpumask(mm));
enter_lazy_tlb(mm, current);
- preempt_disable();
trace_hardirqs_off();
calibrate_delay();
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index d683f5e6d791..b4d43a4af5f7 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -29,7 +29,7 @@ static __always_inline void preempt_count_set(int pc)
} while (0)
#define init_idle_preempt_count(p, cpu) do { \
- task_thread_info(p)->preempt_count = PREEMPT_ENABLED; \
+ task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
} while (0)
static __always_inline void set_preempt_need_resched(void)
diff --git a/init/main.c b/init/main.c
index b4449544390c..dd26a42e80a8 100644
--- a/init/main.c
+++ b/init/main.c
@@ -914,11 +914,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void)
* time - but meanwhile we still have a functioning scheduler.
*/
sched_init();
- /*
- * Disable preemption - early bootup scheduling is extremely
- * fragile until we cpu_idle() for the first time.
- */
- preempt_disable();
+
if (WARN(!irqs_disabled(),
"Interrupts were enabled *very* early, fixing it\n"))
local_irq_disable();
diff --git a/kernel/fork.c b/kernel/fork.c
index 281addb694df..096945ef49ad 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2392,7 +2392,7 @@ static inline void init_idle_pids(struct task_struct *idle)
}
}
-struct task_struct *fork_idle(int cpu)
+struct task_struct * __init fork_idle(int cpu)
{
struct task_struct *task;
struct kernel_clone_args args = {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 57b236251884..bd3fa14fda1f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6512,7 +6512,7 @@ void show_state_filter(unsigned long state_filter)
* NOTE: this function does not set the idle thread's NEED_RESCHED
* flag, to make booting more robust.
*/
-void init_idle(struct task_struct *idle, int cpu)
+void __init init_idle(struct task_struct *idle, int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index f25208e8df83..e4163042c4d6 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -33,7 +33,6 @@ struct task_struct *idle_thread_get(unsigned int cpu)
if (!tsk)
return ERR_PTR(-ENOMEM);
- init_idle(tsk, cpu);
return tsk;
}
--
2.30.2
^ permalink raw reply related
* [PATCH AUTOSEL 5.12 65/80] KVM: PPC: Book3S HV: Fix TLB management on SMT8 POWER9 and POWER10 processors
From: Sasha Levin @ 2021-07-04 23:06 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Fabiano Rosas, Nicholas Piggin, kvm-ppc,
Suraj Jitindar Singh, linuxppc-dev
In-Reply-To: <20210704230616.1489200-1-sashal@kernel.org>
From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
[ Upstream commit 77bbbc0cf84834ed130838f7ac1988567f4d0288 ]
The POWER9 vCPU TLB management code assumes all threads in a core share
a TLB, and that TLBIEL execued by one thread will invalidate TLBs for
all threads. This is not the case for SMT8 capable POWER9 and POWER10
(big core) processors, where the TLB is split between groups of threads.
This results in TLB multi-hits, random data corruption, etc.
Fix this by introducing cpu_first_tlb_thread_sibling etc., to determine
which siblings share TLBs, and use that in the guest TLB flushing code.
[npiggin@gmail.com: add changelog and comment]
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210602040441.3984352-1-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
arch/powerpc/include/asm/cputhreads.h | 30 +++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv.c | 13 ++++++------
arch/powerpc/kvm/book3s_hv_builtin.c | 2 +-
arch/powerpc/kvm/book3s_hv_rm_mmu.c | 2 +-
4 files changed, 39 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index 98c8bd155bf9..b167186aaee4 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -98,6 +98,36 @@ static inline int cpu_last_thread_sibling(int cpu)
return cpu | (threads_per_core - 1);
}
+/*
+ * tlb_thread_siblings are siblings which share a TLB. This is not
+ * architected, is not something a hypervisor could emulate and a future
+ * CPU may change behaviour even in compat mode, so this should only be
+ * used on PowerNV, and only with care.
+ */
+static inline int cpu_first_tlb_thread_sibling(int cpu)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+ return cpu & ~0x6; /* Big Core */
+ else
+ return cpu_first_thread_sibling(cpu);
+}
+
+static inline int cpu_last_tlb_thread_sibling(int cpu)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+ return cpu | 0x6; /* Big Core */
+ else
+ return cpu_last_thread_sibling(cpu);
+}
+
+static inline int cpu_tlb_thread_sibling_step(void)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+ return 2; /* Big Core */
+ else
+ return 1;
+}
+
static inline u32 get_tensr(void)
{
#ifdef CONFIG_BOOKE
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 60c5bc0c130c..1c6e0a52fb53 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2619,7 +2619,7 @@ static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
cpumask_t *cpu_in_guest;
int i;
- cpu = cpu_first_thread_sibling(cpu);
+ cpu = cpu_first_tlb_thread_sibling(cpu);
if (nested) {
cpumask_set_cpu(cpu, &nested->need_tlb_flush);
cpu_in_guest = &nested->cpu_in_guest;
@@ -2633,9 +2633,10 @@ static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
* the other side is the first smp_mb() in kvmppc_run_core().
*/
smp_mb();
- for (i = 0; i < threads_per_core; ++i)
- if (cpumask_test_cpu(cpu + i, cpu_in_guest))
- smp_call_function_single(cpu + i, do_nothing, NULL, 1);
+ for (i = cpu; i <= cpu_last_tlb_thread_sibling(cpu);
+ i += cpu_tlb_thread_sibling_step())
+ if (cpumask_test_cpu(i, cpu_in_guest))
+ smp_call_function_single(i, do_nothing, NULL, 1);
}
static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu)
@@ -2666,8 +2667,8 @@ static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu)
*/
if (prev_cpu != pcpu) {
if (prev_cpu >= 0 &&
- cpu_first_thread_sibling(prev_cpu) !=
- cpu_first_thread_sibling(pcpu))
+ cpu_first_tlb_thread_sibling(prev_cpu) !=
+ cpu_first_tlb_thread_sibling(pcpu))
radix_flush_cpu(kvm, prev_cpu, vcpu);
if (nested)
nested->prev_cpu[vcpu->arch.nested_vcpu_id] = pcpu;
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 158d309b42a3..b5e5d07cb40f 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -797,7 +797,7 @@ void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu,
* Thus we make all 4 threads use the same bit.
*/
if (cpu_has_feature(CPU_FTR_ARCH_300))
- pcpu = cpu_first_thread_sibling(pcpu);
+ pcpu = cpu_first_tlb_thread_sibling(pcpu);
if (nested)
need_tlb_flush = &nested->need_tlb_flush;
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 88da2764c1bb..3ddc83d2e849 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -67,7 +67,7 @@ static int global_invalidates(struct kvm *kvm)
* so use the bit for the first thread to represent the core.
