Re: [PATCH v7 05/12] powerpc/vas: Define helpers to init window context

[Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>]

Michael Ellerman [mpe@ellerman.id.au] wrote:
> Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> writes:
> > diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
> > index a3a705a..3a50d6a 100644
> > --- a/arch/powerpc/platforms/powernv/vas-window.c
> > +++ b/arch/powerpc/platforms/powernv/vas-window.c
> > @@ -11,6 +11,7 @@
> >  #include <linux/mutex.h>
> >  #include <linux/slab.h>
> >  #include <linux/io.h>
> > +#include <linux/log2.h>
> >  
> >  #include "vas.h"
> >  
> > @@ -185,6 +186,310 @@ int map_winctx_mmio_bars(struct vas_window *window)
> >  	return 0;
> >  }
> >  
> > +/*
> > + * Reset all valid registers in the HV and OS/User Window Contexts for
> > + * the window identified by @window.
> > + *
> > + * NOTE: We cannot really use a for loop to reset window context. Not all
> > + *	 offsets in a window context are valid registers and the valid
> > + *	 registers are not sequential. And, we can only write to offsets
> > + *	 with valid registers (or is that only in Simics?).
> 
> I assume there's no "reset everything" register we can write to do this
> for us?

Checked with the hardware team and they said there is no "reset everything"
register. While there are some tricky ways to clear the context, writing
zeroes is the easiest.

> 
> Also if you can clean up the comment to not mention Simics, I would
> assume that applies on real hardware too.
> 
> > + */
> > +void reset_window_regs(struct vas_window *window)
> > +{
> > +	write_hvwc_reg(window, VREG(LPID), 0ULL);
> > +	write_hvwc_reg(window, VREG(PID), 0ULL);
> > +	write_hvwc_reg(window, VREG(XLATE_MSR), 0ULL);
> > +	write_hvwc_reg(window, VREG(XLATE_LPCR), 0ULL);
> > +	write_hvwc_reg(window, VREG(XLATE_CTL), 0ULL);
> > +	write_hvwc_reg(window, VREG(AMR), 0ULL);
> > +	write_hvwc_reg(window, VREG(SEIDR), 0ULL);
> > +	write_hvwc_reg(window, VREG(FAULT_TX_WIN), 0ULL);
> > +	write_hvwc_reg(window, VREG(OSU_INTR_SRC_RA), 0ULL);
> > +	write_hvwc_reg(window, VREG(HV_INTR_SRC_RA), 0ULL);
> > +	write_hvwc_reg(window, VREG(PSWID), 0ULL);
> > +	write_hvwc_reg(window, VREG(SPARE1), 0ULL);
> > +	write_hvwc_reg(window, VREG(SPARE2), 0ULL);
> > +	write_hvwc_reg(window, VREG(SPARE3), 0ULL);
> > +	write_hvwc_reg(window, VREG(SPARE4), 0ULL);
> > +	write_hvwc_reg(window, VREG(SPARE5), 0ULL);
> > +	write_hvwc_reg(window, VREG(SPARE6), 0ULL);
> 
> Should we be writing to spare registers? Presumably in a future hardware
> revision they might have some unknown purpose.

Sure, will skip those.

> 
> > +	write_hvwc_reg(window, VREG(LFIFO_BAR), 0ULL);
> > +	write_hvwc_reg(window, VREG(LDATA_STAMP_CTL), 0ULL);
> > +	write_hvwc_reg(window, VREG(LDMA_CACHE_CTL), 0ULL);
> > +	write_hvwc_reg(window, VREG(LRFIFO_PUSH), 0ULL);
> > +	write_hvwc_reg(window, VREG(CURR_MSG_COUNT), 0ULL);
> > +	write_hvwc_reg(window, VREG(LNOTIFY_AFTER_COUNT), 0ULL);
> > +	write_hvwc_reg(window, VREG(LRX_WCRED), 0ULL);
> > +	write_hvwc_reg(window, VREG(LRX_WCRED_ADDER), 0ULL);
> > +	write_hvwc_reg(window, VREG(TX_WCRED), 0ULL);
> > +	write_hvwc_reg(window, VREG(TX_WCRED_ADDER), 0ULL);
> > +	write_hvwc_reg(window, VREG(LFIFO_SIZE), 0ULL);
> > +	write_hvwc_reg(window, VREG(WINCTL), 0ULL);
> > +	write_hvwc_reg(window, VREG(WIN_STATUS), 0ULL);
> > +	write_hvwc_reg(window, VREG(WIN_CTX_CACHING_CTL), 0ULL);
> > +	write_hvwc_reg(window, VREG(TX_RSVD_BUF_COUNT), 0ULL);
> > +	write_hvwc_reg(window, VREG(LRFIFO_WIN_PTR), 0ULL);
> > +	write_hvwc_reg(window, VREG(LNOTIFY_CTL), 0ULL);
> > +	write_hvwc_reg(window, VREG(LNOTIFY_PID), 0ULL);
> > +	write_hvwc_reg(window, VREG(LNOTIFY_LPID), 0ULL);
> > +	write_hvwc_reg(window, VREG(LNOTIFY_TID), 0ULL);
> > +	write_hvwc_reg(window, VREG(LNOTIFY_SCOPE), 0ULL);
> > +	write_hvwc_reg(window, VREG(NX_UTIL_ADDER), 0ULL);
> > +
> > +	/* Skip read-only registers: NX_UTIL and NX_UTIL_SE */
> > +
> > +	/*
> > +	 * The send and receive window credit adder registers are also
> > +	 * accessible from HVWC and have been initialized above. We don't
> > +	 * need to initialize from the OS/User Window Context, so skip
> > +	 * following calls:
> > +	 *
> > +	 *	write_uwc_reg(window, VREG(TX_WCRED_ADDER), 0ULL);
> > +	 *	write_uwc_reg(window, VREG(LRX_WCRED_ADDER), 0ULL);
> > +	 */
> > +}
> > +
> > +/*
> > + * Initialize window context registers related to Address Translation.
> > + * These registers are common to send/receive windows although they
> > + * differ for user/kernel windows. As we resolve the TODOs we may
> > + * want to add fields to vas_winctx and move the initialization to
> > + * init_vas_winctx_regs().
> > + */
> > +static void init_xlate_regs(struct vas_window *window, bool user_win)
> > +{
> > +	uint64_t lpcr, val;
> > +
> > +	/*
> > +	 * MSR_TA, MSR_US are false for both kernel and user.
> > +	 * MSR_DR and MSR_PR are false for kernel.
> > +	 */
> > +	val = 0ULL;
> > +	val = SET_FIELD(VAS_XLATE_MSR_HV, val, true);
> 
> Using a bool here presumably works, but if you actually wrote:
> 
>   ((u64)true << VAS_XLATE_MSR_HV)
> 
> It would look pretty weird. Using an int would be more normal.

