diff mbox series

[v4,1/3] powerpc/book3s64/radix/tlb: tlbie primitives for process-scoped invalidations from guests

Message ID 20210215063542.3642366-2-bharata@linux.ibm.com
State Changes Requested
Headers show
Series Support for H_RPT_INVALIDATE in PowerPC KVM | expand

Commit Message

Bharata B Rao Feb. 15, 2021, 6:35 a.m. UTC
H_RPT_INVALIDATE hcall needs to perform process scoped tlbie
invalidations of L1 and nested guests from L0. This needs RS register
for TLBIE instruction to contain both PID and LPID. Introduce
primitives that execute tlbie instruction with both PID
and LPID set in prepartion for H_RPT_INVALIDATE hcall.

While we are here, move RIC_FLUSH definitions to header file
and introduce helper rpti_pgsize_to_psize() that will be needed
by the upcoming hcall.

Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
---
 .../include/asm/book3s/64/tlbflush-radix.h    |  18 +++
 arch/powerpc/mm/book3s64/radix_tlb.c          | 122 +++++++++++++++++-
 2 files changed, 136 insertions(+), 4 deletions(-)

Comments

kernel test robot Feb. 15, 2021, 1:10 p.m. UTC | #1
Hi Bharata,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on kvm/linux-next]
[also build test ERROR on v5.11]
[cannot apply to powerpc/next next-20210212]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Bharata-B-Rao/Support-for-H_RPT_INVALIDATE-in-PowerPC-KVM/20210215-143815
base:   https://git.kernel.org/pub/scm/virt/kvm/kvm.git linux-next
config: powerpc64-randconfig-r005-20210215 (attached as .config)
compiler: clang version 12.0.0 (https://github.com/llvm/llvm-project c9439ca36342fb6013187d0a69aef92736951476)
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # install powerpc64 cross compiling tool for clang build
        # apt-get install binutils-powerpc64-linux-gnu
        # https://github.com/0day-ci/linux/commit/2a2c1320dc2bc67ec962721c39e7639cc1abfa9d
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Bharata-B-Rao/Support-for-H_RPT_INVALIDATE-in-PowerPC-KVM/20210215-143815
        git checkout 2a2c1320dc2bc67ec962721c39e7639cc1abfa9d
        # save the attached .config to linux build tree
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=powerpc64 

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All errors (new ones prefixed by >>):

>> arch/powerpc/mm/book3s64/radix_tlb.c:399:20: error: unused function '_tlbie_pid_lpid' [-Werror,-Wunused-function]
   static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid,
                      ^
>> arch/powerpc/mm/book3s64/radix_tlb.c:643:20: error: unused function '_tlbie_va_range_lpid' [-Werror,-Wunused-function]
   static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end,
                      ^
   2 errors generated.


vim +/_tlbie_pid_lpid +399 arch/powerpc/mm/book3s64/radix_tlb.c

   398	
 > 399	static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid,
   400					   unsigned long ric)
   401	{
   402		asm volatile("ptesync" : : : "memory");
   403	
   404		/*
   405		 * Workaround the fact that the "ric" argument to __tlbie_pid
   406		 * must be a compile-time contraint to match the "i" constraint
   407		 * in the asm statement.
   408		 */
   409		switch (ric) {
   410		case RIC_FLUSH_TLB:
   411			__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
   412			fixup_tlbie_pid_lpid(pid, lpid);
   413			break;
   414		case RIC_FLUSH_PWC:
   415			__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
   416			break;
   417		case RIC_FLUSH_ALL:
   418		default:
   419			__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL);
   420			fixup_tlbie_pid_lpid(pid, lpid);
   421		}
   422		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
   423	}
   424	struct tlbiel_pid {
   425		unsigned long pid;
   426		unsigned long ric;
   427	};
   428	