*/
if (cpu_has_feature(CPU_FTR_ARCH_300))
- cpu = cpu_first_thread_sibling(cpu);
+ cpu = cpu_first_tlb_thread_sibling(cpu);
cpumask_clear_cpu(cpu, &kvm->arch.need_tlb_flush);
}
--
2.30.2
^ permalink raw reply related
* [PATCH AUTOSEL 5.12 22/80] crypto: nx - add missing MODULE_DEVICE_TABLE
From: Sasha Levin @ 2021-07-04 23:05 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Herbert Xu, Hulk Robot, Bixuan Cui, linux-crypto,
linuxppc-dev
In-Reply-To: <20210704230616.1489200-1-sashal@kernel.org>
From: Bixuan Cui <cuibixuan@huawei.com>
[ Upstream commit 06676aa1f455c74e3ad1624cea3acb9ed2ef71ae ]
This patch adds missing MODULE_DEVICE_TABLE definition which generates
correct modalias for automatic loading of this driver when it is built
as an external module.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Bixuan Cui <cuibixuan@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/crypto/nx/nx-842-pseries.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/crypto/nx/nx-842-pseries.c b/drivers/crypto/nx/nx-842-pseries.c
index cc8dd3072b8b..8ee547ee378e 100644
--- a/drivers/crypto/nx/nx-842-pseries.c
+++ b/drivers/crypto/nx/nx-842-pseries.c
@@ -1069,6 +1069,7 @@ static const struct vio_device_id nx842_vio_driver_ids[] = {
{"ibm,compression-v1", "ibm,compression"},
{"", ""},
};
+MODULE_DEVICE_TABLE(vio, nx842_vio_driver_ids);
static struct vio_driver nx842_vio_driver = {
.name = KBUILD_MODNAME,
--
2.30.2
^ permalink raw reply related
* [PATCH AUTOSEL 5.12 20/80] sched/core: Initialize the idle task with preemption disabled
From: Sasha Levin @ 2021-07-04 23:05 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, linux-s390, linux-arch, linux-ia64, linux-parisc,
linux-sh, Peter Zijlstra, linux-xtensa, linux-mips, linux-csky,
Ingo Molnar, openrisc, linux-alpha, sparclinux, linux-riscv,
linux-snps-arc, linuxppc-dev, Valentin Schneider,
linux-arm-kernel
In-Reply-To: <20210704230616.1489200-1-sashal@kernel.org>
From: Valentin Schneider <valentin.schneider@arm.com>
[ Upstream commit f1a0a376ca0c4ef1fc3d24e3e502acbb5b795674 ]
As pointed out by commit
de9b8f5dcbd9 ("sched: Fix crash trying to dequeue/enqueue the idle thread")
init_idle() can and will be invoked more than once on the same idle
task. At boot time, it is invoked for the boot CPU thread by
sched_init(). Then smp_init() creates the threads for all the secondary
CPUs and invokes init_idle() on them.
As the hotplug machinery brings the secondaries to life, it will issue
calls to idle_thread_get(), which itself invokes init_idle() yet again.
In this case it's invoked twice more per secondary: at _cpu_up(), and at
bringup_cpu().
Given smp_init() already initializes the idle tasks for all *possible*
CPUs, no further initialization should be required. Now, removing
init_idle() from idle_thread_get() exposes some interesting expectations
with regards to the idle task's preempt_count: the secondary startup always
issues a preempt_disable(), requiring some reset of the preempt count to 0
between hot-unplug and hotplug, which is currently served by
idle_thread_get() -> idle_init().
Given the idle task is supposed to have preemption disabled once and never
see it re-enabled, it seems that what we actually want is to initialize its
preempt_count to PREEMPT_DISABLED and leave it there. Do that, and remove
init_idle() from idle_thread_get().
Secondary startups were patched via coccinelle:
@begone@
@@
-preempt_disable();
...
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210512094636.2958515-1-valentin.schneider@arm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
arch/alpha/kernel/smp.c | 1 -
arch/arc/kernel/smp.c | 1 -
arch/arm/kernel/smp.c | 1 -
arch/arm64/include/asm/preempt.h | 2 +-
arch/arm64/kernel/smp.c | 1 -
arch/csky/kernel/smp.c | 1 -
arch/ia64/kernel/smpboot.c | 1 -
arch/mips/kernel/smp.c | 1 -
arch/openrisc/kernel/smp.c | 2 --
arch/parisc/kernel/smp.c | 1 -
arch/powerpc/kernel/smp.c | 1 -
arch/riscv/kernel/smpboot.c | 1 -
arch/s390/include/asm/preempt.h | 4 ++--
arch/s390/kernel/smp.c | 1 -
arch/sh/kernel/smp.c | 2 --
arch/sparc/kernel/smp_32.c | 1 -
arch/sparc/kernel/smp_64.c | 3 ---
arch/x86/include/asm/preempt.h | 2 +-
arch/x86/kernel/smpboot.c | 1 -
arch/xtensa/kernel/smp.c | 1 -
include/asm-generic/preempt.h | 2 +-
init/main.c | 6 +-----
kernel/fork.c | 2 +-
kernel/sched/core.c | 2 +-
kernel/smpboot.c | 1 -
25 files changed, 8 insertions(+), 34 deletions(-)
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index f4dd9f3f3001..4b2575f936d4 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -166,7 +166,6 @@ smp_callin(void)
DBGS(("smp_callin: commencing CPU %d current %p active_mm %p\n",
cpuid, current, current->active_mm));
- preempt_disable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index 52906d314537..db0e104d6835 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -189,7 +189,6 @@ void start_kernel_secondary(void)
pr_info("## CPU%u LIVE ##: Executing Code...\n", cpu);
local_irq_enable();
- preempt_disable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 74679240a9d8..c7bb168b0d97 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -432,7 +432,6 @@ asmlinkage void secondary_start_kernel(void)
#endif
pr_debug("CPU%u: Booted secondary processor\n", cpu);
- preempt_disable();
trace_hardirqs_off();
/*
diff --git a/arch/arm64/include/asm/preempt.h b/arch/arm64/include/asm/preempt.h
index 80e946b2abee..e83f0982b99c 100644
--- a/arch/arm64/include/asm/preempt.h
+++ b/arch/arm64/include/asm/preempt.h
@@ -23,7 +23,7 @@ static inline void preempt_count_set(u64 pc)
} while (0)
#define init_idle_preempt_count(p, cpu) do { \
- task_thread_info(p)->preempt_count = PREEMPT_ENABLED; \
+ task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
} while (0)
static inline void set_preempt_need_resched(void)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 357590beaabb..48fd89256739 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -223,7 +223,6 @@ asmlinkage notrace void secondary_start_kernel(void)
init_gic_priority_masking();
rcu_cpu_starting(cpu);
- preempt_disable();
trace_hardirqs_off();
/*
diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c
index 0f9f5eef9338..e2993539af8e 100644
--- a/arch/csky/kernel/smp.c
+++ b/arch/csky/kernel/smp.c
@@ -281,7 +281,6 @@ void csky_start_secondary(void)
pr_info("CPU%u Online: %s...\n", cpu, __func__);
local_irq_enable();
- preempt_disable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 49b488580939..d10f780c13b9 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -441,7 +441,6 @@ start_secondary (void *unused)
#endif
efi_map_pal_code();
cpu_init();
- preempt_disable();
smp_callin();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index ef86fbad8546..d542fb7af3ba 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -348,7 +348,6 @@ asmlinkage void start_secondary(void)
*/
calibrate_delay();
- preempt_disable();
cpu = smp_processor_id();
cpu_data[cpu].udelay_val = loops_per_jiffy;
diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c
index 48e1092a64de..415e209732a3 100644
--- a/arch/openrisc/kernel/smp.c
+++ b/arch/openrisc/kernel/smp.c
@@ -145,8 +145,6 @@ asmlinkage __init void secondary_start_kernel(void)
set_cpu_online(cpu, true);
local_irq_enable();
-
- preempt_disable();
/*
* OK, it's off to the idle thread for us
*/
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 10227f667c8a..1405b603b91b 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -302,7 +302,6 @@ void __init smp_callin(unsigned long pdce_proc)
#endif
smp_cpu_init(slave_id);
- preempt_disable();
flush_cache_all_local(); /* start with known state */
flush_tlb_all_local(NULL);
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index c2473e20f5f5..1d7daef1c3b6 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1530,7 +1530,6 @@ void start_secondary(void *unused)
smp_store_cpu_info(cpu);
set_dec(tb_ticks_per_jiffy);
rcu_cpu_starting(cpu);
- preempt_disable();
cpu_callin_map[cpu] = 1;
if (smp_ops->setup_cpu)
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 5e276c25646f..1941a6ce86a1 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -176,7 +176,6 @@ asmlinkage __visible void smp_callin(void)
* Disable preemption before enabling interrupts, so we don't try to
* schedule a CPU that hasn't actually started yet.