Ok.
> 
> > +	val = SET_FIELD(VAS_XLATE_MSR_SF, val, true);
> > +	if (user_win) {
> > +		val = SET_FIELD(VAS_XLATE_MSR_DR, val, true);
> > +		val = SET_FIELD(VAS_XLATE_MSR_PR, val, true);
> > +	}
> > +	write_hvwc_reg(window, VREG(XLATE_MSR), val);
> > +
> > +	lpcr = mfspr(SPRN_LPCR);
> > +	val = 0ULL;
> > +	/*
> > +	 * NOTE: From Section 5.7.6.1 Segment Lookaside Buffer of the
> > +	 *	 Power ISA, v2.07, Page size encoding is 0 = 4KB, 5 = 64KB.
> 
> Which is 5.7.8.1 in ISA v3.0B.

Ok.
> 
> > +	 *
> > +	 * NOTE: From Section 1.3.1, Address Translation Context of the
> > +	 *	 Nest MMU Workbook, LPCR_SC should be 0 for Power9.
> > +	 */
> > +	val = SET_FIELD(VAS_XLATE_LPCR_PAGE_SIZE, val, 5);
> > +	val = SET_FIELD(VAS_XLATE_LPCR_ISL, val, lpcr & LPCR_ISL);
> > +	val = SET_FIELD(VAS_XLATE_LPCR_TC, val, lpcr & LPCR_TC);
> > +	val = SET_FIELD(VAS_XLATE_LPCR_SC, val, 0);
> > +	write_hvwc_reg(window, VREG(XLATE_LPCR), val);
> > +
> > +	/*
> > +	 * Section 1.3.1 (Address translation Context) of NMMU workbook.
> > +	 *	0b00	Hashed Page Table mode
> > +	 *	0b01	Reserved
> > +	 *	0b10	Radix on HPT
> > +	 *	0b11	Radix on Radix
> > +	 */
> > +	val = 0ULL;
> > +	val = SET_FIELD(VAS_XLATE_MODE, val, radix_enabled() ? 3 : 2);
> > +	write_hvwc_reg(window, VREG(XLATE_CTL), val);
> > +
> > +	/*
> > +	 * TODO: Can we mfspr(AMR) even for user windows?
> > +	 */
> > +	val = 0ULL;
> > +	val = SET_FIELD(VAS_AMR, val, mfspr(SPRN_AMR));
> > +	write_hvwc_reg(window, VREG(AMR), val);
> > +
> > +	val = 0ULL;
> > +	val = SET_FIELD(VAS_SEIDR, val, 0);
> > +	write_hvwc_reg(window, VREG(SEIDR), val);
> > +}
> > +
> > +/*
> > + * Initialize Reserved Send Buffer Count for the send window. It involves
> > + * writing to the register, reading it back to confirm that the hardware
> > + * has enough buffers to reserve. See section 1.3.1.2.1 of VAS workbook.
> > + *
> > + * Since we can only make a best-effort attempt to fulfill the request,
> > + * we don't return any errors if we cannot.
> > + *
> > + * TODO: Reserved (aka dedicated) send buffers are not supported yet.
> > + */
> > +static void init_rsvd_tx_buf_count(struct vas_window *txwin,
> > +				struct vas_winctx *winctx)
> > +{
> > +	write_hvwc_reg(txwin, VREG(TX_RSVD_BUF_COUNT), 0ULL);
> > +}
> > +
> > +/*
> > + * init_winctx_regs()
> > + *	Initialize window context registers for a receive window.
> > + *	Except for caching control and marking window open, the registers
> > + *	are initialized in the order listed in Section 3.1.4 (Window Context
> > + *	Cache Register Details) of the VAS workbook although they don't need
> > + *	to be.
> > + *
> > + * Design note: For NX receive windows, NX allocates the FIFO buffer in OPAL
> > + *	(so that it can get a large contiguous area) and passes that buffer
> > + *	to kernel via device tree. We now write that buffer address to the
> > + *	FIFO BAR. Would it make sense to do this all in OPAL? i.e have OPAL
> > + *	write the per-chip RX FIFO addresses to the windows during boot-up
> > + *	as a one-time task? That could work for NX but what about other
> > + *	receivers?  Let the receivers tell us the rx-fifo buffers for now.
> 
> Why did we do it that way?
> 
> If I'm reading the skiboot code right, the "large contiguous area" is 32K.
> 
> That's less than a single page?!

I guess it is because the FIFO can get larger in the future?

Ccing Haren.

Thanks

Sukadev

> 
> 
> cheers