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
David Gibson Feb. 17, 2021, 12:24 a.m. UTC | #2
On Mon, Feb 15, 2021 at 12:05:40PM +0530, Bharata B Rao wrote:
> H_RPT_INVALIDATE hcall needs to perform process scoped tlbie
> invalidations of L1 and nested guests from L0. This needs RS register
> for TLBIE instruction to contain both PID and LPID. Introduce
> primitives that execute tlbie instruction with both PID
> and LPID set in prepartion for H_RPT_INVALIDATE hcall.
> 
> While we are here, move RIC_FLUSH definitions to header file
> and introduce helper rpti_pgsize_to_psize() that will be needed
> by the upcoming hcall.
> 
> Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
> ---
>  .../include/asm/book3s/64/tlbflush-radix.h    |  18 +++
>  arch/powerpc/mm/book3s64/radix_tlb.c          | 122 +++++++++++++++++-
>  2 files changed, 136 insertions(+), 4 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> index 94439e0cefc9..aace7e9b2397 100644
> --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> @@ -4,6 +4,10 @@
>  
>  #include <asm/hvcall.h>
>  
> +#define RIC_FLUSH_TLB 0
> +#define RIC_FLUSH_PWC 1
> +#define RIC_FLUSH_ALL 2
> +
>  struct vm_area_struct;
>  struct mm_struct;
>  struct mmu_gather;
> @@ -21,6 +25,20 @@ static inline u64 psize_to_rpti_pgsize(unsigned long psize)
>  	return H_RPTI_PAGE_ALL;
>  }
>  
> +static inline int rpti_pgsize_to_psize(unsigned long page_size)
> +{
> +	if (page_size == H_RPTI_PAGE_4K)
> +		return MMU_PAGE_4K;
> +	if (page_size == H_RPTI_PAGE_64K)
> +		return MMU_PAGE_64K;
> +	if (page_size == H_RPTI_PAGE_2M)
> +		return MMU_PAGE_2M;
> +	if (page_size == H_RPTI_PAGE_1G)
> +		return MMU_PAGE_1G;
> +	else
> +		return MMU_PAGE_64K; /* Default */
> +}

Would it make sense to put the H_RPT_PAGE_ tags into the
mmu_psize_defs table and scan that here, rather than open coding the
conversion?

> +
>  static inline int mmu_get_ap(int psize)
>  {
>  	return mmu_psize_defs[psize].ap;
> diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
> index fb66d154b26c..097402435303 100644
> --- a/arch/powerpc/mm/book3s64/radix_tlb.c
> +++ b/arch/powerpc/mm/book3s64/radix_tlb.c
> @@ -18,10 +18,6 @@
>  #include <asm/cputhreads.h>
>  #include <asm/plpar_wrappers.h>
>  
> -#define RIC_FLUSH_TLB 0
> -#define RIC_FLUSH_PWC 1
> -#define RIC_FLUSH_ALL 2
> -
>  /*
>   * tlbiel instruction for radix, set invalidation
>   * i.e., r=1 and is=01 or is=10 or is=11
> @@ -128,6 +124,21 @@ 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;
> @@ -188,6 +199,23 @@ 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)
>  {
> @@ -233,6 +261,22 @@ 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)
>  {
>  	/*
> @@ -252,6 +296,25 @@ 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)
> @@ -342,6 +405,31 @@ 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;
> @@ -467,6 +555,20 @@ 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)
>  {
> @@ -547,6 +649,18 @@ 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,
Bharata B Rao Feb. 22, 2021, 6:25 a.m. UTC | #3
On Wed, Feb 17, 2021 at 11:24:48AM +1100, David Gibson wrote:
> On Mon, Feb 15, 2021 at 12:05:40PM +0530, Bharata B Rao wrote:
> > H_RPT_INVALIDATE hcall needs to perform process scoped tlbie
> > invalidations of L1 and nested guests from L0. This needs RS register
> > for TLBIE instruction to contain both PID and LPID. Introduce
> > primitives that execute tlbie instruction with both PID
> > and LPID set in prepartion for H_RPT_INVALIDATE hcall.
> > 
> > While we are here, move RIC_FLUSH definitions to header file
> > and introduce helper rpti_pgsize_to_psize() that will be needed
> > by the upcoming hcall.
> > 
> > Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
> > ---
> >  .../include/asm/book3s/64/tlbflush-radix.h    |  18 +++
> >  arch/powerpc/mm/book3s64/radix_tlb.c          | 122 +++++++++++++++++-
> >  2 files changed, 136 insertions(+), 4 deletions(-)
> > 
> > diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> > index 94439e0cefc9..aace7e9b2397 100644
> > --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> > +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> > @@ -4,6 +4,10 @@
> >  
> >  #include <asm/hvcall.h>
> >  
> > +#define RIC_FLUSH_TLB 0
> > +#define RIC_FLUSH_PWC 1
> > +#define RIC_FLUSH_ALL 2
> > +
> >  struct vm_area_struct;
> >  struct mm_struct;
> >  struct mmu_gather;
> > @@ -21,6 +25,20 @@ static inline u64 psize_to_rpti_pgsize(unsigned long psize)
> >  	return H_RPTI_PAGE_ALL;
> >  }
> >  
> > +static inline int rpti_pgsize_to_psize(unsigned long page_size)
> > +{
> > +	if (page_size == H_RPTI_PAGE_4K)
> > +		return MMU_PAGE_4K;
> > +	if (page_size == H_RPTI_PAGE_64K)
> > +		return MMU_PAGE_64K;
> > +	if (page_size == H_RPTI_PAGE_2M)
> > +		return MMU_PAGE_2M;
> > +	if (page_size == H_RPTI_PAGE_1G)
> > +		return MMU_PAGE_1G;
> > +	else
> > +		return MMU_PAGE_64K; /* Default */
> > +}
> 
> Would it make sense to put the H_RPT_PAGE_ tags into the
> mmu_psize_defs table and scan that here, rather than open coding the
> conversion?