*/
- preempt_disable();
local_irq_enable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
diff --git a/arch/s390/include/asm/preempt.h b/arch/s390/include/asm/preempt.h
index b49e0492842c..23ff51be7e29 100644
--- a/arch/s390/include/asm/preempt.h
+++ b/arch/s390/include/asm/preempt.h
@@ -32,7 +32,7 @@ static inline void preempt_count_set(int pc)
#define init_task_preempt_count(p) do { } while (0)
#define init_idle_preempt_count(p, cpu) do { \
- S390_lowcore.preempt_count = PREEMPT_ENABLED; \
+ S390_lowcore.preempt_count = PREEMPT_DISABLED; \
} while (0)
static inline void set_preempt_need_resched(void)
@@ -91,7 +91,7 @@ static inline void preempt_count_set(int pc)
#define init_task_preempt_count(p) do { } while (0)
#define init_idle_preempt_count(p, cpu) do { \
- S390_lowcore.preempt_count = PREEMPT_ENABLED; \
+ S390_lowcore.preempt_count = PREEMPT_DISABLED; \
} while (0)
static inline void set_preempt_need_resched(void)
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 58c8afa3da65..d60c7374d807 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -877,7 +877,6 @@ static void smp_init_secondary(void)
restore_access_regs(S390_lowcore.access_regs_save_area);
cpu_init();
rcu_cpu_starting(cpu);
- preempt_disable();
init_cpu_timer();
vtime_init();
vdso_getcpu_init();
diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c
index 372acdc9033e..65924d9ec245 100644
--- a/arch/sh/kernel/smp.c
+++ b/arch/sh/kernel/smp.c
@@ -186,8 +186,6 @@ asmlinkage void start_secondary(void)
per_cpu_trap_init();
- preempt_disable();
-
notify_cpu_starting(cpu);
local_irq_enable();
diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c
index 50c127ab46d5..22b148e5a5f8 100644
--- a/arch/sparc/kernel/smp_32.c
+++ b/arch/sparc/kernel/smp_32.c
@@ -348,7 +348,6 @@ static void sparc_start_secondary(void *arg)
*/
arch_cpu_pre_starting(arg);
- preempt_disable();
cpu = smp_processor_id();
notify_cpu_starting(cpu);
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index e38d8bf454e8..ae5faa1d989d 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -138,9 +138,6 @@ void smp_callin(void)
set_cpu_online(cpuid, true);
- /* idle thread is expected to have preempt disabled */
- preempt_disable();
-
local_irq_enable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index f8cb8af4de5c..fe5efbcba824 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -44,7 +44,7 @@ static __always_inline void preempt_count_set(int pc)
#define init_task_preempt_count(p) do { } while (0)
#define init_idle_preempt_count(p, cpu) do { \
- per_cpu(__preempt_count, (cpu)) = PREEMPT_ENABLED; \
+ per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \
} while (0)
/*
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 363b36bbd791..ebc4b13b74a4 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -236,7 +236,6 @@ static void notrace start_secondary(void *unused)
cpu_init();
rcu_cpu_starting(raw_smp_processor_id());
x86_cpuinit.early_percpu_clock_init();
- preempt_disable();
smp_callin();
enable_start_cpu0 = 0;
diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c
index cd85a7a2722b..1254da07ead1 100644
--- a/arch/xtensa/kernel/smp.c
+++ b/arch/xtensa/kernel/smp.c
@@ -145,7 +145,6 @@ void secondary_start_kernel(void)
cpumask_set_cpu(cpu, mm_cpumask(mm));
enter_lazy_tlb(mm, current);
- preempt_disable();
trace_hardirqs_off();
calibrate_delay();
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index d683f5e6d791..b4d43a4af5f7 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -29,7 +29,7 @@ static __always_inline void preempt_count_set(int pc)
} while (0)
#define init_idle_preempt_count(p, cpu) do { \
- task_thread_info(p)->preempt_count = PREEMPT_ENABLED; \
+ task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
} while (0)
static __always_inline void set_preempt_need_resched(void)
diff --git a/init/main.c b/init/main.c
index 5bd1a25f1d6f..c97d3c0247a1 100644
--- a/init/main.c
+++ b/init/main.c
@@ -918,11 +918,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void)
* time - but meanwhile we still have a functioning scheduler.
*/
sched_init();
- /*
- * Disable preemption - early bootup scheduling is extremely
- * fragile until we cpu_idle() for the first time.
- */
- preempt_disable();
+
if (WARN(!irqs_disabled(),
"Interrupts were enabled *very* early, fixing it\n"))
local_irq_disable();
diff --git a/kernel/fork.c b/kernel/fork.c
index 321a5e31d817..2654a5a9e5df 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2405,7 +2405,7 @@ static inline void init_idle_pids(struct task_struct *idle)
}
}
-struct task_struct *fork_idle(int cpu)
+struct task_struct * __init fork_idle(int cpu)
{
struct task_struct *task;
struct kernel_clone_args args = {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 814200541f8f..e25b2d8ec18d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7428,7 +7428,7 @@ void show_state_filter(unsigned long state_filter)
* NOTE: this function does not set the idle thread's NEED_RESCHED
* flag, to make booting more robust.
*/
-void init_idle(struct task_struct *idle, int cpu)
+void __init init_idle(struct task_struct *idle, int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index f25208e8df83..e4163042c4d6 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -33,7 +33,6 @@ struct task_struct *idle_thread_get(unsigned int cpu)
if (!tsk)
return ERR_PTR(-ENOMEM);
- init_idle(tsk, cpu);
return tsk;
}
--
2.30.2
^ permalink raw reply related
* [PATCH AUTOSEL 5.13 69/85] KVM: PPC: Book3S HV: Fix TLB management on SMT8 POWER9 and POWER10 processors
From: Sasha Levin @ 2021-07-04 23:04 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Fabiano Rosas, Nicholas Piggin, kvm-ppc,
Suraj Jitindar Singh, linuxppc-dev
In-Reply-To: <20210704230420.1488358-1-sashal@kernel.org>
From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
[ Upstream commit 77bbbc0cf84834ed130838f7ac1988567f4d0288 ]
The POWER9 vCPU TLB management code assumes all threads in a core share
a TLB, and that TLBIEL execued by one thread will invalidate TLBs for
all threads. This is not the case for SMT8 capable POWER9 and POWER10
(big core) processors, where the TLB is split between groups of threads.