I will give this a try and see how it looks.

Otherwise the changes in the patch which are mainly about
introducing primitives that require to set both PID and LPID
for tlbie instruction - do they look right?

Regards,
Bharata.
diff mbox series

Patch

diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 94439e0cefc9..aace7e9b2397 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -4,6 +4,10 @@ 
 
 #include <asm/hvcall.h>
 
+#define RIC_FLUSH_TLB 0
+#define RIC_FLUSH_PWC 1
+#define RIC_FLUSH_ALL 2
+
 struct vm_area_struct;
 struct mm_struct;
 struct mmu_gather;
@@ -21,6 +25,20 @@  static inline u64 psize_to_rpti_pgsize(unsigned long psize)
 	return H_RPTI_PAGE_ALL;
 }
 
+static inline int rpti_pgsize_to_psize(unsigned long page_size)
+{
+	if (page_size == H_RPTI_PAGE_4K)
+		return MMU_PAGE_4K;
+	if (page_size == H_RPTI_PAGE_64K)
+		return MMU_PAGE_64K;
+	if (page_size == H_RPTI_PAGE_2M)
+		return MMU_PAGE_2M;
+	if (page_size == H_RPTI_PAGE_1G)
+		return MMU_PAGE_1G;
+	else
+		return MMU_PAGE_64K; /* Default */
+}
+
 static inline int mmu_get_ap(int psize)
 {
 	return mmu_psize_defs[psize].ap;
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index fb66d154b26c..097402435303 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -18,10 +18,6 @@ 
 #include <asm/cputhreads.h>
 #include <asm/plpar_wrappers.h>
 
-#define RIC_FLUSH_TLB 0
-#define RIC_FLUSH_PWC 1
-#define RIC_FLUSH_ALL 2
-
 /*
  * tlbiel instruction for radix, set invalidation
  * i.e., r=1 and is=01 or is=10 or is=11
@@ -128,6 +124,21 @@  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;
@@ -188,6 +199,23 @@  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)
 {
@@ -233,6 +261,22 @@  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)
 {
 	/*
@@ -252,6 +296,25 @@  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)
@@ -342,6 +405,31 @@  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;
@@ -467,6 +555,20 @@  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)
 {
@@ -547,6 +649,18 @@  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,