This results in TLB multi-hits, random data corruption, etc.
Fix this by introducing cpu_first_tlb_thread_sibling etc., to determine
which siblings share TLBs, and use that in the guest TLB flushing code.
[npiggin@gmail.com: add changelog and comment]
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210602040441.3984352-1-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
arch/powerpc/include/asm/cputhreads.h | 30 +++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv.c | 13 ++++++------
arch/powerpc/kvm/book3s_hv_builtin.c | 2 +-
arch/powerpc/kvm/book3s_hv_rm_mmu.c | 2 +-
4 files changed, 39 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index 98c8bd155bf9..b167186aaee4 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -98,6 +98,36 @@ static inline int cpu_last_thread_sibling(int cpu)
return cpu | (threads_per_core - 1);
}
+/*
+ * tlb_thread_siblings are siblings which share a TLB. This is not
+ * architected, is not something a hypervisor could emulate and a future
+ * CPU may change behaviour even in compat mode, so this should only be
+ * used on PowerNV, and only with care.
+ */
+static inline int cpu_first_tlb_thread_sibling(int cpu)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+ return cpu & ~0x6; /* Big Core */
+ else
+ return cpu_first_thread_sibling(cpu);
+}
+
+static inline int cpu_last_tlb_thread_sibling(int cpu)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+ return cpu | 0x6; /* Big Core */
+ else
+ return cpu_last_thread_sibling(cpu);
+}
+
+static inline int cpu_tlb_thread_sibling_step(void)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+ return 2; /* Big Core */
+ else
+ return 1;
+}
+
static inline u32 get_tensr(void)
{
#ifdef CONFIG_BOOKE
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index bc0813644666..67cc164c4ac1 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2657,7 +2657,7 @@ static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
cpumask_t *cpu_in_guest;
int i;
- cpu = cpu_first_thread_sibling(cpu);
+ cpu = cpu_first_tlb_thread_sibling(cpu);
if (nested) {
cpumask_set_cpu(cpu, &nested->need_tlb_flush);
cpu_in_guest = &nested->cpu_in_guest;
@@ -2671,9 +2671,10 @@ static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
* the other side is the first smp_mb() in kvmppc_run_core().
*/
smp_mb();
- for (i = 0; i < threads_per_core; ++i)
- if (cpumask_test_cpu(cpu + i, cpu_in_guest))
- smp_call_function_single(cpu + i, do_nothing, NULL, 1);
+ for (i = cpu; i <= cpu_last_tlb_thread_sibling(cpu);
+ i += cpu_tlb_thread_sibling_step())
+ if (cpumask_test_cpu(i, cpu_in_guest))
+ smp_call_function_single(i, do_nothing, NULL, 1);
}
static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu)
@@ -2704,8 +2705,8 @@ static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu)
*/
if (prev_cpu != pcpu) {
if (prev_cpu >= 0 &&
- cpu_first_thread_sibling(prev_cpu) !=
- cpu_first_thread_sibling(pcpu))
+ cpu_first_tlb_thread_sibling(prev_cpu) !=
+ cpu_first_tlb_thread_sibling(pcpu))
radix_flush_cpu(kvm, prev_cpu, vcpu);
if (nested)
nested->prev_cpu[vcpu->arch.nested_vcpu_id] = pcpu;
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 7a0e33a9c980..3edc25c89092 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -800,7 +800,7 @@ void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu,
* Thus we make all 4 threads use the same bit.
*/
if (cpu_has_feature(CPU_FTR_ARCH_300))
- pcpu = cpu_first_thread_sibling(pcpu);
+ pcpu = cpu_first_tlb_thread_sibling(pcpu);
if (nested)
need_tlb_flush = &nested->need_tlb_flush;
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 7a0f12404e0e..502d9ebe3ae4 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -56,7 +56,7 @@ static int global_invalidates(struct kvm *kvm)
* so use the bit for the first thread to represent the core.
*/
if (cpu_has_feature(CPU_FTR_ARCH_300))
- cpu = cpu_first_thread_sibling(cpu);
+ cpu = cpu_first_tlb_thread_sibling(cpu);
cpumask_clear_cpu(cpu, &kvm->arch.need_tlb_flush);
}
--
2.30.2
^ permalink raw reply related
* [PATCH AUTOSEL 5.13 20/85] sched/core: Initialize the idle task with preemption disabled
From: Sasha Levin @ 2021-07-04 23:03 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, linux-s390, linux-arch, linux-ia64, linux-parisc,
linux-sh, Peter Zijlstra, linux-xtensa, linux-mips, linux-csky,
Ingo Molnar, openrisc, linux-alpha, sparclinux, linux-riscv,
linux-snps-arc, linuxppc-dev, Valentin Schneider,
linux-arm-kernel
In-Reply-To: <20210704230420.1488358-1-sashal@kernel.org>
From: Valentin Schneider <valentin.schneider@arm.com>
[ Upstream commit f1a0a376ca0c4ef1fc3d24e3e502acbb5b795674 ]
As pointed out by commit
de9b8f5dcbd9 ("sched: Fix crash trying to dequeue/enqueue the idle thread")
init_idle() can and will be invoked more than once on the same idle
task. At boot time, it is invoked for the boot CPU thread by
sched_init(). Then smp_init() creates the threads for all the secondary
CPUs and invokes init_idle() on them.
As the hotplug machinery brings the secondaries to life, it will issue
calls to idle_thread_get(), which itself invokes init_idle() yet again.
In this case it's invoked twice more per secondary: at _cpu_up(), and at
bringup_cpu().
Given smp_init() already initializes the idle tasks for all *possible*
CPUs, no further initialization should be required. Now, removing
init_idle() from idle_thread_get() exposes some interesting expectations
with regards to the idle task's preempt_count: the secondary startup always
issues a preempt_disable(), requiring some reset of the preempt count to 0
between hot-unplug and hotplug, which is currently served by
idle_thread_get() -> idle_init().
Given the idle task is supposed to have preemption disabled once and never
see it re-enabled, it seems that what we actually want is to initialize its
preempt_count to PREEMPT_DISABLED and leave it there. Do that, and remove
init_idle() from idle_thread_get().
Secondary startups were patched via coccinelle:
@begone@
@@
-preempt_disable();
...
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210512094636.2958515-1-valentin.schneider@arm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
arch/alpha/kernel/smp.c | 1 -
arch/arc/kernel/smp.c | 1 -
arch/arm/kernel/smp.c | 1 -
arch/arm64/include/asm/preempt.h | 2 +-
arch/arm64/kernel/smp.c | 1 -
arch/csky/kernel/smp.c | 1 -
arch/ia64/kernel/smpboot.c | 1 -
arch/mips/kernel/smp.c | 1 -
arch/openrisc/kernel/smp.c | 2 --
arch/parisc/kernel/smp.c | 1 -
arch/powerpc/kernel/smp.c | 1 -
arch/riscv/kernel/smpboot.c | 1 -
arch/s390/include/asm/preempt.h | 4 ++--
arch/s390/kernel/smp.c | 1 -
arch/sh/kernel/smp.c | 2 --
arch/sparc/kernel/smp_32.c | 1 -
arch/sparc/kernel/smp_64.c | 3 ---
arch/x86/include/asm/preempt.h | 2 +-
arch/x86/kernel/smpboot.c | 1 -
arch/xtensa/kernel/smp.c | 1 -
include/asm-generic/preempt.h | 2 +-
init/main.c | 6 +-----
kernel/fork.c | 2 +-
kernel/sched/core.c | 2 +-
kernel/smpboot.c | 1 -
25 files changed, 8 insertions(+), 34 deletions(-)
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index f4dd9f3f3001..4b2575f936d4 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -166,7 +166,6 @@ smp_callin(void)
DBGS(("smp_callin: commencing CPU %d current %p active_mm %p\n",
cpuid, current, current->active_mm));
- preempt_disable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index 52906d314537..db0e104d6835 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -189,7 +189,6 @@ void start_kernel_secondary(void)
pr_info("## CPU%u LIVE ##: Executing Code...\n", cpu);
local_irq_enable();
- preempt_disable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 74679240a9d8..c7bb168b0d97 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -432,7 +432,6 @@ asmlinkage void secondary_start_kernel(void)
#endif
pr_debug("CPU%u: Booted secondary processor\n", cpu);
- preempt_disable();
trace_hardirqs_off();
/*
diff --git a/arch/arm64/include/asm/preempt.h b/arch/arm64/include/asm/preempt.h
index 80e946b2abee..e83f0982b99c 100644
--- a/arch/arm64/include/asm/preempt.h
+++ b/arch/arm64/include/asm/preempt.h
@@ -23,7 +23,7 @@ static inline void preempt_count_set(u64 pc)
} while (0)
#define init_idle_preempt_count(p, cpu) do { \
- task_thread_info(p)->preempt_count = PREEMPT_ENABLED; \
+ task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
} while (0)
static inline void set_preempt_need_resched(void)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index dcd7041b2b07..6671000a8b7d 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -224,7 +224,6 @@ asmlinkage notrace void secondary_start_kernel(void)
init_gic_priority_masking();
rcu_cpu_starting(cpu);
- preempt_disable();
trace_hardirqs_off();
/*
diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c
index 0f9f5eef9338..e2993539af8e 100644
--- a/arch/csky/kernel/smp.c
+++ b/arch/csky/kernel/smp.c
@@ -281,7 +281,6 @@ void csky_start_secondary(void)
pr_info("CPU%u Online: %s...\n", cpu, __func__);
local_irq_enable();
- preempt_disable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 49b488580939..d10f780c13b9 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -441,7 +441,6 @@ start_secondary (void *unused)
#endif
efi_map_pal_code();
cpu_init();
- preempt_disable();
smp_callin();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index ef86fbad8546..d542fb7af3ba 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -348,7 +348,6 @@ asmlinkage void start_secondary(void)
*/
calibrate_delay();
- preempt_disable();
cpu = smp_processor_id();
cpu_data[cpu].udelay_val = loops_per_jiffy;
diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c
index 48e1092a64de..415e209732a3 100644
--- a/arch/openrisc/kernel/smp.c
+++ b/arch/openrisc/kernel/smp.c
@@ -145,8 +145,6 @@ asmlinkage __init void secondary_start_kernel(void)
set_cpu_online(cpu, true);
local_irq_enable();
-
- preempt_disable();
/*
* OK, it's off to the idle thread for us
*/
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 10227f667c8a..1405b603b91b 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -302,7 +302,6 @@ void __init smp_callin(unsigned long pdce_proc)
#endif
smp_cpu_init(slave_id);
- preempt_disable();
flush_cache_all_local(); /* start with known state */
flush_tlb_all_local(NULL);
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 2e05c783440a..6c6e4d934d86 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1547,7 +1547,6 @@ void start_secondary(void *unused)
smp_store_cpu_info(cpu);
set_dec(tb_ticks_per_jiffy);
rcu_cpu_starting(cpu);
- preempt_disable();
cpu_callin_map[cpu] = 1;
if (smp_ops->setup_cpu)
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 9a408e2942ac..bd82375db51a 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -180,7 +180,6 @@ asmlinkage __visible void smp_callin(void)
* Disable preemption before enabling interrupts, so we don't try to
* schedule a CPU that hasn't actually started yet.
*/
- preempt_disable();
local_irq_enable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
diff --git a/arch/s390/include/asm/preempt.h b/arch/s390/include/asm/preempt.h
index b49e0492842c..23ff51be7e29 100644
--- a/arch/s390/include/asm/preempt.h
+++ b/arch/s390/include/asm/preempt.h
@@ -32,7 +32,7 @@ static inline void preempt_count_set(int pc)
#define init_task_preempt_count(p) do { } while (0)
#define init_idle_preempt_count(p, cpu) do { \
- S390_lowcore.preempt_count = PREEMPT_ENABLED; \
+ S390_lowcore.preempt_count = PREEMPT_DISABLED; \
} while (0)
static inline void set_preempt_need_resched(void)
@@ -91,7 +91,7 @@ static inline void preempt_count_set(int pc)
#define init_task_preempt_count(p) do { } while (0)
#define init_idle_preempt_count(p, cpu) do { \
- S390_lowcore.preempt_count = PREEMPT_ENABLED; \
+ S390_lowcore.preempt_count = PREEMPT_DISABLED; \
} while (0)
static inline void set_preempt_need_resched(void)
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 2fec2b80d35d..111909aeb8d2 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -878,7 +878,6 @@ static void smp_init_secondary(void)
restore_access_regs(S390_lowcore.access_regs_save_area);
cpu_init();
rcu_cpu_starting(cpu);
- preempt_disable();
init_cpu_timer();
vtime_init();
vdso_getcpu_init();
diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c
index 372acdc9033e..65924d9ec245 100644
--- a/arch/sh/kernel/smp.c
+++ b/arch/sh/kernel/smp.c
@@ -186,8 +186,6 @@ asmlinkage void start_secondary(void)
per_cpu_trap_init();
- preempt_disable();
-
notify_cpu_starting(cpu);
local_irq_enable();
diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c
index 50c127ab46d5..22b148e5a5f8 100644
--- a/arch/sparc/kernel/smp_32.c
+++ b/arch/sparc/kernel/smp_32.c
@@ -348,7 +348,6 @@ static void sparc_start_secondary(void *arg)
*/
arch_cpu_pre_starting(arg);
- preempt_disable();
cpu = smp_processor_id();
notify_cpu_starting(cpu);
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index e38d8bf454e8..ae5faa1d989d 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -138,9 +138,6 @@ void smp_callin(void)
set_cpu_online(cpuid, true);
- /* idle thread is expected to have preempt disabled */
- preempt_disable();
-
local_irq_enable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index f8cb8af4de5c..fe5efbcba824 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -44,7 +44,7 @@ static __always_inline void preempt_count_set(int pc)
#define init_task_preempt_count(p) do { } while (0)
#define init_idle_preempt_count(p, cpu) do { \
- per_cpu(__preempt_count, (cpu)) = PREEMPT_ENABLED; \
+ per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \
} while (0)
/*
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 7770245cc7fa..ec2d64aa2163 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -236,7 +236,6 @@ static void notrace start_secondary(void *unused)
cpu_init();
rcu_cpu_starting(raw_smp_processor_id());
x86_cpuinit.early_percpu_clock_init();
- preempt_disable();
smp_callin();
enable_start_cpu0 = 0;
diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c
index cd85a7a2722b..1254da07ead1 100644
--- a/arch/xtensa/kernel/smp.c
+++ b/arch/xtensa/kernel/smp.c
@@ -145,7 +145,6 @@ void secondary_start_kernel(void)
cpumask_set_cpu(cpu, mm_cpumask(mm));
enter_lazy_tlb(mm, current);
- preempt_disable();
trace_hardirqs_off();
calibrate_delay();
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index d683f5e6d791..b4d43a4af5f7 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -29,7 +29,7 @@ static __always_inline void preempt_count_set(int pc)
} while (0)
#define init_idle_preempt_count(p, cpu) do { \
- task_thread_info(p)->preempt_count = PREEMPT_ENABLED; \
+ task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
} while (0)
static __always_inline void set_preempt_need_resched(void)
diff --git a/init/main.c b/init/main.c
index e9c42a183e33..e6836a9400d5 100644
--- a/init/main.c
+++ b/init/main.c
@@ -941,11 +941,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void)
* time - but meanwhile we still have a functioning scheduler.
*/
sched_init();
- /*
- * Disable preemption - early bootup scheduling is extremely
- * fragile until we cpu_idle() for the first time.
- */
- preempt_disable();
+
if (WARN(!irqs_disabled(),
"Interrupts were enabled *very* early, fixing it\n"))
local_irq_disable();
diff --git a/kernel/fork.c b/kernel/fork.c
index 24a689df61c9..98b4bc7f0d7b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2407,7 +2407,7 @@ static inline void init_idle_pids(struct task_struct *idle)
}
}
-struct task_struct *fork_idle(int cpu)
+struct task_struct * __init fork_idle(int cpu)
{
struct task_struct *task;
struct kernel_clone_args args = {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4ca80df205ce..0a90d4d7663b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7433,7 +7433,7 @@ void show_state_filter(unsigned long state_filter)
* NOTE: this function does not set the idle thread's NEED_RESCHED
* flag, to make booting more robust.
*/
-void init_idle(struct task_struct *idle, int cpu)
+void __init init_idle(struct task_struct *idle, int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index f25208e8df83..e4163042c4d6 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -33,7 +33,6 @@ struct task_struct *idle_thread_get(unsigned int cpu)
if (!tsk)
return ERR_PTR(-ENOMEM);
- init_idle(tsk, cpu);
return tsk;
}
--
2.30.2
^ permalink raw reply related
* [PATCH AUTOSEL 5.13 22/85] crypto: nx - add missing MODULE_DEVICE_TABLE
From: Sasha Levin @ 2021-07-04 23:03 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Herbert Xu, Hulk Robot, Bixuan Cui, linux-crypto,
linuxppc-dev
In-Reply-To: <20210704230420.1488358-1-sashal@kernel.org>
From: Bixuan Cui <cuibixuan@huawei.com>
[ Upstream commit 06676aa1f455c74e3ad1624cea3acb9ed2ef71ae ]
This patch adds missing MODULE_DEVICE_TABLE definition which generates
correct modalias for automatic loading of this driver when it is built
as an external module.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Bixuan Cui <cuibixuan@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/crypto/nx/nx-842-pseries.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/crypto/nx/nx-842-pseries.c b/drivers/crypto/nx/nx-842-pseries.c
index cc8dd3072b8b..8ee547ee378e 100644
--- a/drivers/crypto/nx/nx-842-pseries.c
+++ b/drivers/crypto/nx/nx-842-pseries.c
@@ -1069,6 +1069,7 @@ static const struct vio_device_id nx842_vio_driver_ids[] = {
{"ibm,compression-v1", "ibm,compression"},
{"", ""},
};
+MODULE_DEVICE_TABLE(vio, nx842_vio_driver_ids);
static struct vio_driver nx842_vio_driver = {
.name = KBUILD_MODNAME,
--
2.30.2
^ permalink raw reply related
* Hitting BUG_ON in do_notify_resume() with gdb and SIGTRAP
From: Radu Rendec @ 2021-07-04 21:38 UTC (permalink / raw)
To: linuxppc-dev
Hi Everyone,
I'm trying to set up my (virtual) environment to test an old bug in the
PPC32 ptrace() code. I came across a completely different problem,
which seems to make gdb pretty much unusable on PPC32. I'm not sure if
this is a real kernel bug or maybe something wrong with my
configuration.
I'm running kernel 5.13 in a qemu VM with one e500mc CPU. I am running
native gdb (inside the VM) and setting a breakpoint in main() in a test
"hello world" program. Upon running the test program, I am hitting the
BUG_ON in do_notify_resume() on line 292. The kernel bug log snippet is
included below at the end of the email.
FWIW, gdb says:
Program terminated with signal SIGTRAP, Trace/breakpoint trap.
The program no longer exists.
I also added a pr_info() to do_notify_resume() just to see how much
different 'regs' and 'current->thread.regs' are. Surprisingly, they are
just 0x30 apart: regs=c7955f10 cur=c7955f40. Also, 'current' seems to
be OK (pid and comm are consistent with the test program).
If I'm not missing something, the 'regs' pointer that is eventually
passed to do_notify_resume() is calculated in interrupt_return() by
adding STACK_FRAME_OVERHEAD (defined to 112) to the value of r1. That
means all registers are saved on the stack before entering the
interrupt handler and, upon returning, a pointer to the register
structure is calculated from the stack pointer. Either the offset
itself is wrong, or the stack pointer is off by 0x30.
This is as far as I have gone. Hopefully this rings a bell to someone
who is familiar with that part of the code and has a better
understanding of PPC32 interrupt handling in general.
Last but not least, my configuration is fairly standard. I'm using the
powerpc-e500mc--glibc--bleeding-edge-2020.08-1 toolchain from Bootlin
to compile everything (kernel and user-space). The qemu version is
5.2.0 (Fedora 34) and the user-space is a small Busybox based rootfs
that I built using Buildroot 2021.05. The gdb version is 9.2.
regs=c7955f10 cur=c7955f40 pid=138 comm=test
------------[ cut here ]------------
kernel BUG at arch/powerpc/kernel/signal.c:296!
Oops: Exception in kernel mode, sig: 5 [#1]
BE PAGE_SIZE=4K SMP NR_CPUS=24 QEMU e500
Modules linked in:
CPU: 0 PID: 138 Comm: test Not tainted 5.13.0-dirty #3
NIP: c0009694 LR: c0009694 CTR: c065f540
REGS: c7955dc0 TRAP: 0700 Not tainted (5.13.0-dirty)
MSR: 00028002 <CE,EE> CR: 28000282 XER: 20000000
GPR00: c0009694 c7955e80 c7145100 0000002c dfbdc3d4 dfbe5d24 00000027 dfbdc3d8
GPR08: c0ffe988 00000000 00000000 00000000 22000282 00000000 00000000 b7fe17b4
GPR16: 00000000 b7ffd588 b7ffe8b8 b7ffee10 b7fff214 b7ffdf40 b7fff208 bffff858
GPR24: bffff970 b7fff130 00000001 bffff960 c7955f10 00000800 c7145100 00000102
NIP [c0009694] do_notify_resume+0x314/0x320
LR [c0009694] do_notify_resume+0x314/0x320
Call Trace:
[c7955e80] [c0009694] do_notify_resume+0x314/0x320 (unreliable)
[c7955ee0] [c0010b94] interrupt_exit_user_prepare+0x94/0xc0
[c7955f00] [c00151e8] interrupt_return+0x14/0x13c
--- interrupt: 7d8 at 0xb7fc3714
NIP: b7fc3714 LR: b7fc3714 CTR: 00000003
REGS: c7955f10 TRAP: 07d8 Not tainted (5.13.0-dirty)
MSR: 1002d002 <CE,EE,PR,ME> CR: 22000284 XER: 00000000
GPR00: b7fc3584 bffff850 00000000 00000000 00000000 00000000 000000a0 6474e552
GPR08: b7fbe0d4 00000001 b7fff230 bffff850 b7fc36d8 00000000 00000000 b7fe17b4
GPR16: 00000000 b7ffd588 b7ffe8b8 b7ffee10 b7fff214 b7ffdf40 b7fff208 bffff858
GPR24: bffff970 b7fff130 00000001 bffff960 b7fff2b0 b7ffd5f0 b7ffe8a8 bffff850
NIP [b7fc3714] 0xb7fc3714
LR [b7fc3714] 0xb7fc3714
--- interrupt: 7d8
Instruction dump:
4bffff04 7c0802a6 93a10054 90010064 93c10058 48b95369 80c20398 3c60c0dc
7f84e378 38e204b0 3863ce30 4809d819 <0fe00000> 60000000 60000000 3d20c0ff
---[ end trace 065671519ba3d526 ]---
Note: the BUG() line is slightly different because I had made this
small change to print the pointers:
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 9ded046edb0e..57ea6e500a6f 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -289,7 +289,12 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
klp_update_patch_state(current);
if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) {
- BUG_ON(regs != current->thread.regs);
+ if (regs != current->thread.regs) {
+ pr_info("regs=%px cur=%px pid=%d comm=%s\n",
+ regs, current->thread.regs,
+ current->pid, current->comm);
+ BUG();
+ }
do_signal(current);
}
^ permalink raw reply related
* Re: [powerpc][5.13.0-next-20210701] Kernel crash while running ltp(chdir01) tests
From: Theodore Ts'o @ 2021-07-04 14:04 UTC (permalink / raw)
To: Zhang Yi
Cc: Sachin Sant, Jan Kara, Guoqing Jiang,
linux-fsdevel@vger.kernel.org, Ext4 Developers List, linuxppc-dev
In-Reply-To: <66fb56cd-f1ff-c592-0202-0691372e32f5@huawei.com>
On Sat, Jul 03, 2021 at 12:55:09PM +0800, Zhang Yi wrote:
> Yeah, it sounds good to me. Do you want me to send the fix patch, or you
> modify your commit 8f9e16badb8fd in another email directly?
I've gone ahead and made the changes; what do you think?
I like how it also removes 40 lines of code. :-)
- Ted
From ef3130d1b0b8ca769252d6a722a2e59a00141383 Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Fri, 2 Jul 2021 18:05:03 -0400
Subject: [PATCH] ext4: inline jbd2_journal_[un]register_shrinker()
The function jbd2_journal_unregister_shrinker() was getting called
twice when the file system was getting unmounted. On Power and ARM
platforms this was causing kernel crash when unmounting the file
system, when a percpu_counter was destroyed twice.
Fix this by removing jbd2_journal_[un]register_shrinker() functions,
and inlining the shrinker setup and teardown into
journal_init_common() and jbd2_journal_destroy(). This means that
ext4 and ocfs2 now no longer need to know about registering and
unregistering jbd2's shrinker.
Also, while we're at it, rename the percpu counter from
j_jh_shrink_count to j_checkpoint_jh_count, since this makes it
clearer what this counter is intended to track.
Fixes: 4ba3fcdde7e3 ("jbd2,ext4: add a shrinker to release checkpointed buffers")
Reported-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Reported-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
fs/ext4/super.c | 8 ---
fs/jbd2/checkpoint.c | 4 +-
fs/jbd2/journal.c | 148 +++++++++++++++++--------------------------
include/linux/jbd2.h | 6 +-
4 files changed, 63 insertions(+), 103 deletions(-)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index b8ff0399e171..dfa09a277b56 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1184,7 +1184,6 @@ static void ext4_put_super(struct super_block *sb)
ext4_unregister_sysfs(sb);
if (sbi->s_journal) {
- jbd2_journal_unregister_shrinker(sbi->s_journal);
aborted = is_journal_aborted(sbi->s_journal);
err = jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
@@ -5176,7 +5175,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_ea_block_cache = NULL;
if (sbi->s_journal) {
- jbd2_journal_unregister_shrinker(sbi->s_journal);
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
}
@@ -5502,12 +5500,6 @@ static int ext4_load_journal(struct super_block *sb,
ext4_commit_super(sb);
}
- err = jbd2_journal_register_shrinker(journal);
- if (err) {
- EXT4_SB(sb)->s_journal = NULL;
- goto err_out;
- }
-
return 0;
err_out:
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 51d1eb2ffeb9..746132998c57 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -701,7 +701,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
__buffer_unlink(jh);
jh->b_cp_transaction = NULL;
- percpu_counter_dec(&journal->j_jh_shrink_count);
+ percpu_counter_dec(&journal->j_checkpoint_jh_count);
jbd2_journal_put_journal_head(jh);
/* Is this transaction empty? */
@@ -764,7 +764,7 @@ void __jbd2_journal_insert_checkpoint(struct journal_head *jh,
jh->b_cpnext->b_cpprev = jh;
}
transaction->t_checkpoint_list = jh;
- percpu_counter_inc(&transaction->t_journal->j_jh_shrink_count);
+ percpu_counter_inc(&transaction->t_journal->j_checkpoint_jh_count);
}
/*
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 152880c298ca..8a9c94dd3599 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1283,6 +1283,48 @@ static int jbd2_min_tag_size(void)
return sizeof(journal_block_tag_t) - 4;
}
+/**
+ * jbd2_journal_shrink_scan()
+ *
+ * Scan the checkpointed buffer on the checkpoint list and release the
+ * journal_head.
+ */
+static unsigned long jbd2_journal_shrink_scan(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ journal_t *journal = container_of(shrink, journal_t, j_shrinker);
+ unsigned long nr_to_scan = sc->nr_to_scan;
+ unsigned long nr_shrunk;
+ unsigned long count;
+
+ count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count);
+ trace_jbd2_shrink_scan_enter(journal, sc->nr_to_scan, count);
+
+ nr_shrunk = jbd2_journal_shrink_checkpoint_list(journal, &nr_to_scan);
+
+ count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count);
+ trace_jbd2_shrink_scan_exit(journal, nr_to_scan, nr_shrunk, count);
+
+ return nr_shrunk;
+}
+
+/**
+ * jbd2_journal_shrink_count()
+ *
+ * Count the number of checkpoint buffers on the checkpoint list.
+ */
+static unsigned long jbd2_journal_shrink_count(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ journal_t *journal = container_of(shrink, journal_t, j_shrinker);
+ unsigned long count;
+
+ count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count);
+ trace_jbd2_shrink_count(journal, sc->nr_to_scan, count);
+
+ return count;
+}
+
/*
* Management for journal control blocks: functions to create and
* destroy journal_t structures, and to initialise and read existing
@@ -1361,6 +1403,19 @@ static journal_t *journal_init_common(struct block_device *bdev,
journal->j_sb_buffer = bh;
journal->j_superblock = (journal_superblock_t *)bh->b_data;
+ journal->j_shrink_transaction = NULL;
+ journal->j_shrinker.scan_objects = jbd2_journal_shrink_scan;
+ journal->j_shrinker.count_objects = jbd2_journal_shrink_count;
+ journal->j_shrinker.seeks = DEFAULT_SEEKS;
+ journal->j_shrinker.batch = journal->j_max_transaction_buffers;
+
+ if (percpu_counter_init(&journal->j_checkpoint_jh_count, 0, GFP_KERNEL))
+ goto err_cleanup;
+
+ if (register_shrinker(&journal->j_shrinker)) {
+ percpu_counter_destroy(&journal->j_checkpoint_jh_count);
+ goto err_cleanup;
+ }
return journal;
err_cleanup:
@@ -2050,93 +2105,6 @@ int jbd2_journal_load(journal_t *journal)
return -EIO;
}
-/**
- * jbd2_journal_shrink_scan()
- *
- * Scan the checkpointed buffer on the checkpoint list and release the
- * journal_head.
- */
-static unsigned long jbd2_journal_shrink_scan(struct shrinker *shrink,
- struct shrink_control *sc)
-{
- journal_t *journal = container_of(shrink, journal_t, j_shrinker);
- unsigned long nr_to_scan = sc->nr_to_scan;
- unsigned long nr_shrunk;
- unsigned long count;
-
- count = percpu_counter_read_positive(&journal->j_jh_shrink_count);
- trace_jbd2_shrink_scan_enter(journal, sc->nr_to_scan, count);
-
- nr_shrunk = jbd2_journal_shrink_checkpoint_list(journal, &nr_to_scan);
-
- count = percpu_counter_read_positive(&journal->j_jh_shrink_count);
- trace_jbd2_shrink_scan_exit(journal, nr_to_scan, nr_shrunk, count);
-
- return nr_shrunk;
-}
-
-/**
- * jbd2_journal_shrink_count()
- *
- * Count the number of checkpoint buffers on the checkpoint list.
- */
-static unsigned long jbd2_journal_shrink_count(struct shrinker *shrink,
- struct shrink_control *sc)
-{
- journal_t *journal = container_of(shrink, journal_t, j_shrinker);
- unsigned long count;
-
- count = percpu_counter_read_positive(&journal->j_jh_shrink_count);
- trace_jbd2_shrink_count(journal, sc->nr_to_scan, count);
-
- return count;
-}
-
-/**
- * jbd2_journal_register_shrinker()
- * @journal: Journal to act on.
- *
- * Init a percpu counter to record the checkpointed buffers on the checkpoint
- * list and register a shrinker to release their journal_head.
- */
-int jbd2_journal_register_shrinker(journal_t *journal)
-{
- int err;
-
- journal->j_shrink_transaction = NULL;
-
- err = percpu_counter_init(&journal->j_jh_shrink_count, 0, GFP_KERNEL);
- if (err)
- return err;
-
- journal->j_shrinker.scan_objects = jbd2_journal_shrink_scan;
- journal->j_shrinker.count_objects = jbd2_journal_shrink_count;
- journal->j_shrinker.seeks = DEFAULT_SEEKS;
- journal->j_shrinker.batch = journal->j_max_transaction_buffers;
-
- err = register_shrinker(&journal->j_shrinker);
- if (err) {
- percpu_counter_destroy(&journal->j_jh_shrink_count);
- return err;
- }
-
- return 0;
-}
-EXPORT_SYMBOL(jbd2_journal_register_shrinker);
-
-/**
- * jbd2_journal_unregister_shrinker()
- * @journal: Journal to act on.
- *
- * Unregister the checkpointed buffer shrinker and destroy the percpu counter.
- */
-void jbd2_journal_unregister_shrinker(journal_t *journal)
-{
- percpu_counter_destroy(&journal->j_jh_shrink_count);
- unregister_shrinker(&journal->j_shrinker);
-}
-EXPORT_SYMBOL(jbd2_journal_unregister_shrinker);
-
/**
* jbd2_journal_destroy() - Release a journal_t structure.
* @journal: Journal to act on.
@@ -2209,8 +2177,10 @@ int jbd2_journal_destroy(journal_t *journal)
brelse(journal->j_sb_buffer);
}
- jbd2_journal_unregister_shrinker(journal);
-
+ if (journal->j_shrinker.flags & SHRINKER_REGISTERED) {
+ percpu_counter_destroy(&journal->j_checkpoint_jh_count);
+ unregister_shrinker(&journal->j_shrinker);
+ }
if (journal->j_proc_entry)
jbd2_stats_proc_exit(journal);
iput(journal->j_inode);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 6cc035321562..fd933c45281a 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -918,11 +918,11 @@ struct journal_s
struct shrinker j_shrinker;
/**
- * @j_jh_shrink_count:
+ * @j_checkpoint_jh_count:
*
* Number of journal buffers on the checkpoint list. [j_list_lock]
*/
- struct percpu_counter j_jh_shrink_count;
+ struct percpu_counter j_checkpoint_jh_count;
/**
* @j_shrink_transaction:
@@ -1556,8 +1556,6 @@ extern int jbd2_journal_set_features
(journal_t *, unsigned long, unsigned long, unsigned long);
extern void jbd2_journal_clear_features
(journal_t *, unsigned long, unsigned long, unsigned long);
-extern int jbd2_journal_register_shrinker(journal_t *journal);
-extern void jbd2_journal_unregister_shrinker(journal_t *journal);
extern int jbd2_journal_load (journal_t *journal);
extern int jbd2_journal_destroy (journal_t *);
extern int jbd2_journal_recover (journal_t *journal);
--
2.31.0
^ permalink raw reply related
* Re: [PATCH] powerpc: Fix spelling mistake "mesages" -> "messages" in Kconfig
From: Geoff Levand @ 2021-07-04 13:58 UTC (permalink / raw)
To: Colin King, Michael Ellerman, Benjamin Herrenschmidt,
Paul Mackerras, linuxppc-dev
Cc: kernel-janitors, linux-kernel
In-Reply-To: <20210704093846.36972-1-colin.king@canonical.com>
On 7/4/21 2:38 AM, Colin King wrote:
> - Enables more verbose log mesages for LV1 hypercall results.
> + Enables more verbose log messages for LV1 hypercall results.
Looks good. Thanks.
Acked by: Geoff Levand <geoff@infradead.org>
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox